Introducing Sonnet 4.6
…agents in a workflow, and problems where getting it just right is paramount. For Claude in Excel users, our add-in now supports MCP connectors, letting Claude work with the other tools…
Search
Project Vend: Phase two
…We’ve been talking a lot on our Engineering Blog about how to set up AI agents for success, and much of it involves giving them the correct tools . Could we apply…
Finding bugs with Claude and property-based testing
…To read all the bug reports our agent found, see https://mmaaz-git.github.io/agentic-pbt-site/ . Maintainer validation Evaluating the effectiveness of any tool which discovers bugs in code is…
Experimenting with AI to defend critical infrastructure
…by pre-defining some code-based “tools” that allow the model to more easily take actions on computer networks. The researchers then tasked this agent with emulating attacks against a cyber-physical…
Long-running Claude for scientific computing
Science Long-running Claude for scientific computing Mar 23, 2026 In this post, Siddharth Mishra-Sharma , a researcher on the Discovery team, explains how to apply multi-day agentic coding workflows—test…
Quantifying infrastructure noise in agentic coding evals
…An agent that writes lean, efficient code very fast will do well under tight constraints. An agent that brute-forces solutions with heavyweight tools will do well under generous ones. Both are…
Claude does cyber competitions
…Claude can make good use of autonomy and tools The HackTheBox competition also demonstrated the agentic capabilities of Claude. Once our researcher started the script late, he went back to moving into…
Project Vend: Can Claude run a small shop? (And why does that matter?)
…improved “scaffolding” (additional tools and training like we mentioned above) is a straightforward path by which Claudius-like agents could be more successful. General improvements to model intelligence and long-context performance…
Cyber toolkits for LLMs
Frontier Red Team LLMs with cyber toolkits can conduct multistage cyber operations on business-sized computer networks Jun 13, 2025 Anthropic (with Carnegie Mellon University’s CyLab ) Large Language Models (LLMs) that…
Introducing Claude for Small Business
…connect the tools you already use, and pick the job. Claude does the work; you approve before anything sends, posts, or pays. It ships with 15 ready-to-run agentic workflows across…