JetBrains AI
Shares rank 20 of 41 coding agents by recommenders
Recommended for its integration with Claude Code and other agent tools and for switching models inside JetBrains IDEs. Critics say suggestions and output are often inaccurate.
Recommended for its integration with Claude Code and other agent tools and for switching models inside JetBrains IDEs. Critics say suggestions and output are often inaccurate.
41 people gave an opinion
- recommend it
- 14
- criticize it
- 27
- approval share
- 34%
Recommended in 7 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 14 people recommend itNeeds 10 or more, met.
- 0.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 7 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
Good value for the money
“I only pay for the $100 annual plan with jetbrains and that's plenty.”
Comment from 21 Jan 2026 in “Vibecoding #2” “how you can get the best bang for your buck”
Comment from 22 Jan 2026 on Hacker News “Do I still get value? Definitely. But it's not the easy life either.”
Comment from 4 Feb 2026 in “Anthropic Claude Max $200/mo: They claim 99% uptime, I calculated 84% Loss: $780” Accurate, useful suggestions and output
“I repeatedly went “oh! Huh!”, so … in that form, it seems very good”
Comment from 10 Jul 2026 in “Write code like a human will maintain it” “it was consistently, surprisingly, very accurate”
Comment from 31 Jul 2026 in “2x, not 10x: coding with LLMs in 2026” “I've been fine with its output mostly”
Comment from 7 Apr 2026 in “Claude Code is locking people out for hours” Works with Claude Code and other harnesses
“JetBrains AI assistant supports ClaudeCode, Codex and any ACP harness including OpenCode”
Comment from 6 Oct 2026 in “JetBrains reports revenue growth, net financial loss for 2025” “despite the great integration it provides for claude code”
Comment from 12 Feb 2026 in “Multi-vector Grep for code agents, save 15% tokens, local”
What people warn about
Each mark is one comment
Output quality inconsistent or poor
“too many silly suggestions that are simply syntax errors”
Comment from 20 Jan 2026 in “Apple testing new App Store design that blurs the line between ads and results” “I tried Kilo Code and CoPilot and JetBrain's agent and others direct against Sonnet 4 and the output was ... not good”
Comment from 2 Nov 2025 in “How I use every Claude Code feature” “it was hot garbage. It guessed the right/acceptable completion about 30% of the time at best.”
Comment from 31 Jul 2026 in “2x, not 10x: coding with LLMs in 2026” Separate, unclear pricing and credit limits
“They also tried to push AI feature set as a separate subscription which is just insane in current tooling market.”
Comment from 6 Oct 2026 in “JetBrains reports revenue growth, net financial loss for 2025” “JetBrains was pushing their own service whose pricing wasn't transparent and just didn't hold up to SotA.”
Comment from 6 Oct 2026 in “JetBrains reports revenue growth, net financial loss for 2025” “I quickly run out of the JetBrains AI 35 monthly credits for $300/yr”
Comment from 5 Feb 2026 in “My AI Adoption Journey” Deletes needed code or inserts bugs
“they have deleted code that I definitely still needed, and I had to reject those changes”
Comment from 14 May 2026 in “God Damn AI is making me dumb” “insert hard-to-spot bugs, like two nested for loops with i and j for loop index variables”
Comment from 7 May 2026 in “Appearing Productive in the Workplace” Cluttered, bolted-on AI features
“AI Chat is a bolted-on afterthought that looks like a hackathon project and functions like one.”
Comment from 6 Oct 2026 in “JetBrains reports revenue growth, net financial loss for 2025” “their AI tools are extremely in your face while also being underwhelming”
Comment from 25 Oct 2026 in “JetBrains Thinkrail” “They have multiple confusing overlapping products/modes going on.”
Comment from 6 Oct 2026 in “JetBrains reports revenue growth, net financial loss for 2025”
Other coding agents people recommend
The four most recommended other coding agents, 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 |
|---|---|---|---|---|---|---|
| GitHub Copilot | 571 | 993 | 37% | 12 | 1 yr46 owners | — |
| oh-my-pi | 104 | 28 | 79% | 9 | 2 mo5 owners | Approved |
| Grok Build CLI | 66 | 114 | 37% | 6 | — | — |
| DeepSeek Harness | 63 | 28 | 69% | 4 | 1 mo5 owners | Approved |
| JetBrains AIThis page | 14 | 27 | 34% | 7 | — | — |
What people said
40 of the 45 comments that mention it, newest first. Each links to the original comment.
“Their AI implementations are an absolute mess.”
“their AI tools are extremely in your face while also being underwhelming”
“which is worse than what people already pay for”
“for me far more useful than either Air or ThinkRail”
“JetBrains AI assistant supports ClaudeCode, Codex and any ACP harness including OpenCode”
“I loved switching between models”
“JetBrains was pushing their own service whose pricing wasn't transparent and just didn't hold up to SotA.”
“They have multiple confusing overlapping products/modes going on.”
“didn’t help that there early model was terrible”
“They also tried to push AI feature set as a separate subscription which is just insane in current tooling market.”
“it literally did not function. I purchased it, and it kept giving me licensing errors”
“AI Chat is a bolted-on afterthought that looks like a hackathon project and functions like one.”
“few things that are deal breakers for me”
“They need to fix how their AI Chat works.”
“they are burning piles of money on areas I never hear anyone talking about using”
“it was hot garbage. It guessed the right/acceptable completion about 30% of the time at best.”
“it was consistently, surprisingly, very accurate”
“I repeatedly went “oh! Huh!”, so … in that form, it seems very good”
“paying more for their AI becomes mandatory”
“they run locally a model and it start to burn the whole computer”
“we've invested so much in our AI integration, are you sure you don't want to use it?”
“they have deleted code that I definitely still needed, and I had to reject those changes”
“insert hard-to-spot bugs, like two nested for loops with i and j for loop index variables”
“I've been fine with its output mostly”
“despite the great integration it provides for claude code”
“I quickly run out of the JetBrains AI 35 monthly credits for $300/yr”
“Do I still get value? Definitely. But it's not the easy life either.”
“suddenly showing only blank window, nothing else. So, not getting anything out of it.”
“Surprising how badly Jetbrains implemented AI.”
“how you can get the best bang for your buck”
“I only pay for the $100 annual plan with jetbrains and that's plenty.”
“too many silly suggestions that are simply syntax errors”
“even though it wasn’t good. It never improved.”
“it's quite odd that they can't get AI tools to work”
“It's a bit janky right now, but it is definitely getting better.”
“What's incredible is just how bad it works.”
“It just seems for the past couple years they have been primarily distracted with AI”
“Not as great as cursor tab, but nothing is.”
“they opted to try and make money off of it”
“I tried Kilo Code and CoPilot and JetBrain's agent and others direct against Sonnet 4 and the output was ... not good”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.