Every source behind the read

Every source GILD analyzed, newest first. Each says who the source is, how it knows, whether it still applies and which findings it counts toward. Open a count to see only its sources.

Source

95 sources in All practitioners, with product documentation Showing all 95 sources

Positive
Taylor Otwell, creator of Laravel
Post on moving Omega development to the cloudX post
Moved his dev work to the cloud, tried Claude and Amp, and kept Amp because it got his workspace scripted while Claude kept hitting snags. He works across 5 repositories and finds orbs less locked down than a sandbox.
"Stuck with Amp because it was able to help me get my workspace scripted and working well - Claude was close but I just kept hitting random snags."
Excerpt, Taylor Otwell
Published Oct 7, 2026self-described: Laravel product work across 5 repositories with multiple agents
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Operational control, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-10-07
Counts toward
Adoption and upkeep, setup: favorable, G1 (1 unit before bounds)
Counts toward
Delivered outcomes, context handling: favorable, G2 (2 units before bounds)
Counts toward
Operational control, execution control: favorable, G1 (1 unit before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs, October 2026
Positive
cavoirom, Hacker News commenter, self-described
Comment on: Plan mode is deadHacker News comment
Has used Amp since November 2025 and says it needs no plan mode, only conversation.
Published Sep 26, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-26
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Developer Experience: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
fishtoaster, Hacker News commenter
Comment on: Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-AstraHacker News comment
Compared cloud agents from Cursor, Amp, and Hoplite and came away preferring Devin.
Published Sep 11, 2026self-described: First engineer at an early-stage startup
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-11
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs (cloud agents)
Positive
microdrum, Hacker News commenter, self-described
Comment on: Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-AstraHacker News comment
Says Amp has led coding agents for almost a year.
Published Sep 10, 2026
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-09-10
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Result Quality: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
Company founder, co-host of Mostly Technical
147: It's Orbin' TimePodcast episode, Mostly Technical (podcast)
Moved their company work to orbs to keep agents off their laptop and share running threads, but finds the weakest part is Amp's harness, and the ship button is loose.
"…button, but the ship button just does just injects a prompt. So it can do literally anything you want. And so it says yeah, it just says pull down uh fix any merge issues, you know, push it back up. Uh you don't need to…"
Transcript excerpt, at 1:01:26Partial support
Published Sep 1, 2026self-described: Their company's app work; the company's CTO tried orbs first
Practitioner account, self-described; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Amp found in GILD's check; Opinion
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-09-01
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Podcasts, Talks & Videos
Who
Very small team
Evidence
Reported
Applies to
Current
Observed on
Amp orbs and portals
Positive
josevalerio, Hacker News commenter, self-described
Comment on: OrbsHacker News comment
Finds orbs more consistent than Codex cloud, alongside Cursor's cloud agents.
Published Aug 30, 2026
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-08-30
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Orbs & Cloud Agents: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs
Positive
altschuler, Hacker News commenter, self-described
Comment on: OrbsHacker News comment
Finds orbs fantastic for portals, multiplayer, local syncing, and Puck, and calls Amp the best US$20 a month they spend on dev tools.
Published Aug 30, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-30
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
US$20 per month subscription, orbs
Positive
cavoirom, Hacker News commenter, self-described
Comment on: Our decision on Cursor following its acquisition by SpaceXHacker News comment
Recommends Amp although it is not popular on Hacker News, saying people who try it will not go back, though the price may be a bit expensive.
Published Aug 29, 2026
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-08-29
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Usage / Cost: Raised as a concern
- Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
Joey Kudish, software developer with 20 years of experience
Post on moving project work to AmpX post
Is moving most of his project work to Amp orbs and writing custom plugins and infrastructure to manage them, keeping Codex for occasional local work and computer use.
"I think I'm ready to move most of my project work to @AmpCode. I'm even writing some custom plugins and custom infra around it to better manage my orbs the way i need them to work."
Excerpt, Joey Kudish
Published Aug 18, 2026self-described: Independent developer running several products; also uses Codex
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-18
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs with a linked ChatGPT subscription, August 2026
Positive
JJ Englert, Enablement Lead at Tenex
Post on the team's use of Amp orbsX post
Says his team is loving Amp's orbs, one of the few tools they found that makes moving work off local machines and into the cloud easy.
"Our team is loving amp right now, specifically how their orbs work."
Excerpt, JJ Englert
Published Aug 18, 2026self-described: AI consulting firm team moving work from local machines to the cloud
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-18
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Orbs & Cloud Agents: Positive
Published on
Developer Communities
Who
Professional team
Evidence
Reported
Applies to
Current
Observed on
Amp orbs, August 2026
Positive
Andrzej Krzywda, CEO of Arkency
Post on an agent recording a bug video in an orbX post
Had the Amp agent find a bug and then record a video of it inside an orb, a workflow he says orbs made frictionless.
"Having the agent finding the bug, then record a video of a bug, this is a new addition to my toolbox."
Excerpt, Andrzej Krzywda
Published Aug 16, 2026Rails consultancy working on large legacy Rails applications
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-16
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relevance
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs, August 2026
Positive
Ravindra Barthwal, founder building dxcode
Post to the Amp team on orbsX post
Found Amp good but costly in the past. After 4 days on the US$20 plan he gets a lot of value, with one orb working for over 4 days and coordinating with other orbs.
"In just $20 I am getting ton of value. One of my orb is working for over 4 days now and co-coordinating with other orbs…"
Excerpt, Ravindra Barthwal
Published Aug 15, 2026self-described: Has tried Cursor, Devin, Codex, Claude, and other cloud agents
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Competitor staff: not counted as independent; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
competitor employee (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-15
Counts toward
Reliability, run stability: favorable, G1 (1 unit before bounds), capped: C-relevance
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp US$20 subscription with orbs, August 2026
Mixed
navs, Hacker News commenter
Comment on: How Compaction Works in PiHacker News comment
Says Amp had a handoff feature for a while that they found genuinely useful and, anecdotally, felt worked better than compaction, until Amp removed it.
Published Aug 14, 2026self-described: Software engineer in Australia, New Zealand and Fiji
Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-14
Counts toward
Adoption and upkeep, continuity: unfavorable, G1 (1 unit before bounds)
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
r5Khe, Hacker News commenter, self-described
Comment on: Launch HN: Hoplite (YC S26) - Effortlessly deploy cloud coding agentsHacker News comment
Has used Amp for a while, says Amp "seems to be doing something very similar" to the cloud agent tool being launched, and calls one thread per VM a solid model going forward.
Published Aug 3, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-03
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Orbs & Cloud Agents: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs
Positive
Andrei Maxim, applied AI engineer and former Ruby developer
The State of Agents in the CloudX post (X article)
After two weeks on Amp, set up orbs, Claude Code cloud, and Codex cloud side by side. Amp generated its own orb setup scripts and orbs just worked, which he rates well above the other two cloud agents.
"All in all, Amp with Orbs feels significantly above the current state of agents in the cloud, much like the jump from Opus 4.1 to 4.5 from late last year."
Excerpt, Andrei Maxim
Published Aug 3, 2026self-described: Compared Amp orbs with Claude Code and Codex cloud environments on his own projects
Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-03
Counts toward
Adoption and upkeep, setup: mixed, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs and CLI local runner, July 2026
Positive
Developer, formerly at Heptabase
AmpCode is coolPersonal blog post, blog.ianhsiao.me
Uses orbs and thread-to-thread messaging to move work between local and remote machines, and credits Amp for removing features as models improve.
Published Jul 31, 2026self-described: Builds their own app; uses orbs from an iPad
Practitioner account, self-described; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Amp partner: not counted as independent; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
program member (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-31
Counts toward
Adoption and upkeep, continuity: mixed, G1 (1 unit before bounds), capped: C-relationship
Not counted
Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Cost predictability and limits, cost transparency: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Operational control, models and deployment: excluded, praise from someone tied to the vendor, kept as an attributed position
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs, Puck, ChatGPT subscription linking
Positive
Mike Hostetler, founder and Elixir agent framework builder
Amp Got Cloud Coding Sandboxes RightX post (X article)
Pointed an orb at his ReqLLM repository: Amp prepared the environment with a skill, made the change, and pushed it to GitHub with permissions in place. His complaints were a large default orb size and a confusing project screen.
"The agent made the requested change, committed the code, and pushed it back to GitHub with the permissions already in place."
Excerpt, Mike Hostetler
Published Jul 20, 2026self-described: Maintains several open-source Elixir repositories, including ReqLLM
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Operational control, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-20
Counts toward
Adoption and upkeep, setup: mixed, G2 (2 units before bounds)
Counts toward
Operational control, execution control: favorable, G1 (1 unit before bounds)
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relevance
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp orbs, July 2026
Mixed
anamexis, Hacker News commenter, self-described
Comment on: Claude Code uses Bun written in Rust nowHacker News comment
Chooses Claude Code over Codex, OpenCode, and Amp mainly for its user experience.
Published Jul 19, 2026
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-07-19
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
usef-, Hacker News commenter, self-described
Comment on: Claude Sonnet 5Hacker News comment
Recalls that Amp picked the best model for each task and that its CLI steered users toward good practice, such as replacing a context clear with a handoff.
Published Jul 1, 2026
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-01
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
nl, Hacker News commenter
Comment on: GLM 5.2 beats Claude in our benchmarksHacker News comment
Says they are a big fan of Amp while discussing which model it uses for search.
Published Jun 29, 2026self-described: Former ML startup founder and former startup CTO
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion; Specific details; Observed on Flash
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
1 artifact (organization page)
Date and version
2026-06-29, Flash
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
nixosbestos, Hacker News commenter, self-described
Comment on: Sakana FuguHacker News comment
Just uses Amp: asks it to do things and it does them.
Published Jun 22, 2026
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-22
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Evaluated as an engineering agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
Software engineer
Amp vs Claude Code: Is It Worth Switching in 2026?Personal blog post, alexdunlop.com
Ran Amp and Claude Code on the same Python task: Amp's model routing and visible subagents stood out, it felt expensive, and both failed on ruff.
Published Jun 15, 2026self-described: Solo build of a multi-agent setup with an MCP server and a web frontend
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-15
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, data control: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Adoption and upkeep, continuity: unfavorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Not counted
Operational control, admin control: repeats a stronger account in its group
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp CLI, pay-as-you-go; updated August 2026 for subscriptions
Negative
mutant, Hacker News commenter, self-described
Comment on: Is Amp more or less expensive than Claude Code? Is it better?Hacker News comment
Did not find much use in Amp and prefers Pi with extensions.
Published May 28, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-28
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
SatvikBeri, Hacker News commenter, self-described
Comment on: Elevated error rates on Opus 4.7Hacker News comment
Has used Amp a bit and finds it quite nice, but more expensive than Claude without a subsidized subscription, so they have little reason to switch.
Published May 15, 2026
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-15
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
Hugo Santos, Founder and CEO of Namespace
CI/CD Is Dead, Agents Need Continuous Compute and ComputersConference talk page with transcript, AI Engineer Europe 2026
Says Namespace's team already works without pull requests: a written spec goes into an agent harness, often Amp since the team is a big Amp fan. The agent checks out a well-known commit, implements the plan, builds and tests it, then asks a human whether to continue.
"We're, we're a big Amp fl- fan, so in our case, it's often Amp."
Excerpt, Hugo Santos
"Uh, this is already how our team is working today and how we see a lot of the companies working today already…"
Same speaker
Published May 13, 2026Namespace, a build and test compute infrastructure company whose team works from specs through agent loops
Practitioner account, self-described; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly
Role
Name self-described; employer self-described; role self-described (Hugo Santos · Founder & CEO , Namespace)
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-23
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Evaluated as an engineering agent
- Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Published on
Podcasts, Talks & Videos
Who
Technical leadership
Evidence
Reported
Applies to
Current
Observed on
Amp as the agent harness in Namespace's own spec-to-validation loop
Positive
ahmadyan, Hacker News commenter
Comment on: DeepClaude - Claude Code agent loop with DeepSeek V4 ProHacker News comment
Finds the same Opus model works better in third-party harnesses such as Amp and Factory Droid than in Claude Code.
Published May 4, 2026self-described: Maker of Agentastic
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Observed on opus
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-04, opus
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Result Quality: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
Jo Kristian Bergum, CEO of Hornet
Post on migrating off AmpX post
Says Amp declared coding agents dead without any clear path for what that means, so the author's team migrated off Amp to Codex and Claude Code, primitives closer to the models.
"…they announced it without any clear path what does it even mean, so we migrated off Amp to primitives closer to the models (codex and claude code)…"
Excerpt, Jo Kristian Bergum
Published Mar 25, 2026Hornet, a Trondheim startup building a retrieval engine for agents
Practitioner account, pseudonymous; ran the rollout; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Ran the rollout
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Ran the rollout
Support
No artifact or independent corroboration recorded
Date and version
2026-03-25
Counts toward
Adoption and upkeep, continuity: unfavorable, G1 (1 unit before bounds)
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Technical leadership
Evidence
Reported
Applies to
Current
Observed on
Amp, March 2026, after Amp's announcement about the end of coding agents
Positive
shell0x, Hacker News commenter, self-described
Comment on: How I write software with LLMsHacker News comment
Has used Codex and Claude Max but keeps returning to Amp, which routes models by mode and often gets things right on the first attempt.
Published Mar 16, 2026
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
1 artifact (organization page)
Date and version
2026-03-16
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
DFilipeS, Hacker News commenter, self-described
Comment on: Show HN: Praxis, my personal take on Compound Engineering with AIHacker News comment
Built their own compound engineering workflow tool with the help of the Amp CLI.
Published Feb 24, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Observed on Amp Code CLI
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-24, Amp Code CLI
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Evaluated as an engineering agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Amp CLI
Positive
_smertens_, Hacker News commenter, self-described
Comment on: Show HN: Tlsctl - A CLI for inspecting and troubleshooting TLSHacker News comment
Built tlsctl, a TLS diagnostics CLI, partly to gain hands-on experience with agentic engineering, and credits Amp as the coding agent.
Published Feb 22, 2026
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-02-22
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Evaluated as an engineering agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
SatvikBeri, Hacker News commenter, self-described
Comment on: Claude Code's compaction discards data that's still on diskHacker News comment
Uses Amp over Claude Code for its thread tree and handoff, which keep each session focused and context low; finds Claude Code's compaction worse.
Published Feb 21, 2026
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-21
Counts toward
Delivered outcomes, context handling: favorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Threads & Handoff: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
jauntywundrkind, Hacker News commenter, self-described
Comment on: Amp Free Is FullHacker News comment
Calls Amp an amazing product they love recommending, praising handoff, threads and sharing, and the Oracle. Says people sign up right away once told about the free, ad-supported plan.
Published Feb 11, 2026
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion; Specific details; Observed on Amp Free
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-02-11, Amp Free
Not counted
Cost predictability and limits, cost transparency: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Oracle & Model Routing: Positive
- Threads & Handoff: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
4b11b4, Hacker News commenter, self-described
Comment on: Claude Code is being dumbed down?Hacker News comment
Says Amp feels much better than Claude Code and likes that a message reaches the agent as soon as they send it.
Published Feb 11, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-11
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Developer Experience: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
asadjb, Hacker News commenter, self-described
Comment on: Review-for-agent: A local, PR-style UI for reviewing AI agent code changesHacker News comment
Liked the Codex app's inline diff comments but prefers working in Amp, so they built a local review tool that works with any agent.
Published Feb 10, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-10
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
Independent developer
I keep coming back to Amp CodePersonal blog post, Jibran's Perspective (asadjb.com)
Compared Amp, Claude Code, and Codex on the same tasks and enjoyed Amp most; cost pushed them to Claude Max, but they plan to return to Amp.
Published Feb 8, 2026self-described: Solo; also uses Claude Code (Max) and Codex
Practitioner account; direct use; counts toward Delivered outcomes, Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Customer of Amp; Used it directly; Specific details; Observed on Claude Opus 4.6
Role
Name unknown; employer unknown; role unknown
Relationship
customer (self disclosed); customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-08, Claude Opus 4.6
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship, C-unknown-control
Counts toward
Cost predictability and limits, cost transparency: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Operational control, models and deployment: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Adoption and upkeep, continuity: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Measured
Applies to
Current
Observed on
Amp smart mode with Claude Opus 4.6, pay-as-you-go
Positive
Developer
Should You Use Ampcode for Production Code? One Month InPersonal blog post, IntelligentTools
After a month with both Cursor and Amp, uses Amp for refactorings and architectural changes that touch many files, and Deep mode almost exclusively for production work. Runs Amp on a dedicated branch and reviews every commit before merging to main.
Published Feb 7, 2026self-described: Healthcare software work; runs Amp on a dedicated branch
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-07
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Delivered outcomes, context handling: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Adoption and upkeep, continuity: mixed, G2 (2 units before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, data control: mixed, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Not counted
Adoption and upkeep, setup: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp CLI and VS Code extension, deep mode
Mixed
zingar, Hacker News commenter, self-described
Comment on: Claude Code: connect to a local model when your quota runs outHacker News comment
Switches from a Claude Pro plan to Amp Free about two thirds of the way through each day and finds the change in ergonomics jarring.
Published Feb 4, 2026
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Observed on amp free
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-04, amp free
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Usage / Cost: Discussed without concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp Free as overflow after Claude Pro limits
Mixed
Web developer
AMP vs Claude Code (CLI): Comparing of Agentic Coding ToolsPersonal blog post, cesarcouto.com
Ran Amp and Claude Code with the same models, repository, and AGENTS.md; Amp was faster, cleaner, and needed fewer fixes, but only its free tier made it affordable.
Published Jan 21, 2026self-described: Professional web development; over 95 percent of their code is AI-generated
Practitioner account, self-described; structured test; counts toward Delivered outcomes, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Observed on free tier; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
customer (self disclosed)
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-01-21, free tier
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, correctness: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, execution control: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, models and deployment: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp CLI on Amp Free, Claude Opus 4.5
Mixed
Developer and YouTube creator
Coding with Claude Opus 4.5 For Free! (AmpCode)Video, YouTube
Uses the Amp extension's free daily US$10 for a few Opus 4.5 requests beside their main tool, and dislikes the CLI.
"…run the code. It has two modes. Smart that uses OPUS 4.5, GBT 5.2 and also RAS which uses smaller models like Hiku 4.5. Now, this is super powerful because $10 of free usage every single day means you could use Oppus 4.5 and JP…"
Transcript excerpt, at 1:05Partial support
Published Jan 19, 2026self-described: Solo
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Amp found in GILD's check; Used it directly; Specific details; Observed on OPUS 4.5
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-19, OPUS 4.5
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, task completion: mixed, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Podcasts, Talks & Videos
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp extension in Antigravity, Amp Free
Positive
weiliddat, Hacker News commenter, self-described
Comment on: OpenAI will start testing ads in ChatGPT free and Go tiersHacker News comment
Uses Amp as their main coding agent outside work on the ad-supported free mode, which moved to a US$10 daily limit with Opus 4.5.
Published Jan 18, 2026
Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details; Observed on Opus 4.5
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-18, Opus 4.5
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Usage / Cost: Discussed without concern
- Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp Free, Opus 4.5
Positive
theshrike79, Hacker News commenter, self-described
Comment on: Unauthenticated remote code execution in OpenCodeHacker News comment
Uses Claude Code and Codex and recommends Amp alongside them for small utility scripts and changes on the free tier.
Published Jan 12, 2026
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-12
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost transparency: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Usage / Cost: Discussed without concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp Free
Positive
tbliu, Hacker News commenter, self-described
Comment on: Anthropic blocks third-party use of Claude Code subscriptionsHacker News comment
Uses Amp's free tier with Opus 4.5 heavily, calls it a very nice CLI, and finds the ads fairly unobtrusive.
Published Jan 9, 2026
Practitioner account, pseudonymous; direct use; counts toward Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details; Observed on Opus 4.5
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
2 artifacts (organization page)
Date and version
2026-01-09, Opus 4.5
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp Free, Opus 4.5, CLI
Positive
truekonrads, Hacker News commenter, self-described
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Loves Amp's results and its opinionated design, including prompts to hand off context, and not being tied to one model.
Published Dec 9, 2025
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-09
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
the_mitsuhiko, Hacker News commenter, self-described
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Thinks Amp is great but pricey, and says it feels like a product its own builders use.
Published Dec 9, 2025
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-12-09
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Developer Experience: Positive
- Usage / Cost: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
incoming1211, Hacker News commenter
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Says their employer pays for Amp and that each member of their team spends more than US$1,000 a month on it.
Published Dec 9, 2025self-described: Engineering team at work
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-09
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Usage / Cost: Discussed without concern
- Is Amp worth what it costs?: Worth it
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Needs a recheck
Observed on
Pay-as-you-go credits paid by the employer
Mixed
sergiotapia, Hacker News commenter, self-described
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Amp was their primary workhorse until they moved to cheaper models in the Claude CLI and then Opus 4.5 directly, spending about US$5 a day on Amp.
Published Dec 9, 2025
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-09
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Mixed
lvl155, Hacker News commenter, self-described
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Found Amp really good in summer 2025 but calls cost its biggest downside and questions what the price buys without its own model.
Published Dec 8, 2025
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-12-08
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Pay-as-you-go credits
Negative
embedding-shape, Hacker News commenter, self-described
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Tried Amp a couple of times, spending US$5, then US$10, then US$20, and says it is so expensive they struggle to judge it fairly. Has ChatGPT Pro and is not stingy with paying for useful things, but Amp is past their limit.
Published Dec 8, 2025
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Amp; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-08
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Pay-as-you-go credits
Positive
incoming1211, Hacker News commenter, self-described
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphHacker News comment
Compares most terminal agents and says Amp costs more but gives the best results, crediting the Librarian and the Oracle.
Published Dec 8, 2025
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-08
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
pjm331, Hacker News commenter, self-described
Comment on: Agent design is still hardHacker News comment
Says Amp started a bit rough but is now really good.
Published Nov 22, 2025
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-22
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Result Quality: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
MorehouseJ09, Founder and CEO of Nuon, Hacker News commenter
Comment on: You should still be writing code from your editorHacker News comment
Is most bullish on Amp because it can be driven from different contexts and its threads beat anything else they have seen.
Published Nov 16, 2025self-described: Founder and CEO of Nuon
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-16
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Threads & Handoff: Positive
Published on
Developer Communities
Who
Technical leadership
Evidence
Reported
Applies to
Still applicable
Positive
Independent developer
Amp Coding Agent: Features That Make It Stand OutPersonal blog post, peterwarnock.com
Says Amp has consistently impressed them, singling out handoff as a better version of Claude Code's compaction and scoped instructions for complex projects.
Published Nov 10, 2025self-described: Engineering lead for CI/CD and DevOps
Practitioner account; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
No tie to Amp found in GILD's check; Used it directly
Role
Name unknown; employer unknown; role unknown
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-10
Counts toward
Delivered outcomes, context handling: favorable, G1 (1 unit before bounds), capped: C-relevance, C-unknown-control
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
Independent developer
Amp: Notes from reading the Amp manualPersonal blog post, hamel.dev
Names threads their favorite Amp feature, finds model abstraction works despite early doubts, and pays per token because the time saved is worth it.
Published Nov 2, 2025self-described: Solo use, including SEO work on their own site
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-02
Counts toward
Cost predictability and limits, cost transparency: mixed, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Operational control, data control: mixed, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Delivered outcomes, context handling: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Counts toward
Adoption and upkeep, ongoing upkeep: favorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Not counted
Adoption and upkeep, setup: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp CLI and VS Code extension, pay per token
Positive
Co-founder of Octoco
Getting Started with AmpPersonal blog post, G-J's Substack
A co-founder's starter guide for Octoco's senior engineers: keep threads short, plan with the Oracle, hand off phases, and expect cost to grow with long threads.
Published Oct 28, 2025self-described: Octoco, senior engineering staff being introduced to Amp
Practitioner account, self-described; direct use; counts toward Reliability, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Needs recheck after 12 months
Role
Name self-described; employer self-described; role self-described (Director of Engineering & Innovation)
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-10-28, Claude Sonnet 4.5; GPT-5, needs a recheck
Counts toward
Operational control, models and deployment: mixed, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Operational control, execution control: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, cost predictability: mixed, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Technical leadership
Evidence
Reported
Applies to
Needs a recheck
Observed on
Main agent Claude Sonnet 4.5 (October 2025)
Positive
hnidiots3, Hacker News commenter, self-described
Comment on: Claude Code on the webHacker News comment
Says having Amp check everything with the Oracle, a second model, gives better results than Codex on backend work.
Published Oct 20, 2025
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion; Specific details; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-10-20, Sonnet 4.5 + GPT-5, needs a recheck
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Oracle & Model Routing: Positive
- Result Quality: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Sonnet 4.5 main agent, GPT-5 Oracle (October 2025)
Positive
WEBdoze, YouTube channel
I Tried the Ad-Supported AI Coding Agent (Amp Free)Video, WEBdoze (YouTube)
Tested Amp Free in the CLI and VS Code extension on a solar panel website, found the free result decent and functional, likes the UI and finds the in-tool ads pretty good. Guesses complex work will still need the paid smart option.
"…this is working. For complex things, I guess you will going to need still the smart option to be enabled. But yeah, you need to add money. I'm curious to see if this uh plan it will work also the free one and the one…"
Transcript excerpt, at 15:24Partial support
Published Oct 17, 2025self-described: Solo, small web projects
Practitioner account, self-described; direct use; counts toward Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-10-17, Amp Free Mode, needs a recheck
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Operational control, data control: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Podcasts, Talks & Videos
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp Free, CLI and web
Positive
Creator of Ghostty
Vibing a Non-Trivial Ghostty FeaturePersonal blog post, mitchellh.com
Built a Ghostty feature with Amp over 16 sessions totalling US$15.98 in token spend, consulting the Oracle for all planning. Guided the agent through cleanup sessions with minor manual changes and merged after a final manual review.
Published Oct 11, 2025self-described: Ghostty, open-source terminal emulator; macOS update notification feature
Practitioner account; direct use; counts toward Delivered outcomes, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Used it directly; Specific details; Needs recheck after 12 months
Role
Name unknown; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-10-11, needs a recheck
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Delivered outcomes, correctness: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Operational control, models and deployment: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Cost predictability and limits, cost predictability: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship, C-unknown-control
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Measured
Applies to
Still applicable
Observed on
Amp with the Oracle (October 2025)
Mixed
Developer
Amp - Vibe Code With Me - Ep 016Video, YouTube
Calls Amp the best coding agent used so far and by far the most expensive, at US$15 in two hours. It was the first test where all the tasks got done, yet the author finds the return hard to justify against Claude Code Max at US$100 a month.
"…could be interesting. But I still think I think I still think it's hard to justify this cost compared to like just giving everybody Claude Max, for example, you know, the 5x or even the 10X. Again, I spent $15 in two hours."
Transcript excerpt, at 2:29:22
Published Oct 6, 2025self-described: Solo, building an expense app on stream
Practitioner account, self-described; structured test; counts toward Delivered outcomes, Reliability, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Amp found in GILD's check; Ran a structured test; Needs recheck after 12 months; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2025-10-06, needs a recheck
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds)
Counts toward
Cost predictability and limits, cost transparency: mixed, G2 (2 units before bounds)
Counts toward
Adoption and upkeep, setup: unfavorable, G1 (1 unit before bounds)
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Not counted
Operational control, execution control: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Podcasts, Talks & Videos
Who
Individual practitioner
Evidence
Measured
Applies to
Needs a recheck
Observed on
Amp CLI, pay-as-you-go
Positive
jeanlucas, Hacker News commenter, self-described
Comment on: Ask HN: What are you working on? (September 2025)Hacker News comment
Tried the terminal agents on a community platform they are building and names Amp their favorite so far.
Published Sep 30, 2025
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-09-30, needs a recheck
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Amp CLI
Mixed
Adam Stacoviak, co-founder and podcast host, Changelog
Changelog #658: Adam Stacoviak on running agents side by sidePodcast episode with publisher transcript
Stacoviak runs Amp beside Claude Code with a product-manager agent reviewing both, uses Claude Code partly because Amp costs him more, and calls Amp's cost justified.
"...in this case one of them was Amp and the other one was Claude Code, because that one's cheaper for me. You're really expensive, by the way."
Transcript excerpt, Adam Stacoviak, around 52:11 in the episode
Published Sep 17, 2025self-described: Changelog, his own long-running project
Counts toward
Published on
Podcasts, Talks & Videos
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
Developer and streamer
Can AMP Code Beat Claude Code? | Feature Build Day 3Video (livestream), YouTube
Tried Amp as a plugin in Cursor to see if it could beat a Claude Code workflow while adding a photo upload feature live. Had Amp turn existing Claude.md files and Cursor rules into AGENTS.md files and calls the agent really, really smooth and really easy.
"This is nice. And now we have a pages, so we have go to app page. I'm just kind of reviewing the code as it's flying in. So client-side validation type, great. Awesome. I think so it just feels smooth I a…"
Transcript excerpt, at 1:02:08Partial support
Published Sep 7, 2025self-described: Solo, building a photo upload feature for their own app
Practitioner account, self-described; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Amp partner: not counted as independent; Used it directly; Needs recheck after 12 months; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
sponsor (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-09-07, Claude Sonnet, needs a recheck
Counts toward
Adoption and upkeep, setup: mixed, G1 (1 unit before bounds)
Not counted
Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Delivered outcomes, correctness: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Delivered outcomes, context handling: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Operational control, models and deployment: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Cost predictability and limits, cost transparency: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Podcasts, Talks & Videos
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Amp in an editor, September 2025
Positive
Mitchell Hashimoto, creator of Ghostty and co-founder of HashiCorp
Post on shared Amp threads in pull requestsX post
Says sharing a whole session globally is the favorite part of Amp, that pull requests with Amp threads attached make Hashimoto very, very happy as a maintainer, and links one from a bug fix that morning.
"PRs with Amp threads attached make me very, very happy as a maintainer."
Excerpt, Mitchell Hashimoto
Published Sep 3, 2025self-described: Maintainer of the Ghostty terminal, reviewing outside pull requests
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-09-03, needs a recheck
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Threads & Handoff: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp public threads, September 2025 (public threads ended June 2, 2026)
Mixed
aitooltrek-com, Hacker News commenter
Comment on: Ask HN: What LLM are you all using for coding assistance right now?Hacker News comment
Tried ChatGPT, Claude, Claude Code, Cursor, and Amp, and kept Claude Code as the daily tool.
Published Aug 13, 2025self-described: Indie maker building an AI tools site
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-08-13, needs a recheck
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
derencius, Hacker News commenter, self-described
Comment on: Getting good results from Claude CodeHacker News comment
Compares terminal agents and rates Amp very good and precise with its changes.
Published Aug 9, 2025
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-08-09, needs a recheck
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Result Quality: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Mixed
pjm331, Hacker News commenter, self-described
Comment on: Jules, our asynchronous coding agentHacker News comment
Finds Amp good but short of Claude Code's polish and features, and reaches for it for code review because of the Oracle.
Published Aug 6, 2025
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-08-06, needs a recheck
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
mark_undoio, CTO of Undo, Hacker News commenter
Comment on: Claude Opus 4.1Hacker News comment
Found that asking Amp to have the Oracle check the main model's debugging work helped, and the main model did better once prompted that way.
Published Aug 5, 2025self-described: CTO of Undo, a record and replay debugging company
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-08-05, Sonnet as its main model and has GPT o3 as a special purpose tool / subagent, needs a recheck
Counts toward
Operational control, models and deployment: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Oracle & Model Routing: Positive
Published on
Developer Communities
Who
Technical leadership
Evidence
Reported
Applies to
Needs a recheck
Observed on
Sonnet main agent, o3 Oracle (August 2025)
Mixed
Johann Rehberger, security researcher (Embrace The Red)
Amp Code: Arbitrary Command Execution via Prompt Injection FixedIndependent security evaluation, Embrace The Red
Found that Amp could write files outside the project folder without approval, so a prompt injection could allowlist bash commands or add a malicious MCP server. Sourcegraph fixed it promptly after his July 2025 report.
"Interestingly, when researching I noticed that Amp can write files outside the project folder without developer approval."
Excerpt, Johann Rehberger
Published Aug 5, 2025self-described: Independent security testing of coding agents during his Month of AI Bugs series
Practitioner account, self-described; structured test; counts toward Operational control, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Specific details; Needs recheck after 12 months
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2025-08-05, needs a recheck
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Adoption and upkeep, continuity: favorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Autonomy & Permissions: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Measured
Applies to
Needs a recheck
Observed on
Amp editor extension, July 2025
Positive
sergiotapia, Hacker News commenter, self-described
Comment on: 6 weeks of Claude CodeHacker News comment
Has used Amp heavily and says it always hits the target.
Published Aug 3, 2025
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-08-03, needs a recheck
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Result Quality: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Amp editor extension
Positive
Independent developer and contributor to the Air framework
Amp Code Deep Dive and TalkPersonal blog post, Elite AI Assisted Coding
Used Amp for a real open-source documentation task that was merged; it fixed a database bug from logs on the first try for US$4.10, though drafts needed trimming.
Published Jul 30, 2025self-described: Open-source documentation task for the Air web framework
Practitioner account, self-described; structured test; counts toward Delivered outcomes, Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Specific details; Needs recheck after 12 months
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2025-07-30, $10 free tier, needs a recheck
Counts toward
Adoption and upkeep, setup: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, correctness: mixed, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, execution control: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp extension in Cursor, US$10 free credit
Mixed
Independent developer maintaining open-source side projects
AI coding agent one-shot challenge with Amp, Claude Code and GeminiPersonal blog post, Land of Unknwon (unknwon.io)
Gave Amp, Claude Code, and Gemini CLI the same one-shot build; Amp matched the template structure best but left a broken app and stopped mid-task.
Published Jul 22, 2025self-described: Solo, side projects
Practitioner account; structured test; counts toward Delivered outcomes, Reliability How GILD checked it
Origin
Published practitioner account
Checked
Ran a structured test; Specific details; Needs recheck after 12 months
Role
Name unknown; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
1 artifact (transcript)
Date and version
2025-07-22, needs a recheck
Counts toward
Delivered outcomes, task completion: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Delivered outcomes, correctness: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Delivered outcomes, context handling: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp CLI, July 2025
Positive
Gys, Hacker News commenter, self-described
Comment on: Ask HN: Why do Cursor, Windsurf and Claude Code dominate the conversation?Hacker News comment
Uses the Amp VS Code plugin and is very happy with it, finding it easier than Claude Code and Cursor, which they tried earlier.
Published Jul 21, 2025
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-07-21, needs a recheck
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp VS Code extension
Positive
d_sc, Hacker News commenter, self-described
Comment on: Cognition (Devin AI) to Acquire WindsurfHacker News comment
Rates Amp very good, highlighting the Oracle that uses o3 for reviews and a team leaning into the agentic approach.
Published Jul 16, 2025
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion; Specific details; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-07-16, needs a recheck
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Oracle & Model Routing: Positive
- Evaluated as an engineering agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Oracle on o3 (July 2025)
Positive
yomismoaqui, Hacker News commenter, self-described
Comment on: AI slows down open source developers. Peter Naur can teach us whyHacker News comment
After several weeks with Claude Code and Amp, says both deliver enough value that paying US$100 a month feels like a bargain.
Published Jul 14, 2025
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-07-14, needs a recheck
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Is Amp worth what it costs?: Worth it
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
mrklol, Hacker News commenter, self-described
Comment on: Clarifying our pricingHacker News comment
Tells others to just switch to Amp, saying its agent is superior in every way and its tooling achieves even more although it uses the same models.
Published Jul 5, 2025
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Opinion; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-07-05, needs a recheck
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Result Quality: Positive
- Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
yomismoaqui, Hacker News commenter, self-described
Comment on: Claude Code for VSCodeHacker News comment
Spent about 15 euros, including 10 euros of free credit, trying Amp in one day and came away impressed.
Published Jun 23, 2025
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-06-23, needs a recheck
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Usage / Cost: Discussed without concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp VS Code extension, pay-as-you-go credits
Positive
Kieran Klaassen, general manager of Cora at Every
Transcript: 'How Two Engineers Ship Like a Team of 15 With AI Agents'Podcast episode transcript, AI & I (Every)
Ranking AI coding agents on the Every podcast, Klaassen puts Amp in the S tier under Claude Code, saying it is very good at just getting work done, with pretty good ergonomics and good tools already.
"Yes. It's very good at just getting work done. The ergonomics are pretty good, good tools already."
Excerpt, Kieran Klaassen
Published Jun 11, 2025Two-engineer team building Cora, an AI email product at Every, running several coding agents side by side
Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Competitor staff: not counted as independent; Used it directly; Needs recheck after 12 months
Role
Name self-described; employer self-described; role self-described (Member of Frontier Team)
Relationship
program member (self disclosed); program member (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-06-11, needs a recheck
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Podcasts, Talks & Videos
Who
Technical leadership
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp in its first weeks, rated in a tier list of the agents the Cora team uses
Positive
vladstudio, Hacker News commenter
Comment on: Cursor 1.0Hacker News comment
Says Amp took model and prompt configuration off their hands, and that they enjoy AI-assisted coding more because it just works.
Published Jun 5, 2025self-described: Self-employed wallpaper designer
Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Amp found in GILD's check; Used it directly; Needs recheck after 12 months
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Amp found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-06-05, needs a recheck
Counts toward
Adoption and upkeep, setup: favorable, G1 (1 unit before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Developer Experience: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Amp with Claude 4, no model picker (June 2025)

Product documentation 18

Pages from Amp, used to check facts for every group.

Pricing
Lists Hobby (free), Individual at US$20 per month (Megawatt), Teams at no extra charge, and Enterprise at custom pricing, with no Amp token fees when you bring your own keys or subscriptions.
Checked Oct 12, 2026
Docs: Pricing
Bills paid credits at providers' API prices with no markup for individuals and non-enterprise workspaces, bills orbs by the minute, and lists Enterprise controls.
Checked Oct 12, 2026
Docs: Sizes & Costs
Lists orb sizes from a1.tiny at US$0.08 per hour to a1.3xlarge at US$2.13 per hour, billed by the minute, with orbs pausing when idle.
Checked Oct 12, 2026
Modes & Models
Shows the models behind the low, medium, high, and ultra modes, the Oracle, and the Search, Librarian, and Task subagents.
Checked Oct 12, 2026
Docs: The Dial
Explains the four modes, that a thread keeps its mode, and how linked ChatGPT and Claude subscriptions change billing.
Checked Oct 12, 2026
Docs: Introduction
Describes Amp as a coding agent and development environment that runs on the web, in macOS and iOS apps, and in the terminal, with orbs per thread.
Checked Oct 12, 2026
Docs: Orbs
Describes orbs as machines Amp creates per thread, with the repository cloned and the agent working after you close your laptop.
Checked Oct 12, 2026
Docs: CLI
Documents the Amp CLI on macOS, Linux, and Windows through WSL, running threads locally, in an orb, or on a runner.
Checked Oct 12, 2026
Docs: Runners
Documents runners, which let threads run on your own machines at no orb cost.
Checked Oct 12, 2026
Docs: Tools
States that Amp does not ask for approval before running tools, and that a custom plugin controls tool use.
Checked Oct 12, 2026
Docs: AGENTS.md
Documents the AGENTS.md files Amp reads for project instructions.
Checked Oct 12, 2026
Docs: Threads
Describes threads as the unit of work, shared with the workspace by default in workspace projects.
Checked Oct 12, 2026
Docs: Workspace Entitlements
Documents per-user spend limits for Enterprise workspaces, assigned individually, by group, or by directory group.
Checked Oct 12, 2026
Docs: Minimal Data Retention
Limits how long model providers retain prompts on Amp-managed connections, and states that neither Amp nor its providers train on customer data.
Checked Oct 12, 2026
Security Reference
States SOC 2 Type II certification, lists inference and infrastructure providers, and notes that Amp offers no self-hosted deployment.
Checked Oct 12, 2026
News: Amp Frontier Corporation
Announces on December 2, 2025 that Amp is spinning out of Sourcegraph as an independent company.
Checked Oct 12, 2026
News: The Coding Agent Is Dead
Announces on February 19, 2026 that the Amp editor extensions end on March 5, 2026, and that users move to the CLI.
Checked Oct 12, 2026
News: Free Agent
Announces on September 13, 2026 that Amp is free when you bring your own compute and model subscriptions or keys.
Checked Oct 12, 2026

Source index

Provenance at a glance

Every source GILD read, with the original address and the context used to count it. Open a finding to filter the full cards above. On smaller screens the index lists each source once by name, cohort and date; its full record above carries the address, context and findings.

Provenance for every analyzed Signals source
Source	Original URL	Author and context	Who	Published	Review date	Applies	Findings
Post on moving Omega development to the cloudID sx-03 \| Developer Communities	x.com/taylorotwell/status/2107981853642666382	Taylor Otwell, creator of Laravelself-described: Laravel product work across 5 repositories with multiple agents	Individual practitioner	Published Oct 7, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Comment on: Plan mode is deadID dc-48 \| Developer Communities	news.ycombinator.com/item?id=49854848	cavoirom, Hacker News commenter, self-described	Individual practitioner	Published Sep 26, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive
Comment on: Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-AstraID dc-47 \| Developer Communities	news.ycombinator.com/item?id=49653534	fishtoaster, Hacker News commenterself-described: First engineer at an early-stage startup	Individual practitioner	Published Sep 11, 2026	Assessment reviewed Nov 1, 2026	Current	Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-AstraID dc-46 \| Developer Communities	news.ycombinator.com/item?id=49651531	microdrum, Hacker News commenter, self-described	Individual practitioner	Published Sep 10, 2026	Assessment reviewed Nov 1, 2026	Current	Result Quality: Positive
147: It's Orbin' TimeID tc-05 \| Podcasts, Talks & Videos	www.youtube.com/watch?v=RXJKUrUuQbY	Company founder, co-host of Mostly Technicalself-described: Their company's app work; the company's CTO tried orbs first	Very small team	Published Sep 1, 2026	Assessment reviewed Nov 1, 2026	Current	Developer Experience: Mixed or negative Orbs & Cloud Agents: Positive Autonomy & Permissions: Raised as a concern
Comment on: OrbsID dc-44 \| Developer Communities	news.ycombinator.com/item?id=49500827	josevalerio, Hacker News commenter, self-described	Individual practitioner	Published Aug 30, 2026	Assessment reviewed Nov 1, 2026	Current	Orbs & Cloud Agents: Positive
Comment on: OrbsID dc-45 \| Developer Communities	news.ycombinator.com/item?id=49501909	altschuler, Hacker News commenter, self-described	Individual practitioner	Published Aug 30, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive Value for Money: Positive Is Amp worth what it costs?: Worth it
Comment on: Our decision on Cursor following its acquisition by SpaceXID dc-43 \| Developer Communities	news.ycombinator.com/item?id=49487590	cavoirom, Hacker News commenter, self-described	Individual practitioner	Published Aug 29, 2026	Assessment reviewed Nov 1, 2026	Current	Usage / Cost: Raised as a concern Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Post on moving project work to AmpID sx-05 \| Developer Communities	x.com/jkudish/status/2089834387718475986	Joey Kudish, software developer with 20 years of experienceself-described: Independent developer running several products; also uses Codex	Individual practitioner	Published Aug 18, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Post on the team's use of Amp orbsID sx-06 \| Developer Communities	x.com/JJEnglert/status/2089677275448914348	JJ Englert, Enablement Lead at Tenexself-described: AI consulting firm team moving work from local machines to the cloud	Professional team	Published Aug 18, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive
Post on an agent recording a bug video in an orbID sx-04 \| Developer Communities	x.com/andrzejkrzywda/status/2088952753196319011	Andrzej Krzywda, CEO of ArkencyRails consultancy working on large legacy Rails applications	Individual practitioner	Published Aug 16, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Result Quality: Positive Orbs & Cloud Agents: Positive
Post to the Amp team on orbsID sx-07 \| Developer Communities	x.com/RavinBarthwal/status/2088444858243625210	Ravindra Barthwal, founder building dxcodeself-described: Has tried Cursor, Devin, Codex, Claude, and other cloud agents	Individual practitioner	Published Aug 15, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive Value for Money: Positive Usage / Cost: Discussed without concern Is Amp worth what it costs?: Worth it
Comment on: How Compaction Works in PiID dc-42 \| Developer Communities	news.ycombinator.com/item?id=49294467	navs, Hacker News commenterself-described: Software engineer in Australia, New Zealand and Fiji	Individual practitioner	Published Aug 14, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Threads & Handoff: Positive Removed Features: Raised as a concern
Comment on: Launch HN: Hoplite (YC S26) - Effortlessly deploy cloud coding agentsID dc-41 \| Developer Communities	news.ycombinator.com/item?id=49158876	r5Khe, Hacker News commenter, self-described	Individual practitioner	Published Aug 3, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive
The State of Agents in the CloudID sx-01 \| Developer Communities	x.com/rockatanescu/status/2084410582900379766	Andrei Maxim, applied AI engineer and former Ruby developerself-described: Compared Amp orbs with Claude Code and Codex cloud environments on his own projects	Individual practitioner	Published Aug 3, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Orbs & Cloud Agents: Positive
AmpCode is coolID ir-11 \| Engineering Blogs & Reviews	blog.ianhsiao.me/ampcode-is-cool	Developer, formerly at Heptabaseself-described: Builds their own app; uses orbs from an iPad	Individual practitioner	Published Jul 31, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Orbs & Cloud Agents: Positive Usage / Cost: Discussed without concern Removed Features: Discussed without concern
Amp Got Cloud Coding Sandboxes RightID sx-02 \| Developer Communities	x.com/mikehostetler/status/2079222152671429068	Mike Hostetler, founder and Elixir agent framework builderself-described: Maintains several open-source Elixir repositories, including ReqLLM	Individual practitioner	Published Jul 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Orbs & Cloud Agents: Positive
Comment on: Claude Code uses Bun written in Rust nowID dc-40 \| Developer Communities	news.ycombinator.com/item?id=48971516	anamexis, Hacker News commenter, self-described	Individual practitioner	Published Jul 19, 2026	Assessment reviewed Nov 1, 2026	Current	Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: Claude Sonnet 5ID dc-39 \| Developer Communities	news.ycombinator.com/item?id=48742031	usef-, Hacker News commenter, self-described	Individual practitioner	Published Jul 1, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Oracle & Model Routing: Positive Developer Experience: Positive Threads & Handoff: Positive
Comment on: GLM 5.2 beats Claude in our benchmarksID dc-38 \| Developer Communities	news.ycombinator.com/item?id=48716904	nl, Hacker News commenterself-described: Former ML startup founder and former startup CTO	Individual practitioner	Published Jun 29, 2026	Assessment reviewed Nov 1, 2026	Current	Listed, no finding position
Comment on: Sakana FuguID dc-37 \| Developer Communities	news.ycombinator.com/item?id=48625432	nixosbestos, Hacker News commenter, self-described	Individual practitioner	Published Jun 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Evaluated as an engineering agent
Amp vs Claude Code: Is It Worth Switching in 2026?ID ir-10 \| Engineering Blogs & Reviews	www.alexdunlop.com/writing/amp-vs-claude-code-worth-switching-2026	Software engineerself-described: Solo build of a multi-agent setup with an MCP server and a web frontend	Individual practitioner	Published Jun 15, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Oracle & Model Routing: Positive Threads & Handoff: Positive Usage / Cost: Raised as a concern Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: Is Amp more or less expensive than Claude Code? Is it better?ID dc-36 \| Developer Communities	news.ycombinator.com/item?id=48302539	mutant, Hacker News commenter, self-described	Individual practitioner	Published May 28, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: Elevated error rates on Opus 4.7ID dc-35 \| Developer Communities	news.ycombinator.com/item?id=48143369	SatvikBeri, Hacker News commenter, self-described	Individual practitioner	Published May 15, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Value for Money: Mixed or negative Usage / Cost: Raised as a concern Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
CI/CD Is Dead, Agents Need Continuous Compute and ComputersID ld-03 \| Podcasts, Talks & Videos	ai.engineer/talks/VktrqzQgytY-ci-cd-is-dead-agents-need-continuous	Hugo Santos, Founder and CEO of NamespaceNamespace, a build and test compute infrastructure company whose team works from specs through agent loops	Technical leadership	Published May 13, 2026	Assessment reviewed Nov 1, 2026	Current	Evaluated as an engineering agent Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Comment on: DeepClaude - Claude Code agent loop with DeepSeek V4 ProID dc-34 \| Developer Communities	news.ycombinator.com/item?id=48003920	ahmadyan, Hacker News commenterself-described: Maker of Agentastic	Individual practitioner	Published May 4, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Result Quality: Positive
Post on migrating off AmpID ld-01 \| Developer Communities	x.com/jobergum/status/2036740110255849855	Jo Kristian Bergum, CEO of HornetHornet, a Trondheim startup building a retrieval engine for agents	Technical leadership	Published Mar 25, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Removed Features: Raised as a concern Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: How I write software with LLMsID dc-33 \| Developer Communities	news.ycombinator.com/item?id=47398717	shell0x, Hacker News commenter, self-described	Individual practitioner	Published Mar 16, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Oracle & Model Routing: Positive Result Quality: Positive Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Comment on: Show HN: Praxis, my personal take on Compound Engineering with AIID dc-32 \| Developer Communities	news.ycombinator.com/item?id=47143410	DFilipeS, Hacker News commenter, self-described	Individual practitioner	Published Feb 24, 2026	Assessment reviewed Nov 1, 2026	Current	Evaluated as an engineering agent
Comment on: Show HN: Tlsctl - A CLI for inspecting and troubleshooting TLSID dc-31 \| Developer Communities	news.ycombinator.com/item?id=47111796	_smertens_, Hacker News commenter, self-described	Individual practitioner	Published Feb 22, 2026	Assessment reviewed Nov 1, 2026	Current	Evaluated as an engineering agent
Comment on: Claude Code's compaction discards data that's still on diskID dc-30 \| Developer Communities	news.ycombinator.com/item?id=47097741	SatvikBeri, Hacker News commenter, self-described	Individual practitioner	Published Feb 21, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Threads & Handoff: Positive
Comment on: Amp Free Is FullID dc-28 \| Developer Communities	news.ycombinator.com/item?id=46971467	jauntywundrkind, Hacker News commenter, self-described	Individual practitioner	Published Feb 11, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Oracle & Model Routing: Positive Threads & Handoff: Positive
Comment on: Claude Code is being dumbed down?ID dc-29 \| Developer Communities	news.ycombinator.com/item?id=46981718	4b11b4, Hacker News commenter, self-described	Individual practitioner	Published Feb 11, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive
Comment on: Review-for-agent: A local, PR-style UI for reviewing AI agent code changesID dc-27 \| Developer Communities	news.ycombinator.com/item?id=46953474	asadjb, Hacker News commenter, self-described	Individual practitioner	Published Feb 10, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
I keep coming back to Amp CodeID ir-09 \| Engineering Blogs & Reviews	asadjb.com/blog/2026-02-08-i-keep-coming-back-to-amp	Independent developerself-described: Solo; also uses Claude Code (Max) and Codex	Individual practitioner	Published Feb 8, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Value for Money: Mixed or negative Usage / Cost: Raised as a concern Removed Features: Discussed without concern Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent Is Amp worth what it costs?: Worth it
Should You Use Ampcode for Production Code? One Month InID ir-08 \| Engineering Blogs & Reviews	intelligenttools.co/blog/ampcode-multi-agent-production	Developerself-described: Healthcare software work; runs Amp on a dedicated branch	Individual practitioner	Published Feb 7, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Oracle & Model Routing: Positive Requires Strong Review: Raised as a concern Autonomy & Permissions: Discussed without concern Needs Close Steering: Discussed without concern Evaluated as an engineering agent
Comment on: Claude Code: connect to a local model when your quota runs outID dc-26 \| Developer Communities	news.ycombinator.com/item?id=46891491	zingar, Hacker News commenter, self-described	Individual practitioner	Published Feb 4, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Usage / Cost: Discussed without concern
AMP vs Claude Code (CLI): Comparing of Agentic Coding ToolsID ir-07 \| Engineering Blogs & Reviews	www.cesarcouto.com/blog/amp-vs-claude-code-cli-comparing-of-agentic-coding-tools/	Web developerself-described: Professional web development; over 95 percent of their code is AI-generated	Individual practitioner	Published Jan 21, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Result Quality: Positive Developer Experience: Positive Value for Money: Mixed or negative Usage / Cost: Raised as a concern Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Coding with Claude Opus 4.5 For Free! (AmpCode)ID tc-04 \| Podcasts, Talks & Videos	www.youtube.com/watch?v=oX9fr_wwQQ0	Developer and YouTube creatorself-described: Solo	Individual practitioner	Published Jan 19, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Mixed or negative Usage / Cost: Discussed without concern
Comment on: OpenAI will start testing ads in ChatGPT free and Go tiersID dc-25 \| Developer Communities	news.ycombinator.com/item?id=46663761	weiliddat, Hacker News commenter, self-described	Individual practitioner	Published Jan 18, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Usage / Cost: Discussed without concern Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Comment on: Unauthenticated remote code execution in OpenCodeID dc-24 \| Developer Communities	news.ycombinator.com/item?id=46595068	theshrike79, Hacker News commenter, self-described	Individual practitioner	Published Jan 12, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Usage / Cost: Discussed without concern
Comment on: Anthropic blocks third-party use of Claude Code subscriptionsID dc-23 \| Developer Communities	news.ycombinator.com/item?id=46555050	tbliu, Hacker News commenter, self-described	Individual practitioner	Published Jan 9, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Positive Usage / Cost: Discussed without concern
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-19 \| Developer Communities	news.ycombinator.com/item?id=46199564	truekonrads, Hacker News commenter, self-described	Individual practitioner	Published Dec 9, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Oracle & Model Routing: Positive Result Quality: Positive Threads & Handoff: Positive
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-20 \| Developer Communities	news.ycombinator.com/item?id=46199621	the_mitsuhiko, Hacker News commenter, self-described	Individual practitioner	Published Dec 9, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Developer Experience: Positive Usage / Cost: Raised as a concern
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-21 \| Developer Communities	news.ycombinator.com/item?id=46199695	incoming1211, Hacker News commenterself-described: Engineering team at work	Very small team	Published Dec 9, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Usage / Cost: Discussed without concern Is Amp worth what it costs?: Worth it
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-22 \| Developer Communities	news.ycombinator.com/item?id=46207957	sergiotapia, Hacker News commenter, self-described	Individual practitioner	Published Dec 9, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Result Quality: Positive Value for Money: Mixed or negative Usage / Cost: Raised as a concern Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-16 \| Developer Communities	news.ycombinator.com/item?id=46199102	lvl155, Hacker News commenter, self-described	Individual practitioner	Published Dec 8, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Value for Money: Mixed or negative Usage / Cost: Raised as a concern Is Amp worth what it costs?: Not worth it
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-17 \| Developer Communities	news.ycombinator.com/item?id=46199109	embedding-shape, Hacker News commenter, self-described	Individual practitioner	Published Dec 8, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Value for Money: Mixed or negative Usage / Cost: Raised as a concern Is Amp worth what it costs?: Not worth it
Comment on: Amp, Inc. - Amp is spinning out of SourcegraphID dc-18 \| Developer Communities	news.ycombinator.com/item?id=46199341	incoming1211, Hacker News commenter, self-described	Individual practitioner	Published Dec 8, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Oracle & Model Routing: Positive Usage / Cost: Discussed without concern Is Amp worth what it costs?: Worth it
Comment on: Agent design is still hardID dc-15 \| Developer Communities	news.ycombinator.com/item?id=46016806	pjm331, Hacker News commenter, self-described	Individual practitioner	Published Nov 22, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Result Quality: Positive
Comment on: You should still be writing code from your editorID dc-14 \| Developer Communities	news.ycombinator.com/item?id=45947940	MorehouseJ09, Founder and CEO of Nuon, Hacker News commenterself-described: Founder and CEO of Nuon	Technical leadership	Published Nov 16, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Threads & Handoff: Positive
Amp Coding Agent: Features That Make It Stand OutID ir-06 \| Engineering Blogs & Reviews	peterwarnock.com/blog/posts/amp-coding-agent-features/	Independent developerself-described: Engineering lead for CI/CD and DevOps	Individual practitioner	Published Nov 10, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Threads & Handoff: Positive Written instructions make results consistent
Amp: Notes from reading the Amp manualID ir-05 \| Engineering Blogs & Reviews	hamel.dev/notes/coding-agents/amp.html	Independent developerself-described: Solo use, including SEO work on their own site	Individual practitioner	Published Nov 2, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Oracle & Model Routing: Positive Threads & Handoff: Positive Value for Money: Positive Usage / Cost: Discussed without concern Written instructions make results consistent Is Amp worth what it costs?: Worth it
Getting Started with AmpID ir-04 \| Engineering Blogs & Reviews	gvrooyen.substack.com/p/getting-started-with-amp	Co-founder of Octocoself-described: Octoco, senior engineering staff being introduced to Amp	Technical leadership	Published Oct 28, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Oracle & Model Routing: Positive Threads & Handoff: Positive Usage / Cost: Discussed without concern Written instructions make results consistent
Comment on: Claude Code on the webID dc-13 \| Developer Communities	news.ycombinator.com/item?id=45649857	hnidiots3, Hacker News commenter, self-described	Individual practitioner	Published Oct 20, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Oracle & Model Routing: Positive Result Quality: Positive
I Tried the Ad-Supported AI Coding Agent (Amp Free)ID tc-03 \| Podcasts, Talks & Videos	www.youtube.com/watch?v=6LtxUE54Llw	WEBdoze, YouTube channelself-described: Solo, small web projects	Individual practitioner	Published Oct 17, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Positive Usage / Cost: Discussed without concern
Vibing a Non-Trivial Ghostty FeatureID ir-03 \| Engineering Blogs & Reviews	mitchellh.com/writing/non-trivial-vibing	Creator of Ghosttyself-described: Ghostty, open-source terminal emulator; macOS update notification feature	Individual practitioner	Published Oct 11, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Oracle & Model Routing: Positive Threads & Handoff: Positive Usage / Cost: Discussed without concern Requires Strong Review: Discussed without concern Needs Close Steering: Raised as a concern
Amp - Vibe Code With Me - Ep 016ID tc-02 \| Podcasts, Talks & Videos	www.youtube.com/watch?v=k_kSlwXl-BI	Developerself-described: Solo, building an expense app on stream	Individual practitioner	Published Oct 6, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Result Quality: Positive Usage / Cost: Raised as a concern Is Amp worth what it costs?: Not worth it
Comment on: Ask HN: What are you working on? (September 2025)ID dc-12 \| Developer Communities	news.ycombinator.com/item?id=45429225	jeanlucas, Hacker News commenter, self-described	Individual practitioner	Published Sep 30, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Changelog #658: Adam Stacoviak on running agents side by sideID sf-1 \| Podcasts, Talks & Videos	changelog.com/podcast/658	Adam Stacoviak, co-founder and podcast host, Changelogself-described: Changelog, his own long-running project	Individual practitioner	Published Sep 17, 2025	Assessment reviewed Nov 1, 2026	Current	Overall signal Usage / Cost: Raised as a concern Is Amp worth what it costs?: Worth it
Can AMP Code Beat Claude Code? \| Feature Build Day 3ID tc-01 \| Podcasts, Talks & Videos	www.youtube.com/watch?v=wN-I5KPkKVc	Developer and streamerself-described: Solo, building a photo upload feature for their own app	Individual practitioner	Published Sep 7, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Developer Experience: Positive Written instructions make results consistent
Post on shared Amp threads in pull requestsID sx-08 \| Developer Communities	x.com/mitchellh/status/1963277478795026484	Mitchell Hashimoto, creator of Ghostty and co-founder of HashiCorpself-described: Maintainer of the Ghostty terminal, reviewing outside pull requests	Individual practitioner	Published Sep 3, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Threads & Handoff: Positive
Comment on: Ask HN: What LLM are you all using for coding assistance right now?ID dc-11 \| Developer Communities	news.ycombinator.com/item?id=44883493	aitooltrek-com, Hacker News commenterself-described: Indie maker building an AI tools site	Individual practitioner	Published Aug 13, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Among practitioners who compared agents, does Amp stay their main agent?: Another agent as main
Comment on: Getting good results from Claude CodeID dc-10 \| Developer Communities	news.ycombinator.com/item?id=44847729	derencius, Hacker News commenter, self-described	Individual practitioner	Published Aug 9, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Result Quality: Positive
Comment on: Jules, our asynchronous coding agentID dc-09 \| Developer Communities	news.ycombinator.com/item?id=44818527	pjm331, Hacker News commenter, self-described	Individual practitioner	Published Aug 6, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Oracle & Model Routing: Positive Developer Experience: Mixed or negative
Comment on: Claude Opus 4.1ID dc-08 \| Developer Communities	news.ycombinator.com/item?id=44805537	mark_undoio, CTO of Undo, Hacker News commenterself-described: CTO of Undo, a record and replay debugging company	Technical leadership	Published Aug 5, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Oracle & Model Routing: Positive
Amp Code: Arbitrary Command Execution via Prompt Injection FixedID sx-09 \| Engineering Blogs & Reviews	embracethered.com/blog/posts/2025/amp-agents-that-modify-system-configuration-and-escape/	Johann Rehberger, security researcher (Embrace The Red)self-described: Independent security testing of coding agents during his Month of AI Bugs series	Individual practitioner	Published Aug 5, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Autonomy & Permissions: Raised as a concern
Comment on: 6 weeks of Claude CodeID dc-07 \| Developer Communities	news.ycombinator.com/item?id=44773188	sergiotapia, Hacker News commenter, self-described	Individual practitioner	Published Aug 3, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Result Quality: Positive
Amp Code Deep Dive and TalkID ir-02 \| Engineering Blogs & Reviews	elite-ai-assisted-coding.dev/p/amp	Independent developer and contributor to the Air frameworkself-described: Open-source documentation task for the Air web framework	Individual practitioner	Published Jul 30, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Result Quality: Positive Usage / Cost: Discussed without concern Requires Strong Review: Discussed without concern Autonomy & Permissions: Discussed without concern Needs Close Steering: Discussed without concern
AI coding agent one-shot challenge with Amp, Claude Code and GeminiID ir-01 \| Engineering Blogs & Reviews	unknwon.io/posts/250722-ai-agent-one-shot-challenge/	Independent developer maintaining open-source side projectsself-described: Solo, side projects	Individual practitioner	Published Jul 22, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Result Quality: Mixed or negative Threads & Handoff: Positive
Comment on: Ask HN: Why do Cursor, Windsurf and Claude Code dominate the conversation?ID dc-06 \| Developer Communities	news.ycombinator.com/item?id=44635811	Gys, Hacker News commenter, self-described	Individual practitioner	Published Jul 21, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Positive Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Comment on: Cognition (Devin AI) to Acquire WindsurfID dc-05 \| Developer Communities	news.ycombinator.com/item?id=44580956	d_sc, Hacker News commenter, self-described	Individual practitioner	Published Jul 16, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Oracle & Model Routing: Positive Evaluated as an engineering agent
Comment on: AI slows down open source developers. Peter Naur can teach us whyID dc-04 \| Developer Communities	news.ycombinator.com/item?id=44562523	yomismoaqui, Hacker News commenter, self-described	Individual practitioner	Published Jul 14, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Is Amp worth what it costs?: Worth it
Comment on: Clarifying our pricingID dc-03 \| Developer Communities	news.ycombinator.com/item?id=44471256	mrklol, Hacker News commenter, self-described	Individual practitioner	Published Jul 5, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Result Quality: Positive Among practitioners who compared agents, does Amp stay their main agent?: Amp as main agent
Comment on: Claude Code for VSCodeID dc-02 \| Developer Communities	news.ycombinator.com/item?id=44356255	yomismoaqui, Hacker News commenter, self-described	Individual practitioner	Published Jun 23, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Usage / Cost: Discussed without concern
Transcript: 'How Two Engineers Ship Like a Team of 15 With AI Agents'ID ld-02 \| Podcasts, Talks & Videos	every.to/podcast/transcript-how-two-engineers-ship-like-a-team-of-15-with-ai-agents	Kieran Klaassen, general manager of Cora at EveryTwo-engineer team building Cora, an AI email product at Every, running several coding agents side by side	Technical leadership	Published Jun 11, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Result Quality: Positive Developer Experience: Positive
Comment on: Cursor 1.0ID dc-01 \| Developer Communities	news.ycombinator.com/item?id=44191851	vladstudio, Hacker News commenterself-described: Self-employed wallpaper designer	Individual practitioner	Published Jun 5, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Positive
PricingID pd-01 \| Product Documentation	ampcode.com/pricing	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: PricingID pd-02 \| Product Documentation	ampcode.com/docs/pricing	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: Sizes & CostsID pd-03 \| Product Documentation	ampcode.com/docs/orbs/sizes-and-costs	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Modes & ModelsID pd-04 \| Product Documentation	ampcode.com/modes	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: The DialID pd-05 \| Product Documentation	ampcode.com/docs/the-dial	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: IntroductionID pd-06 \| Product Documentation	ampcode.com/docs	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: OrbsID pd-07 \| Product Documentation	ampcode.com/docs/orbs	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: CLIID pd-08 \| Product Documentation	ampcode.com/docs/cli	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: RunnersID pd-09 \| Product Documentation	ampcode.com/docs/cli/runners	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: ToolsID pd-10 \| Product Documentation	ampcode.com/docs/tools	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: AGENTS.mdID pd-11 \| Product Documentation	ampcode.com/docs/customize/agents-md	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: ThreadsID pd-12 \| Product Documentation	ampcode.com/docs/threads	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: Workspace EntitlementsID pd-13 \| Product Documentation	ampcode.com/docs/enterprise/workspace-entitlements	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Docs: Minimal Data RetentionID pd-14 \| Product Documentation	ampcode.com/docs/enterprise/minimal-data-retention	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Security ReferenceID pd-15 \| Product Documentation	ampcode.com/security	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
News: Amp Frontier CorporationID pd-16 \| Product Documentation	ampcode.com/news/amp-frontier-corporation	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
News: The Coding Agent Is DeadID pd-17 \| Product Documentation	ampcode.com/news/the-coding-agent-is-dead	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
News: Free AgentID pd-18 \| Product Documentation	ampcode.com/news/free-agent	AmpOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only

Taylor Otwell, creator of Laravel

cavoirom, Hacker News commenter, self-described

fishtoaster, Hacker News commenter

microdrum, Hacker News commenter, self-described

Company founder, co-host of Mostly Technical

josevalerio, Hacker News commenter, self-described

altschuler, Hacker News commenter, self-described

cavoirom, Hacker News commenter, self-described

Joey Kudish, software developer with 20 years of experience

JJ Englert, Enablement Lead at Tenex

Andrzej Krzywda, CEO of Arkency

Ravindra Barthwal, founder building dxcode

navs, Hacker News commenter

r5Khe, Hacker News commenter, self-described

Andrei Maxim, applied AI engineer and former Ruby developer

Developer, formerly at Heptabase

Mike Hostetler, founder and Elixir agent framework builder

anamexis, Hacker News commenter, self-described

usef-, Hacker News commenter, self-described

nl, Hacker News commenter

nixosbestos, Hacker News commenter, self-described

Software engineer

mutant, Hacker News commenter, self-described

SatvikBeri, Hacker News commenter, self-described

Hugo Santos, Founder and CEO of Namespace

ahmadyan, Hacker News commenter

Jo Kristian Bergum, CEO of Hornet

shell0x, Hacker News commenter, self-described

DFilipeS, Hacker News commenter, self-described

_smertens_, Hacker News commenter, self-described

SatvikBeri, Hacker News commenter, self-described

jauntywundrkind, Hacker News commenter, self-described

4b11b4, Hacker News commenter, self-described

asadjb, Hacker News commenter, self-described

Independent developer

Developer

zingar, Hacker News commenter, self-described

Web developer

Developer and YouTube creator

weiliddat, Hacker News commenter, self-described

theshrike79, Hacker News commenter, self-described

tbliu, Hacker News commenter, self-described

truekonrads, Hacker News commenter, self-described

the_mitsuhiko, Hacker News commenter, self-described

incoming1211, Hacker News commenter

sergiotapia, Hacker News commenter, self-described

lvl155, Hacker News commenter, self-described

embedding-shape, Hacker News commenter, self-described

incoming1211, Hacker News commenter, self-described

pjm331, Hacker News commenter, self-described

MorehouseJ09, Founder and CEO of Nuon, Hacker News commenter

Independent developer

Independent developer

Co-founder of Octoco

hnidiots3, Hacker News commenter, self-described

WEBdoze, YouTube channel

Creator of Ghostty

Developer

jeanlucas, Hacker News commenter, self-described

Adam Stacoviak, co-founder and podcast host, Changelog

Developer and streamer

Mitchell Hashimoto, creator of Ghostty and co-founder of HashiCorp

aitooltrek-com, Hacker News commenter

derencius, Hacker News commenter, self-described

pjm331, Hacker News commenter, self-described

mark_undoio, CTO of Undo, Hacker News commenter

Johann Rehberger, security researcher (Embrace The Red)

sergiotapia, Hacker News commenter, self-described

Independent developer and contributor to the Air framework

Independent developer maintaining open-source side projects

Gys, Hacker News commenter, self-described

d_sc, Hacker News commenter, self-described

yomismoaqui, Hacker News commenter, self-described

mrklol, Hacker News commenter, self-described

yomismoaqui, Hacker News commenter, self-described

Kieran Klaassen, general manager of Cora at Every

vladstudio, Hacker News commenter