Demystifying evals for AI agents
Get the developer newsletter Product updates, how-tos, community spotlights, and more. Good evaluations help teams ship AI agents more confidently.
Scaling Managed Agents: Decoupling the brain from the handsAnthropic
Writing effective tools for AI agents—using AI agentsAnthropic
Introducing advanced tool use on the Claude Developer PlatformAnthropic
Introducing Anthropic InterviewerAnthropic
Clio: A system for privacy-preserving insights into real-world AI useAnthropic
Barclays scales Claude to upgrade operations and improve client experienceAnthropic
10 best AI observability tools for monitoring and evaluating agents in 2026Mintlify
Pulumi Neo Now Supports AGENTS.mdPulumi
How to serve trillions of tokens for trillion-parameter coding agentsModal
Do AI Agents Need a Semantic Layer?Motherduck
Building a Remote MCP Server: OAuth, Tool Design & Lessons from 4,000+ AI Queries | MotherDuckMotherduck
AGENTS.md outperforms skills in our agent evalsVercel
You can just ship agentsVercel
skill.md - MintlifyMintlify
Best Documentation Platforms for AI Agents in 2026Mintlify
Voice AI for Government: Speech-to-Text for Government MissionsDeepgram
From ASR to CSR: Why Conversation Changes EverythingDeepgram
Role-Based Access Control for humans and agentsModal
This Month in the DuckDB Ecosystem: January 2026Motherduck
Introducing Embedded DivesMotherduck
