build-eval + hillclimb bring real eval tooling to Claude Code agents
Arindam_1729 · x · 2026-09-29
A practical eval tooling combo for Claude Code: build-eval auto-generates evals from production traces, while hillclimb iterates to push accuracy up and cost down. It accompanies Anthropic's 45-minute "Evals for Taste" session, which walks through wiring a slide-generation Managed Agent, scoring it against SlidesBench, and iterating prompts from failures — turning "this looks bad" into a number you can optimize.
More from coding & agent
- Baseten's Guide: Evaluate Open Models for Coding Agents on Your Own PRs — baseten · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16