Engineering at Anthropic: Inside the team building reliable AI systems
Featured
Quantifying infrastructure noise in agentic coding evals
Infrastructure configuration can swing agentic coding benchmarks by several percentage points—sometimes more than the leaderboard gap between top models.
Eval awareness in Claude Opus 4.6’s BrowseComp performance
Mar 06, 2026
Building a C compiler with a team of parallel Claudes
Feb 05, 2026
Designing AI-resistant technical evaluations
Jan 21, 2026
Demystifying evals for AI agents
Jan 09, 2026
Effective harnesses for long-running agents
Nov 26, 2025
Introducing advanced tool use on the Claude Developer Platform
Nov 24, 2025
Code execution with MCP: Building more efficient agents
Nov 04, 2025
Beyond permission prompts: making Claude Code more secure and autonomous
Oct 20, 2025
Effective context engineering for AI agents
Sep 29, 2025
A postmortem of three recent issues
Sep 17, 2025
Writing effective tools for agents — with agents
Sep 11, 2025
Desktop Extensions: One-click MCP server installation for Claude Desktop
Jun 26, 2025
How we built our multi-agent research system
Jun 13, 2025
Claude Code: Best practices for agentic coding
Apr 18, 2025
The "think" tool: Enabling Claude to stop and think in complex tool use situations
Mar 20, 2025
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
Jan 06, 2025
Building effective agents
Dec 19, 2024
Introducing Contextual Retrieval
Sep 19, 2024