November 21 to 27
Launch Week
A week of releases for collaboratively tracing, evaluating, and iterating on agents. One new feature every workday, for five days straight.
Prompt Playground
Scaling agents across many prompts is hard. We made it easier: version, test, and validate changes against real user conversations.
Read the changelogRole-based access control
A fully rebuilt RBAC gives teams fine-grained control across prompts, datasets, traces, evaluations, projects, and environments.
Read the changelogVoice agent testing got real
Automated voice-to-voice scenario tests with multi-turn conversations, real timing, and realistic simulation.
Read the changelogScenario MCP
Stop hand-writing tests. Scenario MCP writes them for you, straight from how your agent should behave.
Read the changelogBetter Agents CLI
Add testing, evaluations, prompt versioning, and structure to any framework, and ship production-grade agents with confidence.
Read the changelogCatch up on everything we shipped.
Every release, in the changelog, or start building with all of it today.