ai-docs

agents

55件のページ

Agents you can coach: how Asana builds human-agent teams with Claude
Working at the frontier: How Balyasny Asset Management evaluates and governs Claude Fable 5
Claude in Chrome is generally available
How Cresta turned CX expertise into an agent builder on the Claude Agent SDK
Getting the most out of Opus 5.5
How we made claude.ai faster
Built-in memory for Claude Managed Agents
How to prepare for AI-driven code modernization projects
Prompting Claude Sonnet 5.5
How Anthropic's sales team rebuilt inbound with Claude Managed Agents
Using Claude Code: Spending your effort
Orchestrate teams of Claude Code sessions
Prompting best practices
Code execution tool
Compaction on demand
Compaction at a token threshold
Computer use tool
Message your other Claude Code sessions
Memory tool
Prompting Claude Fable 5
Prompting Claude Opus 5
Tool search tool
Orchestrate subagents at scale with dynamic workflows
A harness for every task: dynamic workflows in Claude Code
Compaction and preserved thinking
Compaction
Effort
How Claude Code works
Programmatic tool calling
How Anthropic runs large-scale code migrations with Claude Code
The evolution of agentic surfaces: building with Claude Managed Agents
Increase web search accuracy and efficiency with dynamic filtering
Measuring AI agent autonomy in practice
Multi-agent coordination patterns: Five approaches and when to use them
New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration
Building multi-agent systems: When and how to use them
Agent Harness Design: 3 Patterns for Harnessing Claude's Intelligence
Building effective agents
Effective context engineering for AI agents
Introducing advanced tool use on the Claude Developer Platform
Building a C compiler with a team of parallel Claudes
How we built Claude Code auto mode: a safer way to skip permissions
The "think" tool: Enabling Claude to stop and think in complex tool use situations
Code execution with MCP: Building more efficient agents
Demystifying evals for AI agents
Effective harnesses for long-running agents
Equipping agents for the real world with Agent Skills
Eval awareness in Claude Opus 4.6's BrowseComp performance
Harness design for long-running application development
How we contain Claude across products
Manage tool context
Scaling Managed Agents: Decoupling the brain from the hands
How we built our multi-agent research system
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
Writing effective tools for agents — with agents

作成 Quartz v5.0.0

GitHub
Discord Community