{"type":"analysis","id":"analysis:research-google-s-agents-cli-eval-loop-is-solid-plumbing-but-its-quality-results-come","slug":"research-google-s-agents-cli-eval-loop-is-solid-plumbing-but-its-quality-results-come","title":"Google's Agents CLI eval loop is solid plumbing, but its quality results come from a four-case demo","description":"Google's walkthrough shows generate, grade, compare and a DIY threshold alert catching a prompt regression. The per-case diff is the useful part; the numbers are illustrative, not benchmarks.","published_at":"2026-11-09T16:00:00.000Z","updated_at":"2026-11-09T16:00:00.000Z","record_date":"2026-11-09","topics":["cli","agents","google","research"],"source_urls":["https://developers.googleblog.com/hill-climbing-agent-quality-with-agents-cli-evaluation","https://google.github.io/agents-cli/cli/","https://github.com/google/agents-cli"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-google-s-agents-cli-eval-loop-is-solid-plumbing-but-its-quality-results-come/","markdown":"https://newruntime.com/analysis/research-google-s-agents-cli-eval-loop-is-solid-plumbing-but-its-quality-results-come.md","json":"https://newruntime.com/analysis/research-google-s-agents-cli-eval-loop-is-solid-plumbing-but-its-quality-results-come.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:eedbeae1-173e-4e0e-ae3b-4029319eb351","authorial_article_id":"eedbeae1-173e-4e0e-ae3b-4029319eb351"},"next_reads":[{"type":"topic","path":"/topics/agents/","url":"https://newruntime.com/topics/agents/","title":"Agents","reason":"Explore the agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agents.md","json_url":"https://newruntime.com/topics/agents.json"},{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}