Anthropic Engineering
Official Anthropic engineering posts and technical updates.
Read through RSSHubAppears in:IA
Latest from Anthropic Engineering
- The components of agent memoryhace 3 d
- Redesigning source control at Anthropichace 27 d
- How we contain Claude across products2026-05-24
- An update on recent Claude Code quality reports2026-04-22
- Scaling Managed Agents: Decoupling the brain from the hands2026-04-07
- How we built Claude Code auto mode: a safer way to skip permissions2026-03-24
- Harness design for long-running application development2026-03-23
- Eval awareness in Claude Opus 4.6’s BrowseComp performance2026-03-05
- Building a C compiler with a team of parallel Claudes2026-02-04
- Quantifying infrastructure noise in agentic coding evals2026-02-04
- Designing AI-resistant technical evaluations2026-01-20
- Demystifying evals for AI agents2026-01-08
- Effective harnesses for long-running agents2025-11-25
- Introducing advanced tool use on the Claude Developer Platform2025-11-23
- Code execution with MCP: Building more efficient agents2025-11-03
- Beyond permission prompts: making Claude Code more secure and autonomous2025-10-19
- Equipping agents for the real world with Agent Skills2025-10-15
- Effective context engineering for AI agents2025-09-28
- A postmortem of three recent issues2025-09-16
- Writing effective tools for agents — with agents2025-09-10