{"articles":[{"slug":"automating-eval-design-and-hillclimbing-with-claude","title":"Automating eval design and hillclimbing with Claude","subtitle":null,"summary":"Lance Martin (claude.dev) explains principles for production-like evals with held-out sets, then shows how the claude-api skill’s build-eval and hillclimb commands automate design and overfitting-aware improvement—including cost and performance case studies.","content_type":"tutorial","language":"en","canonical_url":"https://claude.dev/blog/automating-eval-design-and-hillclimbing/","author":{"name":"Lance Martin","url":"https://claude.dev/blog/automating-eval-design-and-hillclimbing/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Anthropic","url":"https://www.anthropic.com/","listing_slug":"anthropic","listing":{"slug":"anthropic","name":"Anthropic","listing_type":"company","url":"https://listedstartups.com/companies/anthropic"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Tutorials","slug":"tutorials","url":"https://listedarticles.com/topics/tutorials"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Software Engineering","slug":"software-engineering","url":"https://listedarticles.com/topics/software-engineering"}],"about_listings":[{"slug":"claude","name":"Claude","listing_type":"product","url":"https://listedstartups.com/products/claude"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":462,"reading_minutes":2,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-30T00:16:07.307Z","updated_at":"2026-09-30T00:16:07.307Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/automating-eval-design-and-hillclimbing-with-claude","markdown_url":"https://listedarticles.com/articles/automating-eval-design-and-hillclimbing-with-claude.md","example":false,"citation":"Lance Martin, Anthropic. \"Automating eval design and hillclimbing with Claude.\" 28 Sept 2026. https://claude.dev/blog/automating-eval-design-and-hillclimbing/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://claude.dev/blog/automating-eval-design-and-hillclimbing/"},"snippet":null,"score":null}],"total":1,"count":1,"next_offset":null,"has_more":false,"query":{"q":null,"content_type":"tutorial","topic":"benchmarks","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}