Anthropic · Blogs
Blogs listings from Anthropic on TechiSeek. 23 public listings.
- Scaling Managed Agents: Decoupling the brain from the hands (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Introducing advanced tool use on the Claude Developer Platform (Anthropic)Claude can now discover, learn, and execute tools dynamically to enable agents that take action in the real world.
- Writing effective tools for AI agents—using AI agents (Anthropic)Get the developer newsletter Product updates, how-tos, community spotlights, and more. The Model Context Protocol (MCP) can empower LLM age…
- An update on recent Claude Code quality reports (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- The "think" tool: Enabling Claude to stop and think (Anthropic)Get the developer newsletter Product updates, how-tos, community spotlights, and more. Extended thinking update Extended thinking capabilit…
- Effective harnesses for long-running agents (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- How we built our multi-agent research system (Anthropic)Get the developer newsletter Product updates, how-tos, community spotlights, and more. Claude now has Research capabilities that allow it t…
- A postmortem of three recent issues (Anthropic)This is a technical report on three bugs that intermittently degraded responses from Claude.
- Donating our open-source alignment tool (Anthropic)Donating our open-source alignment tool In October 2025, we launched Petri, an open-source toolbox of alignment tests that can be applied t…
- Quantifying infrastructure noise in agentic coding evals (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Beyond permission prompts: making Claude Code more secure and autonomous (Anthropic)Learn how Claude Code's new sandboxing feature protects developers with filesystem and network isolation, reducing permission prompts and i…
- How we built Claude Code auto mode: a safer way to skip permissions (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Eval awareness in Claude Opus 4.6’s BrowseComp performance (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Equipping agents for the real world with Agent Skills (Anthropic)Discover how Anthropic builds AI agents with practical capabilities through modular skills, enabling them to handle complex real-world task…
- Claude Desktop Extensions: One-click MCP server installation for Claude Desktop (Anthropic)Get the developer newsletter Product updates, how-tos, community spotlights, and more. File extension update Claude Desktop Extensions now…
- Designing AI resistant technical evaluations (Anthropic)What we learned from three iterations of a performance engineering take-home that Claude keeps beating.
- Code execution with MCP: building more efficient AI agents (Anthropic)Learn how code execution with the Model Context Protocol enables agents to handle more tools while using fewer tokens, reducing context ove…
- Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet (Anthropic)Explore Claude's breakthrough performance on SWE-Bench, demonstrating advanced software engineering capabilities and code generation accura…
- Demystifying evals for AI agents (Anthropic)Get the developer newsletter Product updates, how-tos, community spotlights, and more. Good evaluations help teams ship AI agents more conf…
- Building a C compiler with a team of parallel Claudes (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Reverse engineering Claude's CVE-2026-2796 exploit (Anthropic)Evyatar Ben Asher, Keane Lucas, Nicholas Carlini, Newton Cheng, and Daniel Freeman Today we published an update on our collaboration with M…
- Harness design for long-running application development (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Effective context engineering for AI agents (Anthropic)Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.