Research
Trustworthy agents in practice
Five principles for building AI agents that balance autonomy with safety, with defenses spanning the model, harness, tools, and environment.
ResearchSleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingAnthropic
ResearchSHADE-Arena: Evaluating Sabotage and Monitoring in LLM AgentsAnthropic
ResearchProject Swap: What happens when agents trade for us?Anthropic
ResearchVibe physics: The AI grad studentAnthropic
ResearchTowards measuring the representation of subjective global opinions in language modelsAnthropic
Blogs10 best AI observability tools for monitoring and evaluating agents in 2026Mintlify
BlogsHow Redis is Used in Practice | RedisRedis
BlogsPulumi Neo Now Supports AGENTS.mdPulumi
BlogsHow to serve trillions of tokens for trillion-parameter coding agentsModal
EventsDo AI Agents Need a Semantic Layer?Motherduck
BlogsBuilding a Remote MCP Server: OAuth, Tool Design & Lessons from 4,000+ AI Queries | MotherDuckMotherduck
BlogsHow to Attract New Patients to Your Dental PracticeHeygen
BlogsAGENTS.md outperforms skills in our agent evalsVercel
BlogsYou can just ship agentsVercel
Resourcesskill.md - MintlifyMintlify
BlogsBest Documentation Platforms for AI Agents in 2026Mintlify
Products & ServicesVoice AI for Government: Speech-to-Text for Government MissionsDeepgram
BlogsFrom ASR to CSR: Why Conversation Changes EverythingDeepgram
BlogsThe Coana Approach to Reachability AnalysisSocket
