GEPA prompt optimizer
Prompt optimizer in AI tools
Recommended for automatically improving prompts and skill content, with clear tracking of changes. Results vary by model: it can work well for some and poorly for others.
Recommended for automatically improving prompts and skill content, with clear tracking of changes. Results vary by model: it can work well for some and poorly for others.
13 people gave an opinion
- recommend it
- 12
- criticize it
- 1
- approval share
- 92%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 12 people recommend itNeeds 10 or more, met.
- 12 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not 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
Optimizes prompts and skill content
“To avoid that bias, I use GEPA to optimize the prompt for each model/tool/harness combination”
Comment from 11 Mar 2026 in “How are people do AI evals these days?” “using GEPA where you optimize the skill content instead of the prompt works really well”
Comment from 4 Feb 2026 in “Agent Skills” “It extends GEPA (our prompt optimizer, discussed here previously)”
Comment from 22 Feb 2026 in “Optimize_anything: A Universal API for Optimizing Any Text Parameter” - Comment from 22 Feb 2026 in “Optimize_anything: A Universal API for Optimizing Any Text Parameter”
Strong prompt optimization results
“it's really the optimizer (ex. GEPA) doing the heavy-lifting.”
Comment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?” “impressed by its prompt optimization results”
Comment from 23 Feb 2026 in “Optimize_anything: A Universal API for Optimizing Any Text Parameter”
What people warn about
Each mark is one comment
Uneven results across different models
“It actually ended up working really well for some models and horrible for others”
Comment from 4 Feb 2026 in “Show HN: I built "AI Wattpad" to eval LLMs on fiction”
What people said
12 of the 14 comments that mention it, newest first. Each links to the original comment.
“assume you'll throw a frontier model at every mutation”
“Now with Gepa I expect things are getting very interesting”
“GEPA is great and let's you easily visualize / track the changes it makes to the prompt”
“it's really the optimizer (ex. GEPA) doing the heavy-lifting.”
“To avoid that bias, I use GEPA to optimize the prompt for each model/tool/harness combination”
“impressed by its prompt optimization results”
“GEPA (our state of the art prompt optimizer)”
“It extends GEPA (our prompt optimizer, discussed here previously)”
“there is a better way of optimizing and building them using model languages themselves as evaluator and skill builder”
“It actually ended up working really well for some models and horrible for others”
“using GEPA where you optimize the skill content instead of the prompt works really well”
“seems like it could be a reasonable approach for systematic evaluation of skills”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.