Search Anthropic

The components of agent memory
For Claude to learn from experience, it has to decide what’s worth remembering before it knows what’s next. Here’s how “dreaming” helps it organize memory and correct mistakes.
An update on recent Claude Code quality reports
We traced recent reports of Claude Code quality issues to three separate changes. Here's what happened and what we're changing.
Scaling Managed Agents: Decoupling the brain from the hands
Harnesses encode assumptions that go stale as models improve. Managed Agents—our hosted service for long-horizon agent work—is built around interfaces that stay stable as harnesses change.
Harness design for long-running application development
Harness design is key to performance at the frontier of agentic coding. Here's how we pushed Claude further in frontend design and long-running autonomous software engineering.
Long-running Claude for scientific computing
A practical guide to running Claude Code for multi-day scientific tasks—test oracles, persistent memory, and orchestration patterns.
Building a C compiler with a team of parallel Claudes
Nicholas Carlini, a researcher on our Safeguards team, explains how he tasked 16 agents with writing a Rust-based C compiler, from scratch, capable of compiling the Linux kernel.
Introducing Claude Opus 4.6
Introducing a smarter, more capable Opus for coding, agents, vision, and complex professional work.
Effective harnesses for long-running agents
We developed a two-fold solution to enable the Claude Agent SDK to work effectively across many context windows: an initializer agent that sets up the environment on the first run, and a coding agent that is tasked with making incremental progress in every session while leaving clear artifacts for the next session.
Introducing advanced tool use on the Claude Developer Platform
We’ve added three new beta features that let Claude discover, learn, and execute tools dynamically. Here’s how they work.
Code execution with MCP: Building more efficient agents
Learn how code execution with the Model Context Protocol enables agents to handle more tools while using fewer tokens, reducing context overhead by up to 98.7%.
Introducing Agent Skills
Build custom Skills to teach Claude specialized tasks. Create once, use everywhere—from spreadsheets to coding. Available across Claude.ai, API, and Code.
Equipping agents for the real world with Agent Skills
Claude is powerful, but real work requires procedural knowledge and organizational context. Introducing Agent Skills, a new way to build specialized agents using files and folders.
Effective context engineering for AI agents
We explore the emerging art of context engineering and offer a refined mental model for building steerable, effective agents.
Writing effective tools for agents — with agents
In this post, we describe our most effective techniques for improving performance in a variety of agentic AI systems.
How we built our multi-agent research system
On the the engineering challenges and lessons learned from building Claude's Research system
Claude Code: Best practices for agentic coding
A blog post covering tips and tricks that have proven effective for using Claude Code across various codebases, languages, and environments.
The "think" tool: Enabling Claude to stop and think in complex tool use situations
A blog post for developers, describing a new method for complex tool-use situations
Introducing Contextual Retrieval
Contextual retrieval improves how AI systems access and use information, reducing retrieval failures in large knowledge bases.
Collaborate with Claude on Projects
Claude Pro and Team users can now organize chats into Projects, bringing internal knowledge and chat activity together in one place.
Many-shot jailbreaking
A long-context jailbreak that overrides safety training with hundreds of faux dialogues, and the mitigations that reduce its effectiveness.