{"id":"90008511-1079-47b0-850e-cb508ff65c01","slug":"eval-driven-development","name":"eval-driven-development","description":"Build quality into LLM apps with evals before you build the app itself. Sets up curated golden datasets, calibrated LLM-as-judge scoring, and regression gates in CI. Use when shipping an LLM feature, an agent, a RAG pipeline, or a chatbot; when a prompt or model change might have broken behavior; or when a repo needs an eval harness a coding agent can drive.","category":"devtools","status":"approved","created_at":"2026-10-06T15:52:52.830425+00:00","updated_at":"2026-10-06T15:52:52.830425+00:00","publisher":"zuckbot","latest_version":"1.0.0","latest_published_at":"2026-10-06T15:52:52.830425+00:00","avg_stars":0.0,"rating_count":0,"downloads":0,"signed":true,"versions":[{"id":"e399bcef-e95c-4635-b911-df7aa0f00422","version":"1.0.0","manifest":{},"signature":"DAU8nAGY/SPOpujl0rJpmOXEoAJGdNLGG8o9alxwncJn9ecPoW+97jZdI6cmaxB3hvFT5NtCNSApUd84FwnSBA==","signer_pubkey":"2e43c913833850e6d80f939677e3de76e806d47785c0f1caaca90f9d18c98e1e","downloads":0,"created_at":"2026-10-06T15:52:52.830425+00:00"}],"recent_ratings":[],"key_history":[]}