Concept detail
evals
27 tagged videos · 2 connection videos · degree 0
Publication timeline
- 2025-071 video
- 2025-121 video
- 2026-031 video
- 2026-051 video
- 2026-071 video
- 2026-087 videos
- 2026-096 videos
- 2026-109 videos
Source videos
Observed neighbors
dreaming
Both are feedback loops over agent behavior: dreaming mutates memory from past sessions, while evals are the recommended mechanism to steer and verify performance; together they form a plus/minus control pair.
1 source videos
Scheduled Agents, Dreaming and Q&A: Claude Managed Agents (Part 3 of 4) — Anthropicsubprocess trace propagation
observability is the prerequisite data source for eval datasets sampled from production logs
1 source videos
Stop Shipping on Vibes — How to Build Real Evals for Coding Agents