Claude Code, Anthropic Inc., San Francisco, California, USA


Introducing Claude Code

Feb 24, 2025

We're launching Claude Code, our agentic coding tool, in a limited research preview. Claude Code lets developers delegate substantial engineering tasks to Claude directly from their terminal.

Claude Code has already become indispensable for our team. In early testing, Claude completed tasks in one pass that would normally take 45+ minutes of manual work.

With Claude Code, our goal is to better understand how developers use Claude to help improve our models for all.

In this demo, Claude Code completes complex coding tasks that would ordinarily take a significant amount of manual work. It explains an unfamiliar Next.js project, adds new functionality, creates tests, fixes build errors, and explains its changes.
 
Last edited:

Claude Code is all you need in 2026

Jan 14, 2026

Claude Code in 2026 is not what it was when it launched. After a year of building frameworks, custom setups, and elaborate systems to make AI coding work, we've come to a point now where... most of that is overkill.

In this video, I'll show you what building with pure vanilla Claude Code actually looks like in 2026. No frameworks. No custom rules. Just Claude Code with Opus 4.5 handling real professional development work.

I'll build a real feature in a real app, walking you through plan mode, the clarifying questions flow, and the native features that now do what frameworks used to do.

If you're just getting into AI-assisted development, or if you've been layering tools onto your workflow — this video will show you the simpler path forward.

briancasel.com
 

Building Claude Code with Boris Cherny

Mar 4, 2026

Boris Cherny is the creator and Head of Claude Code at Anthropic. He previously spent five years at Meta as a Principal Engineer and is the author of the book Programming TypeScript.

In this episode of Pragmatic Engineer, we went through how Claude Code was built and what it means when engineers no longer write most of the code themselves.

We discuss how Claude Code evolved from a side project into a core internal tool at Anthropic and how Boris uses it day-to-day. We go deep into workflow details, including parallel agents, PR structure, deterministic review patterns, and how the system retrieves context from large codebases. We also get into how Claude Cowork was built.

As coding becomes more accessible, the role of engineers shifts rather than shrinks. We examine what that shift means in practice, which skills become more important, and why the lines between product, engineering, and design are blurring.

In this episode, we cover:

(00:00) Intro
(11:15) Lessons from Meta
(19:46) Joining Anthropic
(23:08) The origins of Claude Code
(32:55) Boris's Claude Code workflow
(36:27) Parallel agents
(40:25) Code reviews
(47:18) Claude Code's architecture
(52:38) Permissions and sandboxing
(55:05) Engineering culture at Anthropic
(1:05:15) Claude Cowork
(1:12:48) Observability and privacy
(1:14:45) Agent swarms
(1:21:16) LLMs and the printing press analogy
(1:30:16) Standout engineer archetypes
(1:32:12) What skills still matter for engineers
(1:35:24) Book recommendations
 
Back
Top