Skip to content
ClaudeClaude

How we Claude Code

See how Anthropic engineers actually use Claude Code day to day. You'll configure a real repo the way we do internally: project context files, custom commands, hooks, and subagents. Then run the same task stock versus tuned and see the difference for yourself.

May 23, 202631mWatch on YouTube ↗

Episode Details

EPISODE INFO

Released
May 23, 2026
Duration
31m
Channel
Claude
Watch on YouTube
▶ Open ↗

EPISODE DESCRIPTION

See how Anthropic engineers actually use Claude Code day to day. You'll configure a real repo the way we do internally: project context files, custom commands, hooks, and subagents. Then run the same task stock versus tuned and see the difference for yourself.

EPISODE SUMMARY

In this episode of Claude, How we Claude Code explores anthropic’s Claude Code workflow: interactive specs, HTML plans, agent verification The speaker argues that as models and agents run longer, teams must front-load clarification by having Claude “interview” the user for requirements rather than relying on vague prompts like “make it better.”

RELATED EPISODES

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

How AirOps chases friction to build AI products with Claude

How AirOps chases friction to build AI products with Claude

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