Explains the design of a coding agent and shares how he uses it in everyday work, including project instructions, reusable commands and ways to verify a change.
Why read Boris Cherny?
Cherny explains why Claude Code lives in a terminal, how project files provide context and how commands become reusable workflows. Start with his interview with Cat Wu if the machinery around an AI coding assistant feels mysterious.
His own setup thread then shows how those ideas fit together in practice: planning a change, recording recurring mistakes in a shared instruction file and giving the agent a way to test its work. It is useful for choosing a few repeatable habits for your project, with a concrete example from the person who created the tool.
Start with the original
Selected work
Interview ·
Claude Code: Anthropic's Agent in Your Terminal
How does a coding agent fit into a developer's tools? Cherny and Cat Wu explain terminal access, project memory, custom commands and code review in this interview, available with a transcript.
Thread ·
How I use Claude Code: my setup
Which parts of an agent workflow are worth making repeatable? Cherny's setup thread covers planning, shared project instructions, reusable commands and verification through tests or a browser.
Projects & roles
Claude Code
Anthropic's coding agent; Cherny's own biography and the team's recorded sessions identify him as its creator.
Community rating
Sources & further reading
- His own current biography states that he is a software engineer at Anthropic who created Claude Code, and links @bcherny.
- Anthropic's recorded event identifies Cherny as a member of the Claude Code creator team and technical staff.
- The original interview pairs Cherny with Claude Code product manager Cat Wu and includes his direct account of building the tool.