Research
Evaluating Claude with BioMysteryBench \ Anthropic
BioMysteryBench tests Claude on 99 real bioinformatics problems. Opus 4.6 solved 77% of human-solvable questions and some that experts could not.
ResearchFinding bugs with Claude and property-based testing \ Anthropicanthropic.com
ResearchProject Fetch: Can Claude train a robot dog? \ Anthropicanthropic.com
ResearchHow Canada uses Claude \ Anthropicanthropic.com
ResearchHow Australia uses Claude \ Anthropicanthropic.com
ResearchEvaluating feature steering: A case study in mitigating social biases \ Anthropicanthropic.com
ResearchEvaluating and Mitigating Discrimination in Language Model Decisionsanthropic.com
Blogs10 best AI observability tools for monitoring and evaluating agents in 2026Mintlify
BlogsFrom Automation Veteran to AI Pioneer: How Evan Nison transformed his agency with Zapier MCPZapier
BlogsAnthropic integration with Modal brings scalable compute to Claude ScienceModal
BlogsLies, damn lies, and benchmarksDeepgram
BlogsAnthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI AttackSocket
BlogsCollaborating with Anthropic on Claude Sonnet 4.5 to power intelligent coding agentsVercel
BlogsClaude Connectors: How to Connect Claude to Other AppsZapier
BlogsThe Claude Skills I Actually Use for DevOpsPulumi
BlogsClaude Code + Dives = Any data UIMotherduck
BlogsQuestions to Ask Your Hardened Image ProviderDocker
Blogs7 best MCP servers for Claude Code in 2026Mintlify
Resourcesllms.txt - MintlifyMintlify
BlogsThe 9 best AI coding tools in 2026Zapier
BlogsStop Tuning Prompts. Build a Harness.Pulumi
