AWS Kiro
Ranked 4 of 9 AI code editors by recommenders
Developers like its spec-driven workflow for requirements and tasks, but critics say it struggles with larger epics and does not always follow specs.
Developers like its spec-driven workflow for requirements and tasks, but critics say it struggles with larger epics and does not always follow specs.
73 people gave an opinion
- recommend it
- 36
- criticize it
- 37
- approval share
- 49%
Recommended in 11 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 36 people recommend itNeeds 10 or more, met.
- 0.9 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 11 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong at requirements and specs
“The requirements and tasks, it does really well, but the connection of the epics/larger tasks is where it crumbles mostly.”
Comment from 19 Nov 2025 in “Gemini 3” “AI does not forget requirements when you use a spec driven AI tool like Kiro”
Comment from 30 Dec 2025 in “The Future of Software Development Is Software Developers” “In my experience, it's high-quality for creating and iterating on specs.”
Comment from 12 Mar 2026 in “Kotlin creator's new language: a formal way to talk to LLMs instead of English” - Comment from 11 Mar 2026 in “Amazon is holding a mandatory meeting about AI breaking its systems”
- Comment from 15 Nov 2025 in “Spec-Driven Development: The Waterfall Strikes Back”
Preferred over other coding tools
“All of my coworkers pretty much love using Cline and Kiro.”
Comment from 3 Dec 2025 in “Everyone in Seattle hates AI” “Tbh I’ve found Kiro to be much better than Claude Code.”
Comment from 9 Jan 2026 in “Anthropic bans use of API in OpenCode CLI tool” “I have been loving using Kiro for the same reasons”
Comment from 28 May 2026 in “AI sticker shock hits corporate America” - Comment from 22 Jun 2026 in “Codex logging bug may write TBs to local SSDs”
Worth the money for productivity
“it is clearly a significant productivity increase per dollar spent”
Comment from 28 May 2026 in “AI sticker shock hits corporate America” “My experience is positive. Kiro writes most of my code.”
Comment from 15 Mar 2026 in “Ask HN: How is AI-assisted coding going for you professionally?” “Ultimately it was money well-spent”
Comment from 13 Jun 2026 in “AI Coding at Home Without Going Broke” Prompts you to clarify intent
“Kiro, what we use at work, on the other hand will just prompt you.”
Comment from 2 Jun 2026 in “Alphabet Announces $80B Equity Capital Raise to Expand AI Infra and Compute” “it makes me slow down and think about what I want it to do”
Comment from 22 Feb 2026 in “How I use Claude Code: Separation of planning and execution”
What people warn about
Each mark is one comment
Outages linked to its agent actions
“its hard to stay excited about the tools when they can be down for a week because kiro launched”
Comment from 15 May 2026 in “Amazon workers under pressure to up their AI usage–so they're making up tasks” “how productive was the genius at the AWS who used Kiro to cause that December outage”
Comment from 7 Mar 2026 in “We Might All Be AI Engineers Now” “deleted an entire infrastructure environment, complete with data, config, etc.”
Comment from 25 May 2026 in “Leave Me Behind” - Comment from 22 Mar 2026 in “Reports of code's death are greatly exaggerated”
Fails to finish or respect specs
“I, sadly, couldn't even get it to implement solitaire correctly, but the idea sounds good.”
Comment from 19 Nov 2025 in “Gemini 3” “agents don't respect all the details of the specs it creates enough to make the time investment in super-detailed specs worthwhile”
Comment from 30 Dec 2025 in “The Future of Software Development Is Software Developers” “It never occurred to the AI agent to do some simple cross examination before essentially throwing in the towel?”
Comment from 3 May 2026 in “Uncle Bob: It's Over” Confusing token billing and suspensions
“Three billion dollars sounds about right for a free week of Kiro in the default Agentic mode.”
Comment from 17 Jul 2026 in “Ask HN: Any AWS billing issues known? Amazon forecast of 3 billion dollars” “They took a page from AWS on whatever the hell a Kiro token is supposed to represent.”
Comment from 4 Sep 2026 in “IBM Bob” “My AWS Kiro account was suspended after upgrading to their $200/month Power plan.”
Comment from 22 Mar 2026 in “AWS Kiro accounts suspended en masse – AWS flagging fraud detection issues” Missing features compared with rivals
“Most of my gripes are with the harness, CC is way better.”
Comment from 15 Mar 2026 in “Ask HN: How is AI-assisted coding going for you professionally?” “it's just not there. Most of the features I like in Cursor are missing.”
Comment from 31 Aug 2026 in “Our decision on Cursor following its acquisition by SpaceX”
Other AI code editors people recommend
The four most recommended other AI code editors, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Cursor | 853 | 820 | 51% | 13 | 1 yr65 owners | — |
| Google Antigravity | 337 | 576 | 37% | 13 | 1 mo26 owners | — |
| Windsurf | 42 | 27 | 61% | 10 | — | — |
| AWS KiroThis page | 36 | 37 | 49% | 11 | — | — |
| JetBrains Air | 13 | 21 | 38% | 4 | — | — |
What people said
40 of the 90 comments that mention it, newest first. Each links to the original comment.
“They took a page from AWS on whatever the hell a Kiro token is supposed to represent.”
“it's just not there. Most of the features I like in Cursor are missing.”
“Currently covered by AWS startup credits, though.”
“Three billion dollars sounds about right for a free week of Kiro in the default Agentic mode.”
“well a bit better because you get a better idea of what the harness is doing, but otherwise identical”
“Kiro is surprisingly good, if the interface for saving and resuming was slightly more reliable”
“I prefer it to anything else I've tried”
“Ultimately it was money well-spent”
“Not a really good look for it if it's just smattering use here and there.”
“Kiro, what we use at work, on the other hand will just prompt you.”
“Kiro is of course really good to back into AWS stuff, it knows more about AWS than Amazon themselves!”
“I have been loving using Kiro for the same reasons”
“it is clearly a significant productivity increase per dollar spent”
“deleted an entire infrastructure environment, complete with data, config, etc.”
“its hard to stay excited about the tools when they can be down for a week because kiro launched”
“It never occurred to the AI agent to do some simple cross examination before essentially throwing in the towel?”
“try Amazon Kiro and other companies that run Claude on their own hardware”
“This is exactly happening to engineers at AWS with Kiro causing outages”
“My AWS Kiro account was suspended after upgrading to their $200/month Power plan.”
“Most of my gripes are with the harness, CC is way better.”
“My experience is positive. Kiro writes most of my code.”
“In my experience, it's high-quality for creating and iterating on specs.”
“it's high-quality for creating and iterating on specs”
“The all you can eat model of LLM usage is very tempting compared to say Cursor.”
“how productive was the genius at the AWS who used Kiro to cause that December outage”
“it makes me slow down and think about what I want it to do”
“I can let it run for an hour or more in this mode.”
“starts to get at addressing the inherent issues in LLM based coding assistance, but it is an early step”
“Tbh I’ve found Kiro to be much better than Claude Code.”
“this has been monumentally more efficient than searching the web for a good blog post explaining the concept.”
“agents don't respect all the details of the specs it creates enough to make the time investment in super-detailed specs worthwhile”
“Yes what you are describing is exactly what Kiro solves”
“AI does not forget requirements when you use a spec driven AI tool like Kiro”
“Amazon themselves have already been using in-house versions of this to build AWS for over a year”
“they were showcasing Kiro extensively with real life products that have been built with it”
“a step in the direction of applying AI across the entire SDLC”
“All of my coworkers pretty much love using Cline and Kiro.”
“The requirements and tasks, it does really well, but the connection of the epics/larger tasks is where it crumbles mostly.”
“I, sadly, couldn't even get it to implement solitaire correctly, but the idea sounds good.”
“Amazon's Kiro is incredibly spec driven.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.