Skip to main content
Kiro SignalsBack to the read

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.

Whose sources count

Source

89 sources in All practitioners, with product documentation Showing all 89 sources

  1. Negative

    rsammons, GitHub user

    Reliability regression: file edits fail, IDE freezes, spec operations die with network errors, and in-app bug reporter is brokenGitHub issue on kirodotdev/Kiro

    Design generation from an existing spec failed three times with a backend network error after about 20 minutes. Each attempt re-ran 25 or more tool calls, and credits were still consumed for the failed work.

    "~20 minutes elapsed before any problem was surfaced; three identical failures; no design document produced; credits consumed for failed operations…"
    Excerpt, rsammons

    Published Oct 2, 2026self-described: Kiro IDE 1.1.14 on Windows 11 Business, spec-driven work

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Reliability, Cost predictability and limits How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Observed on 1.1.14; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-10-02, 1.1.14
    Counts toward
    Reliability, service availability: unfavorable, G2 (2 units before bounds)
    Counts toward
    Cost predictability and limits, cost predictability: unfavorable, G1 (1 unit before bounds)
    Counts toward
    Delivered outcomes, task completion: unfavorable, G1 (1 unit before bounds)
    Not counted
    Reliability, run stability: repeats a stronger account in its group

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Measured
    Applies to
    Current
    Observed on
    Kiro IDE 1.1.14

  2. Negative

    s4i, Hacker News commenter, self-described

    Comment on: Our decision on Cursor following its acquisition by SpaceXHacker News comment

    Looking for a Cursor replacement, tried Kiro, which shares the philosophy but lacks most of the Cursor features they rely on.

    Published Aug 31, 2026

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-08-31
    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

  3. Negative

    codeduck, Hacker News commenter, self-described

    Comment on: Meta Security Researcher's AI Agent Accidentally Deleted Her EmailsHacker News comment

    Spent an hour persuading Kiro that a failing local MCP call came from its own missing Authorization header; it was not attributed to the proxy. Only the logs convinced it.

    Published Aug 31, 2026

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-08-31
    Counts toward
    Delivered outcomes, task completion: unfavorable, G2 (2 units before bounds)

    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

  4. Negative

    rgoltz, GitHub user

    Kiro IDE - Extension host crashes when processing large LLM responses (event loop blocked)GitHub issue on kirodotdev/Kiro

    The Kiro agent crashed the editor's extension host 3 times in one working day across 2 instances, losing in-progress work each time and making sessions longer than 30 minutes unusable.

    "This happens repeatedly and reliably, 3 crashes in a single working day across 2 Kiro instances."
    Excerpt, rgoltz

    Published Aug 6, 2026self-described: Two Kiro instances on Windows 11, spec sessions with subagents

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Customer of Kiro; Used it directly; Artifact checked (log); Observed on 1.0.242
    Role
    Pseudonymous account; identity not pursued
    Relationship
    customer (self disclosed)
    How they know
    Used it directly
    Support
    1 artifact (log)
    Date and version
    2026-08-06, 1.0.242
    Counts toward
    Reliability, run stability: unfavorable, G3 (3 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
    Measured
    Applies to
    Current
    Observed on
    Kiro IDE 1.0.242

  5. Mixed

    Engineer working daily across AWS accounts

    Kiro CLI Gets Worse After an Hour. Here's How I Fixed It.Personal blog post, DEV Community (AWS Community Builders)

    Uses Kiro CLI daily for AWS work and finds it degrades after an hour or two of one session. One task per session and steering files keep it sharp.

    Published Jul 16, 2026self-described: Daily AWS operations work with Kiro CLI

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Kiro partner: not counted as independent; Used it directly; Specific details
    Role
    Name self-described; employer unknown; role unknown
    Relationship
    program member (suspected)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-07-16
    Counts toward
    Delivered outcomes, task completion: mixed, G2 (2 units before bounds)
    Counts toward
    Delivered outcomes, context handling: unfavorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: unfavorable, G2 (2 units before bounds)
    Counts toward
    Operational control, execution control: unfavorable, G1 (1 unit before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Published in the DEV space of AWS's Community Builders program, which only members post to. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Current
    Observed on
    Kiro CLI

  6. Positive

    danny_codes, Hacker News commenter, self-described

    Comment on: GLM 5.2 and the coming AI margin collapseHacker News comment

    Switched to Kiro and finds it essentially the same as their previous tool, slightly better for showing what the harness is doing.

    Published Jul 7, 2026

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-07-07
    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

  7. Positive

    iLoveOncall, Amazon engineer

    Comment on: Codex logging bug may write TBs to local SSDsHacker News comment

    Works at Amazon but not on the Kiro team, and "surprisingly" finds Kiro fine. Prefers it to anything else tried except Amazon Q Developer in IntelliJ, which is now deprecated.

    Published Jun 22, 2026self-described: Amazon or AWS engineer describing internal use

    Practitioner account, pseudonymous; direct use; not counted, tied to the vendor How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-06-22
    Not counted
    no aspect: excluded, praise from someone tied to the vendor, kept as an attributed position; takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Current

  8. Positive

    epistasis, Hacker News commenter, self-described

    Comment on: Codex logging bug may write TBs to local SSDsHacker News comment

    Kiro is surprisingly good. With more reliable session save and resume, and remote sessions, they would switch to it full time.

    Published Jun 22, 2026

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance

    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

  9. Mixed

    astqs, Hacker News commenter, self-described

    Comment on: AI coding at home without going brokeHacker News comment

    Spent about 200 euros of usage in one weekend in December. It was money well spent, though they expect heavy use to cost far more at break-even prices.

    Published Jun 13, 2026

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-06-13
    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
    Still applicable

  10. Positive

    isengard3000, Amazon employee

    Comment on: 'Sloppenheimer:' Amazon employees mock the company's AI on SlackHacker News comment

    An Amazon employee with Claude Code and Codex available still likes Kiro CLI and finds it easier to understand than Claude Code.

    Published Jun 9, 2026self-described: Amazon or AWS engineer describing internal use

    Practitioner account, pseudonymous; direct use; not counted, tied to the vendor How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-06-09
    Not counted
    Operational control, models and deployment: excluded, praise from someone tied to the vendor, kept as an attributed position
    Not counted
    Delivered outcomes, task completion: 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

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Current
    Observed on
    Kiro CLI

  11. Mixed

    sparrc, AWS engineer

    Comment on: 'Sloppenheimer:' Amazon employees mock the company's AI on SlackHacker News comment

    At AWS most engineers use Kiro as the de facto standard. Teams share AGENTS.md files, team-specific skills, and on-call skills, and their org built an MCP server for on-call.

    Published Jun 9, 2026self-described: AWS; most engineers use Kiro, with team-specific skills and an org MCP server for on-call

    Practitioner account, pseudonymous; second-hand; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Second-hand
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Reports others' experience
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-06-09
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Organization-wide
    Evidence
    Reported
    Applies to
    Current
    Observed on
    Kiro inside AWS

  12. No opinion stated

    korbonits, Hacker News commenter, self-described

    Comment on: Ask HN: What was your "oh shit" moment with GenAI?Hacker News comment

    Moved to Claude Code "this January", having heard it got really good the previous November while still using Kiro. Calls it a eureka moment and has been busy building ever since.

    Published Jun 6, 2026

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-06-06
    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
    Still applicable

  13. Positive

    marysol5, Hacker News commenter

    Comment on: Alphabet announces $80B equity capital raise to expand AI infra and computeHacker News comment

    Kiro, which they use at work, prompts the user when a command needs input such as a sudo password, while another agent sat thinking until they intervened.

    Published Jun 2, 2026self-described: Uses Kiro and Gemini at work

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-06-02
    Not counted
    Operational control, execution control: repeats a stronger account in its group

    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
    Kiro at work

  14. Positive

    forgotaccount3, Hacker News commenter

    Comment on: AI sticker shock hits corporate AmericaHacker News comment

    Their employer uses Kiro on a deal below public pricing, has enabled overages for everyone, and moves people between tiers by usage. They see clear productivity per dollar.

    Published May 28, 2026self-described: Employer-wide Kiro deployment with overages enabled

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Customer of Kiro; Used it directly
    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
    2026-05-28
    Not counted
    Delivered outcomes, task completion: 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 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Developer Communities
    Who
    Organization-wide
    Evidence
    Reported
    Applies to
    Current

  15. Mixed

    Insanity, Amazon engineer

    Comment on: Microsoft starts canceling Claude Code licensesHacker News comment

    With both available inside Amazon, thinks Kiro has a first-mover advantage there but finds Claude Code better to use.

    Published May 23, 2026self-described: Amazon or AWS engineer describing internal use

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-05-23
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Current

  16. Positive

    NTRIXLM, Hacker News commenter

    Comment on: Show HN: I Made a Claude Skill for Spec-Driven Development (SDD)Hacker News comment

    Prefers Kiro for its spec management, but the employer provides only Claude and a personal plan is not affordable, so they rebuilt Kiro's spec flow as a Claude skill.

    Published May 21, 2026self-described: Team on a shared Claude subscription; Kiro not provided by the employer

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-05-21
    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

  17. Mixed

    Developer

    When a Kiro CLI Update Silently Breaks Your MCP Servers: The Approved Environment Variables GotchaPersonal blog post, DEV Community

    A Kiro CLI update stopped expanding unapproved environment variables in MCP configs, so the author's MCP server began returning 401 errors overnight until the variables were approved.

    Published May 21, 2026self-described: Daily Kiro CLI workflow with MCP servers

    Practitioner account, self-described; direct use; counts toward Reliability, Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Used it directly; Specific details; Observed on Kiro CLI v2.4.0
    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
    2026-05-21, Kiro CLI v2.4.0
    Counts toward
    Reliability, regressions: unfavorable, G2 (2 units before bounds), capped: C-relationship
    Counts toward
    Operational control, execution control: favorable, G2 (2 units before bounds), capped: C-relationship

    Checked Oct 30, 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
    Kiro CLI v2.4.0

  18. Positive

    Miner49er, Hacker News commenter

    Comment on: I believe there are entire companies right now under AI psychosisHacker News comment

    Struggles to use the 1,000 credits a US$20 plan gives each month, despite using Kiro more than anyone else on the team.

    Published May 16, 2026self-described: On a team, Kiro plan at $20 a month for 1000 credits

    Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-05-16
    Counts toward
    Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
    Not counted
    Cost predictability and limits, limits in practice: 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
    Very small team
    Evidence
    Reported
    Applies to
    Still applicable
    Observed on
    Pro plan, 1,000 credits

  19. Negative

    iLoveOncall, Amazon engineer

    Comment on: Amazon rolls out Claude Code and Codex internallyHacker News comment

    Says "we had to use Kiro and a lot of people don't like it"; calls Kiro IDE "a piece of crap" and "I guess the CLI was fine as far as CLIs go".

    Published May 5, 2026self-described: Amazon, company-wide internal tooling

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-05-05
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Organization-wide
    Evidence
    Reported
    Applies to
    Still applicable

  20. Negative

    k3vinw, Hacker News commenter

    Comment on: Uncle Bob: It's OverHacker News comment

    During a refactor, Kiro blamed the testing library. The engineer stepped in and found the real cause, an async bug hidden by faulty test doubles.

    Published May 3, 2026self-described: Team project, refactoring existing code

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-05-03
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  21. Positive

    Geshan Manandhar, Geshan's Blog

    Using Spec Driven Development with AWS Kiro to add the last updated date on Eleventy blogPersonal blog post

    Added a last-updated date to an Eleventy blog through a Kiro spec. Kiro wrote the requirements and design docs and a task list of up to 6 tasks, installed fast-check, added a test framework and ran tests, and the feature worked after a couple of minor changes by the author.

    Published May 3, 2026self-described: Personal Eleventy blog, one feature built through a spec

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Operational control 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
    2026-05-03
    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

    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
    Kiro IDE specs

  22. Positive

    topce, Hacker News commenter

    Comment on: Microsoft and OpenAI end their exclusive and revenue-sharing dealHacker News comment

    Having used both Copilot and Kiro, lists Sonnet at 1 and Opus at 3 on Copilot against 1.3 and 2.2 on Kiro, and says "IMHO lot of people will switch to kiro and or deep seek", adding "it look like AWS done best inference".

    Published Apr 27, 2026self-described: Uses both GitHub Copilot and Kiro

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Specific details; Observed on kiro sonet 1.3 kiro opus 2.2
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-04-27, kiro sonet 1.3 kiro opus 2.2
    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
    Kiro credit multipliers: Sonnet 1.3x, Opus 2.2x

  23. Mixed

    Developer

    Kiro Forgets Everything Every Session. So I've Built It a Memory.Personal blog post, DEV Community

    Kiro CLI forgets project decisions between sessions. Steering files record what the project is and leave out what the agent learned, so the author built an MCP memory server to keep those lessons.

    Published Apr 27, 2026self-described: Daily Kiro CLI use on a TypeScript CLI project

    Practitioner account, self-described; direct use; not counted, earlier release How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Used it directly; Specific details; Out of date (earlier release)
    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
    2026-04-27, out of date
    Not counted
    Delivered outcomes, correctness: excluded, describes an earlier release or was retracted
    Not counted
    Delivered outcomes, context handling: excluded, describes an earlier release or was retracted
    Not counted
    Reliability, run stability: excluded, describes an earlier release or was retracted
    Not counted
    Cost predictability and limits, cost transparency: excluded, describes an earlier release or was retracted

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Out of date
    Observed on
    Kiro CLI

  24. Positive

    geeky4qwerty, Hacker News commenter

    Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageHacker News comment

    After quota problems with Google's tools, moved to Kiro for the IDE and Codex for the CLI and is happy with the setup.

    Published Apr 12, 2026self-described: Kiro as IDE and Codex as CLI, also pays for Google Pro

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    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
    2026-04-12
    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
    Still applicable

  25. Positive

    Engineering manager, cloud infrastructure platform team

    Kiro showcase: Automating Changes Across Several Repos with Spec-Driven Development and Custom Sub-AgentsPersonal blog post, DEV Community

    De Paolis used a Kiro spec and an agent run as parallel kiro-cli subagents to change 30+ repos, spending "probably less than 90 minutes" and roughly 80 credits of a 1K monthly allowance on the US$20/month plan, against "likely 4-6 hours" of work by hand.

    Published Apr 7, 2026self-described: Platform team responsible for Terraform across 200+ repositories

    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; Observed on $20/month plan
    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
    2026-04-07, $20/month plan
    Counts toward
    Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relationship
    Counts toward
    Operational control, execution control: mixed, G2 (2 units before bounds), capped: C-relationship
    Counts toward
    Adoption and upkeep, setup: 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, correctness: 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
    Technical leadership
    Evidence
    Measured
    Applies to
    Still applicable
    Observed on
    Kiro IDE specs and Kiro CLI subagents, Pro plan

  26. No opinion stated

    imtaxu, GitHub user and AWS Organizations administrator

    Kiro subscription assignment fails on Organizations management account and routes to standalone CreateAssignment pathGitHub issue on kirodotdev/Kiro

    Could not assign any paid Kiro plan to Identity Center users or groups from an AWS Organizations management account. CloudTrail showed the call going to a standalone Amazon Q Developer subscription path and failing with AccessDenied.

    "I cannot assign a paid Kiro subscription to a user or group from AWS IAM Identity Center."
    Excerpt, imtaxu

    Published Apr 2, 2026self-described: AWS Organizations management account assigning paid Kiro plans to IAM Identity Center users and groups

    Practitioner account, pseudonymous; ran the rollout; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Ran the rollout; Artifact checked (log); Observed on 0.11.107
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
    How they know
    Ran the rollout
    Support
    1 artifact (log)
    Date and version
    2026-04-02, 0.11.107
    Counts toward
    Adoption and upkeep, setup: unfavorable, G3 (3 units before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Developer Communities
    Who
    Organization-wide
    Evidence
    Reported
    Applies to
    Current
    Observed on
    Kiro 0.11.107, Kiro console in AWS

  27. Negative

    huey77, Hacker News commenter

    Comment on: AWS Kiro accounts suspended en masse - AWS flagging fraud detection issuesHacker News comment

    Their Kiro account was suspended after an upgrade to the US$200 Power plan, with no explanation, and they link reports suggesting it was widespread.

    Published Mar 22, 2026self-described: Building workern.io in Melbourne, on Kiro $200/month Power plan

    not counted, repeats a stronger account How GILD checked it
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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 (issue)
    Date and version
    2026-03-22, $200/month Power plan
    Not counted
    Reliability, service availability: 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
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Power plan

  28. Positive

    Software developer and TDD trainer

    Kiro for Test-Driven Development (TDD)Personal blog post, DEV Community

    With steering files that encode TDD, Kiro followed red, green, refactor on a kata, occasionally jumping ahead the way human trainees do.

    Published Mar 16, 2026self-described: Solo kata experiment

    Practitioner account, self-described; structured test; counts toward Delivered outcomes How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Ran a structured test; 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
    Ran a structured test
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-03-16
    Counts toward
    Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
    Counts toward
    Delivered outcomes, correctness: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship

    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
    Still applicable

  29. Mixed

    konaraddi, AWS engineer

    Comment on: Ask HN: How is AI-assisted coding going for you professionally?Hacker News comment

    An AWS engineer says Kiro writes most of their code, but quality degrades over long context, it is slow on simple steps, and setup sometimes costs more than it saves.

    Published Mar 15, 2026self-described: Amazon or AWS engineer describing internal use

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly; Observed on Claude Opus 4.6 1M
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-03-15, Claude Opus 4.6 1M
    Not counted
    Delivered outcomes, task completion: repeats a stronger account in its group
    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

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable
    Observed on
    Claude Opus 4.6 1M in Kiro

  30. Mixed

    humbleharbinger, Amazon engineer

    Comment on: Ask HN: How is AI-assisted coding going for you professionally?Hacker News comment

    An Amazon engineer reports being two to four times as productive with Kiro on Opus 4.6, while most of their complaints are with Kiro's harness compared with Claude Code.

    Published Mar 15, 2026self-described: Amazon or AWS engineer describing internal use

    Practitioner account, pseudonymous; direct use; not counted, tied to the vendor How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly; Specific details; Observed on Opus 4.6
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected); vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-03-15, Opus 4.6
    Not counted
    Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works for Amazon, which makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable
    Observed on
    Claude Opus 4.6 in Kiro

  31. Positive

    avereveard, Hacker News commenter

    Comment on: 1M context is now generally available for Opus 4.6 and Sonnet 4.6Hacker News comment

    Uses Kiro at work and prefers in-IDE agents because reviewing changes and pulling in context is faster. Task delegation is the feature that matters to them.

    Published Mar 14, 2026self-described: Kiro at work, Roo Code at home

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-03-14
    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
    Still applicable
    Observed on
    Kiro IDE at work

  32. Positive

    wenc, Hacker News commenter

    Comment on: After outages, Amazon to make senior engineers sign off on AI-assisted changesHacker News comment

    Uses Kiro IDE mainly to write and pressure-test specs, often for hours or days, then hands the task list to headless agents including Kiro CLI and Claude Code.

    Published Mar 11, 2026self-described: Kiro IDE as spec generator, headless CLI agents in tmux for implementation

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Observed on Kiro IDE (≠ Kiro CLI)
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-03-11, Kiro IDE (≠ Kiro CLI)
    Counts toward
    Reliability, run stability: favorable, G1 (1 unit 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 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
    Observed on
    Kiro IDE for specs, Kiro CLI and Claude Code for implementation

  33. Positive

    daheza, Hacker News commenter

    Comment on: After outages, Amazon to make senior engineers sign off on AI-assisted changesHacker News comment

    Really liked Kiro IDE: its usage model is tempting next to Cursor, and the editor features are much the same.

    Published Mar 10, 2026self-described: Senior engineering manager, team moving a monolith into AWS

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-03-10
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  34. Negative

    stavarotti, Hacker News commenter, self-described

    Comment on: Amazon holds engineering meeting following AI-related outagesHacker News comment

    Tried Kiro and quickly left, and wonders whether a company's insistence on home-grown tools like Kiro over Codex, Cursor or Claude explains the problem the thread discusses.

    Published Mar 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 Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-03-10
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  35. Mixed

    achenatx, Hacker News commenter, self-described

    Comment on: How I use Claude Code: Separation of planning and executionHacker News comment

    The spec flow lets Kiro run an hour or more on small chunks with mostly correct results that still need fixes. Steering files use up context and force resets.

    Published Feb 22, 2026

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-02-22
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit 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
    Still applicable

  36. Positive

    mlaretallack, Hacker News commenter, self-described

    Comment on: How I use Claude Code: Separation of planning and executionHacker News comment

    Kiro's requirements, design, task list, and coding sequence works well because it forces a slower, deliberate pass over what the author wants.

    Published Feb 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 Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-02-22
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  37. Positive

    mlaretallack, Hacker News commenter

    Comment on: Ask HN: Are you using an agent orchestrator to write code?Hacker News comment

    Runs a separate Kiro instance per project in its own desktop workspace, about four at a time, and relies on Kiro's notifications when an agent needs input.

    Published Feb 13, 2026self-described: Runs about four projects at once, one Kiro instance per desktop workspace

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-02-13
    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
    Still applicable
    Observed on
    Kiro IDE

  38. Positive

    Lee Gilmore, Principal Cloud Architect and AWS Community Lead at Leighton

    Kiro: AI spec-driven delivery and what it means for the future of software developmentCompany blog post, Leighton

    Gilmore reports that Leighton's AWS practice estimates up to six times the output when Kiro specs and steering docs are used well, but calls it no plug-and-play tool: senior engineers must validate its output and teams must change how they work.

    "At Leighton our early experience with AI-assisted spec-driven development suggests material productivity gains, with our AWS Practice estimating up to a 6x increase in output and delivery speed when used effectively."
    Excerpt, Lee Gilmore

    Published Feb 13, 2026UK software consultancy with an AWS practice delivering client projects

    Practitioner account; direct use; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Kiro partner: not counted as independent; Used it directly
    Role
    Name unknown; employer unknown; role unknown
    Relationship
    consultant or reseller (suspected); consultant or reseller (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-02-13
    Counts toward
    Adoption and upkeep, setup: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship, C-unknown-control
    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

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author is AWS Community Lead at Leighton, an AWS consulting partner. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current
    Observed on
    Kiro IDE and CLI with specs, steering docs and agent hooks

  39. Mixed

    smarchypants, GitHub user

    New sessions immediately hit 85%+ context usage and enter summarization loop, even with minimal steering docs and simple promptsGitHub issue on kirodotdev/Kiro

    After 6 months of normal use, every new session hit 85% context on the first exchange because Kiro ignored .kiroignore and loaded all 10,080 workspace files. Only moving the files out of the workspace fixed it.

    "Actual behavior: All 10,080 files were still loaded into context (100,000+ tokens)…"
    Excerpt, smarchypants

    Published Jan 18, 2026self-described: Home automation workspace with three MCP servers, using Kiro for 6+ months

    Practitioner account, pseudonymous; structured test; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Ran a structured test; Specific details; Observed on 0.8.140
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
    How they know
    Ran a structured test
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-01-18, 0.8.140
    Counts toward
    Reliability, regressions: unfavorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: unfavorable, 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
    Measured
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE 0.8.140 on macOS

  40. Mixed

    hmokiguess, Hacker News commenter

    Comment on: How do you pick a Coding Agent HN?Hacker News comment

    Tried Kiro on AWS credits and found it outperformed Claude Code in some cases, but not by enough to switch from Claude Code.

    Published Jan 15, 2026self-described: Compares Claude Code, Codex, and Kiro

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-01-15
    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
    Observed on
    Kiro on AWS credits

  41. Positive

    Engineer

    What I Learned Using Specification-Driven Development with KiroPersonal blog post, DEV Community (AWS Community Builders)

    Spec-driven work in Kiro changed how the author thinks about specifications: writing acceptance criteria first exposed hidden assumptions and stopped over-engineering.

    Published Jan 12, 2026self-described: A real project, solo

    Practitioner account, self-described; direct use; not counted, tied to the vendor How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Kiro partner: not counted as independent; Used it directly
    Role
    Name self-described; employer unknown; role unknown
    Relationship
    program member (suspected)
    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: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Published in the DEV space of AWS's Community Builders program, which only members post to. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  42. Negative

    sirtaj, Hacker News commenter

    Comment on: Anthropic blocks third-party use of Claude Code subscriptionsHacker News comment

    Uses Kiro CLI with Opus at work and finds it clearly inferior to Claude Code within the first 30 seconds.

    Published Jan 9, 2026self-described: 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 Kiro found in GILD's check; Used it directly; Observed on opus
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-01-09, opus
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro CLI, Claude Opus

  43. Negative

    elfly, Hacker News commenter, self-described

    Comment on: Anthropic blocks third-party use of Claude Code subscriptionsHacker News comment

    Kiro starts well with planning but is hard to control: it changes files on a whim and switches opinions mid-answer.

    Published Jan 9, 2026

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-01-09
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance
    Not counted
    Operational control, execution control: repeats a stronger account in its group
    Not counted
    Operational control, models and deployment: repeats a stronger account in its group

    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

  44. Positive

    cobolcomesback, Hacker News commenter, self-described

    Comment on: Anthropic blocks third-party use of Claude Code subscriptionsHacker News comment

    Finds Kiro better than Claude Code: result quality is similar, but Claude Code got stuck on tool-call errors where Kiro just worked, and they prefer Kiro's simpler UX.

    Published Jan 9, 2026

    Practitioner account, pseudonymous; direct use; counts toward Reliability, Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-01-09
    Counts toward
    Operational control, models and deployment: favorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: favorable, G1 (1 unit before bounds), capped: C-relevance

    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

  45. Negative

    thegagne, Hacker News commenter

    Comment on: How Google got its groove back and edged ahead of OpenAIHacker News comment

    A spec run produced odd requirements, an over-complex design, a long task list, and many passing tests but no useful code, after 8 hours and 200+ credits.

    Published Jan 8, 2026self-described: Software engineering architect, developer productivity golden paths

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-01-08
    Counts toward
    Operational control, execution control: unfavorable, 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
    Still applicable
    Observed on
    Credit pricing

  46. Negative

    falkensmaize, Hacker News commenter

    Comment on: Opus 4.5 is not the normal AI agent experience that I have had thus farHacker News comment

    Using Opus 4.5 through Kiro at work, it could not upgrade Nx and yarn in a 20-app monorepo, invented config options, and the engineer fixed it by hand.

    Published Jan 7, 2026self-described: At work, TypeScript monorepo with about 20 apps

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Observed on Opus 4.5 through Kiro; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2026-01-07, Opus 4.5 through Kiro
    Counts toward
    Delivered outcomes, task completion: unfavorable, G2 (2 units before bounds)
    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, pending a recheck

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Claude Opus 4.5 through Kiro

  47. Negative

    CuriouslyC, Hacker News commenter

    Comment on: The future of software development is software developersHacker News comment

    Not a fan: Kiro is too heavyweight, and agents do not follow its detailed specs closely enough to repay the time spent writing them.

    Published Dec 30, 2025self-described: CEO and chief scientist of Sibylline Software, building a spec-driven dev tool

    Practitioner account, pseudonymous; opinion; not counted, from a competitor's side How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Competitor staff: not counted as independent; Opinion
    Role
    Pseudonymous account; identity not pursued
    Relationship
    competitor employee (self disclosed)
    How they know
    Opinion, no use stated
    Support
    No artifact or independent corroboration recorded
    Date and version
    2025-12-30
    Not counted
    Delivered outcomes, correctness: excluded, criticism from a competitor's side, kept as an attributed position

    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

  48. Positive

    Developer

    I Stopped Fighting My AI How Kiro's agent hooks and steering files fixed my biggest frustration with AI coding toolsPersonal blog post, DEV Community

    After months of re-explaining the project to Cursor and Copilot, Kiro's steering files kept its conventions across sessions and hooks automated the follow-up work.

    Published Nov 26, 2025self-described: Solo, React and Node dashboard

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, 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
    2025-11-26
    Counts toward
    Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relationship
    Counts toward
    Adoption and upkeep, setup: 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
    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

    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
    Still applicable

  49. Mixed

    lan321, Hacker News commenter

    Comment on: Gemini 3Hacker News comment

    Likes how Kiro splits large projects into bite-sized chunks, but could not get it to implement solitaire correctly.

    Published Nov 19, 2025self-described: Works under company policy on LLM agent repo access

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-11-19
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  50. Mixed

    Developer writing in the AWS Community Builders organization on DEV

    Brilliant, Broken, and Frustrating: My Deep Dive into Amazon's Kiro AI IDE, the Flawed Junior DeveloperPersonal blog post, DEV Community (AWS Community Builders)

    Values how specs force planning, but reports weekly model errors, stuck tasks, and a 1,500-line app for a job worth under 200 lines.

    Published Oct 24, 2025self-described: Solo, personal projects

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Kiro partner: not counted as independent; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Name self-described; employer unknown; role unknown
    Relationship
    program member (suspected)
    How they know
    Used it directly
    Support
    1 artifact (issue)
    Date and version
    2025-10-24, current preview state, needs a recheck
    Counts toward
    Reliability, service availability: unfavorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: unfavorable, G2 (2 units before bounds)
    Counts toward
    Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)
    Not counted
    Delivered outcomes, task completion: repeats a stronger account in its group
    Not counted
    Delivered outcomes, context handling: repeats a stronger account in its group
    Not counted
    Cost predictability and limits, limits in practice: a lead (G0), counts toward nothing until substantiated
    Not counted
    Adoption and upkeep, setup: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Published in the DEV space of AWS's Community Builders program, which only members post to. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE early access, then a paid plan

  51. Positive

    nikolay, Hacker News commenter, self-described

    Comment on: Is vibe coding dying?Hacker News comment

    Gets impressive results from Kiro's spec-based approach, though it takes much longer than generating a program from one prompt.

    Published Oct 23, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-10-23, 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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  52. Negative

    hatmanstack, Hacker News commenter, self-described

    Comment on: Understanding Spec-Driven-Development: Kiro, Spec-Kit, and TesslHacker News comment

    The spec approach generated massive task lists and deleted code unpredictably without reverting. Plain iteration is simpler for this author.

    Published Oct 17, 2025

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-10-17, needs a recheck
    Counts toward
    Reliability, run stability: 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
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  53. Mixed

    Birgitta Böckeler, Distinguished Engineer at Thoughtworks

    Understanding Spec-Driven-Development: Kiro, spec-kit, and TesslEngineering article, martinfowler.com

    Böckeler found Kiro the simplest, most lightweight of three spec tools. Asked to fix a small bug, it produced 4 user stories with 16 acceptance criteria, which the author likened to a sledgehammer cracking a nut, preferring to review code over all those markdown files.

    Published Oct 15, 2025self-described: Hands-on evaluation of three spec-driven tools in September 2025, published on martinfowler.com

    Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Name self-described; employer self-described; role self-described (Distinguished Engineer)
    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
    2025-10-15, needs a recheck
    Counts toward
    Delivered outcomes, task completion: unfavorable, 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, pending a recheck

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE, September 2025

  54. Negative

    jtrn, Hacker News commenter, self-described

    Comment on: Cursor 1.7Hacker News comment

    Asked to build a simple MCP server from documentation, Kiro planned and executed impressively for six hours without reaching a basic MVP.

    Published Oct 1, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-10-01, 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, pending a recheck

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck

  55. Negative

    KaiMagnus, Hacker News commenter, self-described

    Comment on: Getting AI to work in complex codebasesHacker News comment

    The requirements, design, and task documents caught edge cases at first, but the planning still produced mediocre code that was mostly thrown away. Small fast iterations work better for this author.

    Published Sep 24, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-09-24, needs a recheck
    Not counted
    Delivered outcomes, correctness: repeats a stronger account in its group
    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

  56. Mixed

    Ryan Ries, Principal AI and Data Scientist at Mission Cloud

    First Impressions: I got my Kiro beta keyCompany blog post, Mission Cloud

    Ries found the spec mode's requirements interview impressive and finished weeks of work in hours, but Kiro fell into repeated failed fixes and, once long chats were summarized, forgot the scripts he had built with it.

    "But after the chat history got summarized, Kiro completely forgot they existed."
    Excerpt, Ryan Ries

    Published Sep 10, 2025AWS consultancy; leads a team of data engineers, architects and data scientists; built a full-stack app during the beta

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Kiro partner: not counted as independent; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Name self-described; employer unknown; role unknown
    Relationship
    partner (suspected)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2025-09-10, beta, needs a recheck
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds)
    Counts toward
    Delivered outcomes, context handling: unfavorable, G2 (2 units before bounds)
    Not counted
    Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works at Mission Cloud, an AWS Premier Tier Partner. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro beta, spec mode on a React app with Google OAuth

  57. No opinion stated

    Johann Rehberger, security researcher (Embrace The Red)

    AWS Kiro: Arbitrary Code Execution via Indirect Prompt InjectionIndependent security evaluation, Embrace The Red

    Tested Kiro on launch day and found it could write its own settings without approval. A prompt injection in a source file could then allowlist every Bash command or add a malicious MCP server. AWS fixed it by August 5, 2025 in v0.1.42.

    "AWS Kiro was vulnerable to arbitrary command execution via indirect prompt injection."
    Excerpt, Johann Rehberger

    Published Aug 26, 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 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
    2025-08-26, needs a recheck
    Counts toward
    Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Measured
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE at launch, July 2025; fixed in v0.1.42

  58. Negative

    AchintyaAshok, Hacker News commenter, self-described

    Comment on: I got access to Kiro preview. Amazon cannot compete with Claude-codeHacker News comment

    Expected Kiro to beat Claude Code on requirements and planning, but found steering rigid, phases run without enough back-and-forth, limited models, and odd request pricing.

    Published Aug 22, 2025

    Practitioner account, pseudonymous; direct use; not counted, earlier release How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Out of date (earlier release); Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-08-22, out of date
    Not counted
    Adoption and upkeep, setup: excluded, describes an earlier release or was retracted
    Not counted
    Delivered outcomes, task completion: excluded, describes an earlier release or was retracted
    Not counted
    Operational control, models and deployment: excluded, describes an earlier release or was retracted
    Not counted
    Cost predictability and limits, cost transparency: excluded, describes an earlier release or was retracted

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Out of date
    Observed on
    Kiro early access, Claude Sonnet 3.7 and 4

  59. Mixed

    shepardrtc, Hacker News commenter

    Comment on: AWS pricing for Kiro dev tool dubbed 'a wallet-wrecking tragedy'Hacker News comment

    On a greenfield project their vibe requests ran out quickly, so they moved chat work to Copilot and kept Kiro for spec requests, which it handles well.

    Published Aug 18, 2025self-described: Greenfield project, Kiro for specs and VS Code Copilot for the rest

    Practitioner account, pseudonymous; direct use; not counted, earlier release How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Out of date (earlier release)
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-08-18, out of date
    Not counted
    Delivered outcomes, task completion: excluded, describes an earlier release or was retracted
    Not counted
    Cost predictability and limits, limits in practice: excluded, describes an earlier release or was retracted

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Out of date
    Observed on
    Vibe and spec request plans, August 2025

  60. No opinion stated

    supermanonipad, Hacker News commenter

    Comment on: Ask HN: What's the best free AI coding assistant available?Hacker News comment

    Not a programmer, relied on AI coding assistants including Augment Code (1,000 free daily requests) and Kiro IDE (200 free daily requests) until both moved behind paywalls, and asks for still-free alternatives.

    Published Aug 17, 2025self-described: Non-programmer building personal projects

    Practitioner account, pseudonymous; direct use; not counted, earlier release How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Specific details; Out of date (200 free daily requests)
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-08-17, 200 free daily requests, out of date
    Not counted
    Adoption and upkeep, continuity: excluded, describes an earlier release or was retracted

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Out of date
    Observed on
    Kiro IDE early access, 200 free daily requests

  61. Negative

    ChilledTonic, Hacker News commenter, self-described

    Comment on: Kiro Pricing Plans Are Now LiveHacker News comment

    Likes the idea of spec documents and steering, but found them underwhelming in use: they often confused the model more than they produced working code.

    Published Aug 15, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-08-15, 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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  62. No opinion stated

    PseudoComputer, Hacker News commenter

    Comment on: Got tired of bad PDF WebApp so we made a Free, Open-Sourced, Private AlternativeHacker News comment

    Their team used Kiro IDE on Claude 4 for some of the more complicated tools in a PDF web app, such as Sort Pages with its UI and image "preview". The app was a lot more complicated than they thought, so they resorted to vibe coding for some functionality.

    Published Aug 3, 2025self-described: Small team building an open-source PDF web app

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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, Claude 4, 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

    Published on
    Developer Communities
    Who
    Very small team
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE on Claude Sonnet 4

  63. Positive

    sqrtc, Hacker News commenter, self-described

    Comment on: Developing with Kiro: Amazon's New Agentic IDEHacker News comment

    On a hard date-time parsing problem, the spec flow forced careful thinking about the problem, and watching Kiro work the task list was impressive. Terminal runs still needed approval one by one.

    Published Jul 25, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-07-25, needs a recheck
    Not counted
    Delivered outcomes, task completion: repeats a stronger account in its group
    Not counted
    Operational control, execution control: 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
    Still applicable
    Observed on
    Kiro IDE early access

  64. Positive

    Semaphor, Hacker News commenter, self-described

    Comment on: Developing with Kiro: Amazon's New Agentic IDEHacker News comment

    After using it for a while, other tools feel lacking: the multistep spec process keeps the model in line, and they left Kiro only when Sonnet 4 was overloaded.

    Published Jul 25, 2025

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-07-25, Sonnet 4.0, needs a recheck
    Counts toward
    Reliability, service availability: unfavorable, G1 (1 unit before bounds)
    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, pending a recheck

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE early access, Claude Sonnet 4

  65. Mixed

    Cu3PO42, Hacker News commenter

    Comment on: Developing with Kiro: Amazon's New Agentic IDEHacker News comment

    From a short spec, Kiro wrote about 5,000 lines with tests that worked, but the tool was over-engineered, and the author cut it to about 800 lines by hand.

    Published Jul 25, 2025self-described: Personal macOS helper tool, TypeScript

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro 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 Kiro 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
    2025-07-25, needs a recheck
    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 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Measured
    Applies to
    Still applicable
    Observed on
    Kiro IDE early access, TypeScript

  66. Negative

    sgt101, Hacker News commenter, self-described

    Comment on: Developing with Kiro: Amazon's New Agentic IDEHacker News comment

    Kiro spent half a day writing code and tests for an app the author could not use, while Replit plus two hours in Cursor produced a working result.

    Published Jul 25, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-07-25, needs a recheck
    Not counted
    Delivered outcomes, task completion: repeats a stronger account in its group
    Not counted
    Operational control, execution control: 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
    Observed on
    Kiro IDE early access

  67. Positive

    Randall Hunt, chief technology officer at Caylent

    Development environment AWS Kiro offers AI codingConference interview article, theCUBE via SiliconANGLE

    Caylent's CTO argues that the spec-driven mode, which collects and edits requirements before design, sets Kiro apart from Cursor and Windsurf, and calls it the agent for people with agency.

    "“One of the things that sets it apart from other IDEs like Cursor or Windsurf for Codeium … is a spec-driven development model,” Hunt said."
    Excerpt, Randall Hunt

    Published Jul 16, 2025AWS Premier Partner consultancy building cloud and AI systems for clients

    Practitioner account, self-described; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Kiro partner: not counted as independent; Opinion; Needs recheck after 12 months
    Role
    Name self-described; employer unknown; role unknown
    Relationship
    partner (suspected); partner (self disclosed); affiliate (self disclosed)
    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
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author is CTO of Caylent, an AWS Premier Tier Services Partner. Kept in the record; it takes part in no figure.

    Published on
    Talks & Podcasts
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro early access, two days after launch

  68. Mixed

    willsmith72, Hacker News commenter, self-described

    Comment on: Kiro: A new agentic IDEHacker News comment

    First impressions: autopilot should be off by default as in Claude Code and Cline, the Kiro panel ignores the user's sidebar layout, and the chat box is busy.

    Published Jul 15, 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 Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    2025-07-15, needs a recheck
    Not counted
    Operational control, execution control: 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
    Observed on
    Kiro IDE early access

  69. Positive

    danudey, Hacker News commenter

    Comment on: Cognition (Devin AI) to Acquire WindsurfHacker News comment

    Where Copilot and Cursor had produced broken code, Kiro wrote requirements, a design, and a traced task list, then working Rust code for a project the author barely knew.

    Published Jul 15, 2025self-described: Own Rust project rust-downloader, new to Rust

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro 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 Kiro 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 (pull request)
    Date and version
    2025-07-15, needs a recheck
    Counts toward
    Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
    Counts toward
    Delivered outcomes, correctness: favorable, G2 (2 units before bounds)

    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
    Still applicable
    Observed on
    Kiro IDE early access, Rust project

  70. Positive

    danbeaulieu, Hacker News commenter

    Comment on: Kiro: A new agentic IDEHacker News comment

    Having used Kiro, says it builds the spec from both the requirements and the existing code, so the spec covers integration points and skips what the code already does.

    Published Jul 15, 2025self-described: Amazon employee, per profile email

    Practitioner account, pseudonymous; direct use; not counted, tied to the vendor How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Kiro staff: not counted as independent; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (suspected)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2025-07-15, needs a recheck
    Not counted
    Delivered outcomes, context handling: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author's Hacker News profile gives an amazon.com email address, and Amazon makes Kiro. Kept in the record; it takes part in no figure.

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE early access

  71. Mixed

    ActorNightly, Hacker News commenter, self-described

    Comment on: Kiro: A new agentic IDEHacker News comment

    On launch day, liked the product but found Kiro sitting idle with its helper plugin using heavy CPU for no reason.

    Published Jul 14, 2025

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Kiro found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Kiro 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
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance

    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
    Kiro IDE early access

  72. Positive

    Yehuda Cohen, AWS Community Builder, Fun With The Cloud

    Developing with Kiro: Amazon's New Agentic IDEPersonal blog post, Substack

    Built a portfolio site in about four hours with zero lines of code and had Kiro write steering docs for a Spring Boot + Angular project. Kiro looped on environment issues and went in circles on an 8000-line alchemy contribution until a more detailed spec, then generated roughly 80% of it.

    Published Jul 14, 2025self-described: Early-access tester across a TanStack Start site, Spring Boot and Angular projects, open-source pull requests, and internal CLI tools

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Kiro partner: not counted as independent; Used it directly; Needs recheck after 12 months; Specific details
    Role
    Name self-described; employer unknown; role unknown
    Relationship
    program member (suspected); program member (self disclosed)
    How they know
    Used it directly
    Support
    1 artifact (pull request)
    Date and version
    2025-07-14, public preview, needs a recheck
    Counts toward
    Delivered outcomes, correctness: unfavorable, G1 (1 unit before bounds)
    Counts toward
    Reliability, run stability: unfavorable, 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, context handling: excluded, praise from someone tied to the vendor, kept as an attributed position
    Not counted
    Adoption and upkeep, setup: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author is in AWS's Community Builders program, which gave him early access to Kiro. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro IDE early access

  73. Positive

    Guille Ojeda, Principal Innovation Architect at Caylent

    Kiro: First ImpressionsCompany blog post, Caylent

    After testing Kiro for a few weeks, Ojeda calls it particularly suitable for enterprise teams that prioritize maintainability and documentation over raw speed. Notes specs add overhead to initial development, rapid-prototyping teams "might find" it too structured, and suggests planning 2-3 weeks of setup and team training.

    "I'd suggest you plan for 2-3 weeks of setup and team training to see meaningful productivity gains."
    Excerpt, Guille Ojeda

    Published Jul 14, 2025AWS Premier Partner consultancy; a few weeks of partner access before launch

    Practitioner account; direct use; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Kiro partner: not counted as independent; Used it directly; Needs recheck after 12 months; Specific details
    Role
    Name unknown; employer unknown; role unknown
    Relationship
    partner (suspected); partner (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2025-07-14, Claude 4 Sonnet, needs a recheck
    Counts toward
    Adoption and upkeep, setup: mixed, G1 (1 unit before bounds), capped: C-unknown-control
    Not counted
    Cost predictability and limits, cost transparency: excluded, praise from someone tied to the vendor, kept as an attributed position

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Not counted

    Its author works at Caylent, an AWS Premier Tier Services Partner. Kept in the record; it takes part in no figure.

    Published on
    Engineering Blogs & Reviews
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Kiro early access with Claude Sonnet 4

Product documentation 16

Pages from Amazon Web Services, used to check facts for every group.

  1. Kiro pricing

    Lists Free with 50 credits, Pro at US$20, Pro+ at US$40, Pro Max at US$100, and Power at US$200 per user per month. Paid plans include 1,000 to 10,000 credits, and add-on credits cost US$0.04 each.

    Checked Oct 12, 2026

  2. Kiro FAQ

    Explains credits, the Auto agent and model choice, which surfaces a subscription covers, and that content from IAM Identity Center users is not used for service improvement.

    Checked Oct 12, 2026

  3. Models

    Lists each model's context window, credit multiplier relative to Auto, plan availability, and whether inference stays in the US or EU geography or routes globally.

    Checked Oct 12, 2026

  4. Specs

    Documents feature and bugfix specs built from requirements.md or bugfix.md, design.md, and tasks.md, with tasks run one at a time or in parallel waves.

    Checked Oct 12, 2026

  5. Steering

    Documents workspace, global, and team steering files, including team files pushed to developer machines through MDM, and AGENTS.md support.

    Checked Oct 12, 2026

  6. Hooks

    Documents event-driven hooks that run shell commands or agent prompts when the agent edits files, calls tools, or finishes a task.

    Checked Oct 12, 2026

  7. Permissions

    Documents capability-based allow, ask, and deny rules for file access, shell commands, web tools, and MCP, where a deny rule always wins.

    Checked Oct 12, 2026

  8. Kiro CLI

    Describes Kiro CLI for terminal workflows, custom agents, headless runs in pipelines, and ACP connections to other editors.

    Checked Oct 12, 2026

  9. Upgrading from Amazon Q Developer CLI

    States that Kiro CLI is the next update of Q Developer CLI, available from November 17, 2025, and that Q Developer Pro subscriptions keep working in it.

    Checked Oct 12, 2026

  10. Migrating from Amazon Q Developer

    Compares Q Developer IDE extensions with Kiro IDE and Kiro CLI, and gives migration steps for VS Code, JetBrains, Visual Studio, and Eclipse users.

    Checked Oct 12, 2026

  11. Cloud sessions

    Describes agent sessions in a managed cloud sandbox, included in paid plans with no separate compute charge, up to 10 at a time.

    Checked Oct 12, 2026

  12. Enterprise governance

    Documents admin controls for approved models, MCP servers through a registry, API keys, web tools, sign-in methods, and cloud sessions.

    Checked Oct 12, 2026

  13. Enterprise settings

    Lists profile settings for customer managed keys, code references, the usage dashboard, user activity reports, prompt logging, MCP, web tools, and overages.

    Checked Oct 12, 2026

  14. Enterprise billing

    Explains per-user tiers billed through AWS, opt-in overages, proration, and per-user cost lookup in AWS Billing and Cost Management.

    Checked Oct 12, 2026

  15. Data protection

    States what Kiro stores by user type, that enterprise content is not used for service improvement, and how Free and individual users opt out.

    Checked Oct 12, 2026

  16. Compliance validation

    States that Kiro IDE and CLI are HIPAA eligible and that Kiro is in scope of AWS's ISO/IEC 27001:2022 certification.

    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
SourceOriginal URLAuthor and contextWhoPublishedReview dateAppliesFindings
Reliability regression: file edits fail, IDE freezes, spec operations die with network errors, and in-app bug reporter is brokenID sx-02 | Developer Communitiesgithub.com/kirodotdev/Kiro/issues/11754rsammons, GitHub userself-described: Kiro IDE 1.1.14 on Windows 11 Business, spec-driven workIndividual practitionerPublished Oct 2, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Our decision on Cursor following its acquisition by SpaceXID dc-40 | Developer Communitiesnews.ycombinator.com/item?id=49507987s4i, Hacker News commenter, self-describedIndividual practitionerPublished Aug 31, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Meta Security Researcher's AI Agent Accidentally Deleted Her EmailsID dc-41 | Developer Communitiesnews.ycombinator.com/item?id=49508101codeduck, Hacker News commenter, self-describedIndividual practitionerPublished Aug 31, 2026Assessment reviewed Nov 1, 2026Current
Kiro IDE - Extension host crashes when processing large LLM responses (event loop blocked)ID sx-04 | Developer Communitiesgithub.com/kirodotdev/Kiro/issues/10701rgoltz, GitHub userself-described: Two Kiro instances on Windows 11, spec sessions with subagentsIndividual practitionerPublished Aug 6, 2026Assessment reviewed Nov 1, 2026Current
Kiro CLI Gets Worse After an Hour. Here's How I Fixed It.ID ir-25 | Engineering Blogs & Reviewsdev.to/aws-builders/kiro-cli-gets-worse-after-an-hour-heres-how-i-fixed-it-1l7gEngineer working daily across AWS accountsself-described: Daily AWS operations work with Kiro CLIIndividual practitionerPublished Jul 16, 2026Assessment reviewed Nov 1, 2026CurrentNot counted. Published in the DEV space of AWS's Community Builders program, which only members post to.
Comment on: GLM 5.2 and the coming AI margin collapseID dc-39 | Developer Communitiesnews.ycombinator.com/item?id=48813890danny_codes, Hacker News commenter, self-describedIndividual practitionerPublished Jul 7, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Codex logging bug may write TBs to local SSDsID dc-37 | Developer Communitiesnews.ycombinator.com/item?id=48629256iLoveOncall, Amazon engineerself-described: Amazon or AWS engineer describing internal useIndividual practitionerPublished Jun 22, 2026Assessment reviewed Nov 1, 2026CurrentNot counted. Its author works for Amazon, which makes Kiro.
Comment on: Codex logging bug may write TBs to local SSDsID dc-38 | Developer Communitiesnews.ycombinator.com/item?id=48630622epistasis, Hacker News commenter, self-describedIndividual practitionerPublished Jun 22, 2026Assessment reviewed Nov 1, 2026Current
Comment on: AI coding at home without going brokeID dc-36 | Developer Communitiesnews.ycombinator.com/item?id=48520954astqs, Hacker News commenter, self-describedIndividual practitionerPublished Jun 13, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: 'Sloppenheimer:' Amazon employees mock the company's AI on SlackID dc-35 | Developer Communitiesnews.ycombinator.com/item?id=48467123isengard3000, Amazon employeeself-described: Amazon or AWS engineer describing internal useIndividual practitionerPublished Jun 9, 2026Assessment reviewed Nov 1, 2026CurrentNot counted. Its author works for Amazon, which makes Kiro.
Comment on: 'Sloppenheimer:' Amazon employees mock the company's AI on SlackID dc-53 | Developer Communitiesnews.ycombinator.com/item?id=48464729sparrc, AWS engineerself-described: AWS; most engineers use Kiro, with team-specific skills and an org MCP server for on-callOrganization-widePublished Jun 9, 2026Assessment reviewed Nov 1, 2026CurrentNot counted. Its author works for Amazon, which makes Kiro.
Comment on: Ask HN: What was your "oh shit" moment with GenAI?ID dc-52 | Developer Communitiesnews.ycombinator.com/item?id=48428607korbonits, Hacker News commenter, self-describedIndividual practitionerPublished Jun 6, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Alphabet announces $80B equity capital raise to expand AI infra and computeID dc-51 | Developer Communitiesnews.ycombinator.com/item?id=48368019marysol5, Hacker News commenterself-described: Uses Kiro and Gemini at workIndividual practitionerPublished Jun 2, 2026Assessment reviewed Nov 1, 2026Current
Comment on: AI sticker shock hits corporate AmericaID dc-34 | Developer Communitiesnews.ycombinator.com/item?id=48308504forgotaccount3, Hacker News commenterself-described: Employer-wide Kiro deployment with overages enabledOrganization-widePublished May 28, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Microsoft starts canceling Claude Code licensesID dc-33 | Developer Communitiesnews.ycombinator.com/item?id=48246824Insanity, Amazon engineerself-described: Amazon or AWS engineer describing internal useIndividual practitionerPublished May 23, 2026Assessment reviewed Nov 1, 2026CurrentNot counted. Its author works for Amazon, which makes Kiro.
Comment on: Show HN: I Made a Claude Skill for Spec-Driven Development (SDD)ID dc-50 | Developer Communitiesnews.ycombinator.com/item?id=48221805NTRIXLM, Hacker News commenterself-described: Team on a shared Claude subscription; Kiro not provided by the employerIndividual practitionerPublished May 21, 2026Assessment reviewed Nov 1, 2026Current
When a Kiro CLI Update Silently Breaks Your MCP Servers: The Approved Environment Variables GotchaID ir-24 | Engineering Blogs & Reviewsdev.to/greennnote/when-a-kiro-cli-update-silently-breaks-your-mcp-servers-the-approved-environment-variables-gotcha-15g2Developerself-described: Daily Kiro CLI workflow with MCP serversIndividual practitionerPublished May 21, 2026Assessment reviewed Nov 1, 2026Current
Comment on: I believe there are entire companies right now under AI psychosisID dc-32 | Developer Communitiesnews.ycombinator.com/item?id=48161765Miner49er, Hacker News commenterself-described: On a team, Kiro plan at $20 a month for 1000 creditsVery small teamPublished May 16, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Amazon rolls out Claude Code and Codex internallyID dc-31 | Developer Communitiesnews.ycombinator.com/item?id=48019846iLoveOncall, Amazon engineerself-described: Amazon, company-wide internal toolingOrganization-widePublished May 5, 2026Assessment reviewed Nov 1, 2026Still applicableNot counted. Its author works for Amazon, which makes Kiro.
Comment on: Uncle Bob: It's OverID dc-30 | Developer Communitiesnews.ycombinator.com/item?id=47999976k3vinw, Hacker News commenterself-described: Team project, refactoring existing codeIndividual practitionerPublished May 3, 2026Assessment reviewed Nov 1, 2026Still applicable
Using Spec Driven Development with AWS Kiro to add the last updated date on Eleventy blogID ir-30 | Engineering Blogs & Reviewsgeshan.com.np/blog/2026/05/aws-kiro/Geshan Manandhar, Geshan's Blogself-described: Personal Eleventy blog, one feature built through a specIndividual practitionerPublished May 3, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Microsoft and OpenAI end their exclusive and revenue-sharing dealID dc-49 | Developer Communitiesnews.ycombinator.com/item?id=47927373topce, Hacker News commenterself-described: Uses both GitHub Copilot and KiroIndividual practitionerPublished Apr 27, 2026Assessment reviewed Nov 1, 2026Needs a recheck
Kiro Forgets Everything Every Session. So I've Built It a Memory.ID ir-21 | Engineering Blogs & Reviewsdev.to/tverney_77/kiro-forgets-everything-every-session-so-ive-built-it-a-memory-1e86Developerself-described: Daily Kiro CLI use on a TypeScript CLI projectIndividual practitionerPublished Apr 27, 2026Assessment reviewed Nov 1, 2026Out of dateOut of date, counts toward nothing current
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageID dc-29 | Developer Communitiesnews.ycombinator.com/item?id=47739622geeky4qwerty, Hacker News commenterself-described: Kiro as IDE and Codex as CLI, also pays for Google ProIndividual practitionerPublished Apr 12, 2026Assessment reviewed Nov 1, 2026Still applicable
Kiro showcase: Automating Changes Across Several Repos with Spec-Driven Development and Custom Sub-AgentsID ir-18 | Engineering Blogs & Reviewsdev.to/dvddpl/kiro-showcase-automating-changes-across-several-repos-with-spec-driven-development-and-custom-8boEngineering manager, cloud infrastructure platform teamself-described: Platform team responsible for Terraform across 200+ repositoriesTechnical leadershipPublished Apr 7, 2026Assessment reviewed Nov 1, 2026Still applicable
Kiro subscription assignment fails on Organizations management account and routes to standalone CreateAssignment pathID sx-05 | Developer Communitiesgithub.com/kirodotdev/Kiro/issues/7089imtaxu, GitHub user and AWS Organizations administratorself-described: AWS Organizations management account assigning paid Kiro plans to IAM Identity Center users and groupsOrganization-widePublished Apr 2, 2026Assessment reviewed Nov 1, 2026Current
Comment on: AWS Kiro accounts suspended en masse - AWS flagging fraud detection issuesID dc-28 | Developer Communitiesnews.ycombinator.com/item?id=47474508huey77, Hacker News commenterself-described: Building workern.io in Melbourne, on Kiro $200/month Power planIndividual practitionerPublished Mar 22, 2026Assessment reviewed Nov 1, 2026Needs a recheck
Kiro for Test-Driven Development (TDD)ID ir-15 | Engineering Blogs & Reviewsdev.to/dhelper/kiro-for-test-driven-development-tdd-11meSoftware developer and TDD trainerself-described: Solo kata experimentIndividual practitionerPublished Mar 16, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Ask HN: How is AI-assisted coding going for you professionally?ID dc-26 | Developer Communitiesnews.ycombinator.com/item?id=47391478konaraddi, AWS engineerself-described: Amazon or AWS engineer describing internal useIndividual practitionerPublished Mar 15, 2026Assessment reviewed Nov 1, 2026Still applicableNot counted. Its author works for Amazon, which makes Kiro.
Comment on: Ask HN: How is AI-assisted coding going for you professionally?ID dc-27 | Developer Communitiesnews.ycombinator.com/item?id=47392420humbleharbinger, Amazon engineerself-described: Amazon or AWS engineer describing internal useIndividual practitionerPublished Mar 15, 2026Assessment reviewed Nov 1, 2026Still applicableNot counted. Its author works for Amazon, which makes Kiro.
Comment on: 1M context is now generally available for Opus 4.6 and Sonnet 4.6ID dc-48 | Developer Communitiesnews.ycombinator.com/item?id=47373485avereveard, Hacker News commenterself-described: Kiro at work, Roo Code at homeIndividual practitionerPublished Mar 14, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: After outages, Amazon to make senior engineers sign off on AI-assisted changesID dc-25 | Developer Communitiesnews.ycombinator.com/item?id=47330762wenc, Hacker News commenterself-described: Kiro IDE as spec generator, headless CLI agents in tmux for implementationIndividual practitionerPublished Mar 11, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: After outages, Amazon to make senior engineers sign off on AI-assisted changesID dc-24 | Developer Communitiesnews.ycombinator.com/item?id=47325484daheza, Hacker News commenterself-described: Senior engineering manager, team moving a monolith into AWSIndividual practitionerPublished Mar 10, 2026Assessment reviewed Nov 1, 2026Still applicableListed, no finding position
Comment on: Amazon holds engineering meeting following AI-related outagesID dc-47 | Developer Communitiesnews.ycombinator.com/item?id=47323127stavarotti, Hacker News commenter, self-describedIndividual practitionerPublished Mar 10, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: How I use Claude Code: Separation of planning and executionID dc-22 | Developer Communitiesnews.ycombinator.com/item?id=47107951achenatx, Hacker News commenter, self-describedIndividual practitionerPublished Feb 22, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: How I use Claude Code: Separation of planning and executionID dc-23 | Developer Communitiesnews.ycombinator.com/item?id=47111077mlaretallack, Hacker News commenter, self-describedIndividual practitionerPublished Feb 22, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Ask HN: Are you using an agent orchestrator to write code?ID dc-46 | Developer Communitiesnews.ycombinator.com/item?id=46999385mlaretallack, Hacker News commenterself-described: Runs about four projects at once, one Kiro instance per desktop workspaceIndividual practitionerPublished Feb 13, 2026Assessment reviewed Nov 1, 2026Still applicable
Kiro: AI spec-driven delivery and what it means for the future of software developmentID ld-03 | Engineering Blogs & Reviewswww.leighton.com/insights/kiro-ai-spec-driven-delivery-and-what-it-means-for-the-future-of-software-developmentLee Gilmore, Principal Cloud Architect and AWS Community Lead at LeightonUK software consultancy with an AWS practice delivering client projectsTechnical leadershipPublished Feb 13, 2026Assessment reviewed Nov 1, 2026CurrentNot counted. Its author is AWS Community Lead at Leighton, an AWS consulting partner.
New sessions immediately hit 85%+ context usage and enter summarization loop, even with minimal steering docs and simple promptsID sx-03 | Developer Communitiesgithub.com/kirodotdev/Kiro/issues/4992smarchypants, GitHub userself-described: Home automation workspace with three MCP servers, using Kiro for 6+ monthsIndividual practitionerPublished Jan 18, 2026Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: How do you pick a Coding Agent HN?ID dc-45 | Developer Communitiesnews.ycombinator.com/item?id=46634773hmokiguess, Hacker News commenterself-described: Compares Claude Code, Codex, and KiroIndividual practitionerPublished Jan 15, 2026Assessment reviewed Nov 1, 2026Still applicable
What I Learned Using Specification-Driven Development with KiroID ir-14 | Engineering Blogs & Reviewsdev.to/aws-builders/what-i-learned-using-specification-driven-development-with-kiro-pdjEngineerself-described: A real project, soloIndividual practitionerPublished Jan 12, 2026Assessment reviewed Nov 1, 2026Still applicableNot counted. Published in the DEV space of AWS's Community Builders program, which only members post to.
Comment on: Anthropic blocks third-party use of Claude Code subscriptionsID dc-19 | Developer Communitiesnews.ycombinator.com/item?id=46553871sirtaj, Hacker News commenterself-described: At workIndividual practitionerPublished Jan 9, 2026Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Anthropic blocks third-party use of Claude Code subscriptionsID dc-20 | Developer Communitiesnews.ycombinator.com/item?id=46554344elfly, Hacker News commenter, self-describedIndividual practitionerPublished Jan 9, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Anthropic blocks third-party use of Claude Code subscriptionsID dc-21 | Developer Communitiesnews.ycombinator.com/item?id=46555342cobolcomesback, Hacker News commenter, self-describedIndividual practitionerPublished Jan 9, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: How Google got its groove back and edged ahead of OpenAIID dc-18 | Developer Communitiesnews.ycombinator.com/item?id=46540927thegagne, Hacker News commenterself-described: Software engineering architect, developer productivity golden pathsIndividual practitionerPublished Jan 8, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Opus 4.5 is not the normal AI agent experience that I have had thus farID dc-17 | Developer Communitiesnews.ycombinator.com/item?id=46521873falkensmaize, Hacker News commenterself-described: At work, TypeScript monorepo with about 20 appsIndividual practitionerPublished Jan 7, 2026Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: The future of software development is software developersID dc-16 | Developer Communitiesnews.ycombinator.com/item?id=46434560CuriouslyC, Hacker News commenterself-described: CEO and chief scientist of Sibylline Software, building a spec-driven dev toolIndividual practitionerPublished Dec 30, 2025Assessment reviewed Nov 1, 2026Still applicable
I Stopped Fighting My AI How Kiro's agent hooks and steering files fixed my biggest frustration with AI coding toolsID ir-09 | Engineering Blogs & Reviewsdev.to/ibrahimpima/i-stopped-fighting-my-ai-how-kiros-agent-hooks-and-steering-files-fixed-my-biggest-frustration-493mDeveloperself-described: Solo, React and Node dashboardIndividual practitionerPublished Nov 26, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Gemini 3ID dc-15 | Developer Communitiesnews.ycombinator.com/item?id=45977765lan321, Hacker News commenterself-described: Works under company policy on LLM agent repo accessIndividual practitionerPublished Nov 19, 2025Assessment reviewed Nov 1, 2026Still applicable
Brilliant, Broken, and Frustrating: My Deep Dive into Amazon's Kiro AI IDE, the Flawed Junior DeveloperID ir-08 | Engineering Blogs & Reviewsdev.to/aws-builders/brilliant-broken-and-frustrating-my-deep-dive-into-amazons-kiro-ai-ide-the-flawed-junior-gn5Developer writing in the AWS Community Builders organization on DEVself-described: Solo, personal projectsIndividual practitionerPublished Oct 24, 2025Assessment reviewed Nov 1, 2026Needs a recheckNot counted. Published in the DEV space of AWS's Community Builders program, which only members post to.
Comment on: Is vibe coding dying?ID dc-14 | Developer Communitiesnews.ycombinator.com/item?id=45677617nikolay, Hacker News commenter, self-describedIndividual practitionerPublished Oct 23, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Understanding Spec-Driven-Development: Kiro, Spec-Kit, and TesslID dc-13 | Developer Communitiesnews.ycombinator.com/item?id=45614020hatmanstack, Hacker News commenter, self-describedIndividual practitionerPublished Oct 17, 2025Assessment reviewed Nov 1, 2026Still applicable
Understanding Spec-Driven-Development: Kiro, spec-kit, and TesslID ir-29 | Engineering Blogs & Reviewsmartinfowler.com/articles/exploring-gen-ai/sdd-3-tools.htmlBirgitta Böckeler, Distinguished Engineer at Thoughtworksself-described: Hands-on evaluation of three spec-driven tools in September 2025, published on martinfowler.comIndividual practitionerPublished Oct 15, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Cursor 1.7ID dc-12 | Developer Communitiesnews.ycombinator.com/item?id=45438043jtrn, Hacker News commenter, self-describedIndividual practitionerPublished Oct 1, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Getting AI to work in complex codebasesID dc-11 | Developer Communitiesnews.ycombinator.com/item?id=45358387KaiMagnus, Hacker News commenter, self-describedIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
First Impressions: I got my Kiro beta keyID ld-04 | Engineering Blogs & Reviewswww.missioncloud.com/blog/first-impressions-i-got-my-kiro-beta-keyRyan Ries, Principal AI and Data Scientist at Mission CloudAWS consultancy; leads a team of data engineers, architects and data scientists; built a full-stack app during the betaTechnical leadershipPublished Sep 10, 2025Assessment reviewed Nov 1, 2026Needs a recheckNot counted. Its author works at Mission Cloud, an AWS Premier Tier Partner.
AWS Kiro: Arbitrary Code Execution via Indirect Prompt InjectionID sx-01 | Engineering Blogs & Reviewsembracethered.com/blog/posts/2025/aws-kiro-aribtrary-command-execution-with-indirect-prompt-injection/Johann Rehberger, security researcher (Embrace The Red)self-described: Independent security testing of coding agents during his Month of AI Bugs seriesIndividual practitionerPublished Aug 26, 2025Assessment reviewed Nov 1, 2026Needs a recheckListed, no finding position
Comment on: I got access to Kiro preview. Amazon cannot compete with Claude-codeID dc-10 | Developer Communitiesnews.ycombinator.com/item?id=44985470AchintyaAshok, Hacker News commenter, self-describedIndividual practitionerPublished Aug 22, 2025Assessment reviewed Nov 1, 2026Out of dateOut of date, counts toward nothing current
Comment on: AWS pricing for Kiro dev tool dubbed 'a wallet-wrecking tragedy'ID dc-09 | Developer Communitiesnews.ycombinator.com/item?id=44942897shepardrtc, Hacker News commenterself-described: Greenfield project, Kiro for specs and VS Code Copilot for the restIndividual practitionerPublished Aug 18, 2025Assessment reviewed Nov 1, 2026Out of dateOut of date, counts toward nothing current
Comment on: Ask HN: What's the best free AI coding assistant available?ID dc-44 | Developer Communitiesnews.ycombinator.com/item?id=44934092supermanonipad, Hacker News commenterself-described: Non-programmer building personal projectsIndividual practitionerPublished Aug 17, 2025Assessment reviewed Nov 1, 2026Out of dateOut of date, counts toward nothing current
Comment on: Kiro Pricing Plans Are Now LiveID dc-08 | Developer Communitiesnews.ycombinator.com/item?id=44918292ChilledTonic, Hacker News commenter, self-describedIndividual practitionerPublished Aug 15, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Got tired of bad PDF WebApp so we made a Free, Open-Sourced, Private AlternativeID dc-43 | Developer Communitiesnews.ycombinator.com/item?id=44777902PseudoComputer, Hacker News commenterself-described: Small team building an open-source PDF web appVery small teamPublished Aug 3, 2025Assessment reviewed Nov 1, 2026Needs a recheckListed, no finding position
Comment on: Developing with Kiro: Amazon's New Agentic IDEID dc-04 | Developer Communitiesnews.ycombinator.com/item?id=44680957sqrtc, Hacker News commenter, self-describedIndividual practitionerPublished Jul 25, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Developing with Kiro: Amazon's New Agentic IDEID dc-05 | Developer Communitiesnews.ycombinator.com/item?id=44681330Semaphor, Hacker News commenter, self-describedIndividual practitionerPublished Jul 25, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Developing with Kiro: Amazon's New Agentic IDEID dc-06 | Developer Communitiesnews.ycombinator.com/item?id=44682381Cu3PO42, Hacker News commenterself-described: Personal macOS helper tool, TypeScriptIndividual practitionerPublished Jul 25, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Developing with Kiro: Amazon's New Agentic IDEID dc-07 | Developer Communitiesnews.ycombinator.com/item?id=44683433sgt101, Hacker News commenter, self-describedIndividual practitionerPublished Jul 25, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Development environment AWS Kiro offers AI codingID ld-01 | Talks & Podcastssiliconangle.com/2025/07/16/amazon-kiro-development-environment-ai-deployment-aicloudleaders/Randall Hunt, chief technology officer at CaylentAWS Premier Partner consultancy building cloud and AI systems for clientsTechnical leadershipPublished Jul 16, 2025Assessment reviewed Nov 1, 2026Needs a recheckNot counted. Its author is CTO of Caylent, an AWS Premier Tier Services Partner.
Comment on: Kiro: A new agentic IDEID dc-02 | Developer Communitiesnews.ycombinator.com/item?id=44571958willsmith72, Hacker News commenter, self-describedIndividual practitionerPublished Jul 15, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Cognition (Devin AI) to Acquire WindsurfID dc-03 | Developer Communitiesnews.ycombinator.com/item?id=44576078danudey, Hacker News commenterself-described: Own Rust project rust-downloader, new to RustIndividual practitionerPublished Jul 15, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Kiro: A new agentic IDEID dc-42 | Developer Communitiesnews.ycombinator.com/item?id=44567106danbeaulieu, Hacker News commenterself-described: Amazon employee, per profile emailIndividual practitionerPublished Jul 15, 2025Assessment reviewed Nov 1, 2026Needs a recheckNot counted. Its author's Hacker News profile gives an amazon.com email address, and Amazon makes Kiro.
Comment on: Kiro: A new agentic IDEID dc-01 | Developer Communitiesnews.ycombinator.com/item?id=44562880ActorNightly, Hacker News commenter, self-describedIndividual practitionerPublished Jul 14, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Developing with Kiro: Amazon's New Agentic IDEID ir-28 | Engineering Blogs & Reviewsyehudacohen.substack.com/p/developing-with-kiro-amazons-newYehuda Cohen, AWS Community Builder, Fun With The Cloudself-described: Early-access tester across a TanStack Start site, Spring Boot and Angular projects, open-source pull requests, and internal CLI toolsIndividual practitionerPublished Jul 14, 2025Assessment reviewed Nov 1, 2026Needs a recheckNot counted. Its author is in AWS's Community Builders program, which gave him early access to Kiro.
Kiro: First ImpressionsID ld-02 | Engineering Blogs & Reviewscaylent.com/blog/kiro-first-impressionsGuille Ojeda, Principal Innovation Architect at CaylentAWS Premier Partner consultancy; a few weeks of partner access before launchTechnical leadershipPublished Jul 14, 2025Assessment reviewed Nov 1, 2026Needs a recheckNot counted. Its author works at Caylent, an AWS Premier Tier Services Partner.
Kiro pricingID pd-01 | Product Documentationkiro.dev/pricing/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Kiro FAQID pd-02 | Product Documentationkiro.dev/faq/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
ModelsID pd-03 | Product Documentationkiro.dev/docs/models/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
SpecsID pd-04 | Product Documentationkiro.dev/docs/specs/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
SteeringID pd-05 | Product Documentationkiro.dev/docs/steering/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
HooksID pd-06 | Product Documentationkiro.dev/docs/hooks/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
PermissionsID pd-07 | Product Documentationkiro.dev/docs/permissions/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Kiro CLIID pd-08 | Product Documentationkiro.dev/docs/cli/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Upgrading from Amazon Q Developer CLIID pd-09 | Product Documentationkiro.dev/docs/upgrade-guides/migrating-from-q/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Migrating from Amazon Q DeveloperID pd-10 | Product Documentationkiro.dev/docs/upgrade-guides/migrating-from-q-developer/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Cloud sessionsID pd-11 | Product Documentationkiro.dev/docs/cloud-sessions/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Enterprise governanceID pd-12 | Product Documentationkiro.dev/docs/enterprise/governance/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Enterprise settingsID pd-13 | Product Documentationkiro.dev/docs/enterprise/settings/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Enterprise billingID pd-14 | Product Documentationkiro.dev/docs/enterprise/billing/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Data protectionID pd-15 | Product Documentationkiro.dev/docs/privacy-and-security/data-protection/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only
Compliance validationID pd-16 | Product Documentationkiro.dev/docs/privacy-and-security/compliance-validation/Amazon Web ServicesOfficialNot counted (documentation)No date statedDocumentation checked Oct 12, 2026CurrentVerification only