Skip to content
ClaudeClaude

Teaching agents to learn from your team

Agent that improves itself daily by treating instructions as code: edited, reviewed, merged like any PR. Writing skills that teach agents how to think (not what to do). Closing feedback loop so team judgment flows back automatically.

May 22, 202628mWatch on YouTube ↗

Episode Details

EPISODE INFO

Released
May 22, 2026
Duration
28m
Channel
Claude
Watch on YouTube
▶ Open ↗

EPISODE DESCRIPTION

Agent that improves itself daily by treating instructions as code: edited, reviewed, merged like any PR. Writing skills that teach agents how to think (not what to do). Closing feedback loop so team judgment flows back automatically.

EPISODE SUMMARY

In this episode of Claude, Teaching agents to learn from your team explores how Warp’s Buzz agent learns from team feedback loops daily Warp built Buzz to triage and draft responses for thousands of social mentions monthly, saving a small team time while keeping human authenticity for final replies.

RELATED EPISODES

How we Claude Code

How we Claude Code

Agent Battle: Mine the most diamonds in 45 minutes

Agent Battle: Mine the most diamonds in 45 minutes

Evals for taste: Hill-climbing a slide-generation agent

Evals for taste: Hill-climbing a slide-generation agent

Agents that remember

Agents that remember

Tool, skill, or subagent? Decomposing an agent that outgrew its prompt

Tool, skill, or subagent? Decomposing an agent that outgrew its prompt

Making agentic workflows trustworthy and verifiable with a custom DSL

Making agentic workflows trustworthy and verifiable with a custom DSL

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome