Launch Week

A week of releases for collaboratively tracing, evaluating, and iterating on agents. One new feature every workday, for five days straight.

Day 01

Thursday, Nov 21
Prompt Playground
Scaling agents across many prompts is hard. We made it easier: version, test, and validate changes against real user conversations.
Read the changelog

Day 02

Friday, Nov 22
Role-based access control
A fully rebuilt RBAC gives teams fine-grained control across prompts, datasets, traces, evaluations, projects, and environments.
Read the changelog

Day 03

Monday, Nov 25
Voice agent testing got real
Automated voice-to-voice scenario tests with multi-turn conversations, real timing, and realistic simulation.
Read the changelog

Day 04

Tuesday, Nov 26
Scenario MCP
Stop hand-writing tests. Scenario MCP writes them for you, straight from how your agent should behave.
Read the changelog

Day 05

Wednesday, Nov 27
Better Agents CLI
Add testing, evaluations, prompt versioning, and structure to any framework, and ship production-grade agents with confidence.
Read the changelog

Catch up on everything we shipped.

Every release, in the changelog, or start building with all of it today.

See the changelog
Start free

Platform

• Agentic AI Testing - Run realistic user scenarios against your agent to catch issues before production
• LLM Evaluation - Measure response quality and accuracy so you ship agents that hold up in production
• LLM Observability - Trace every agent step and monitor cost and latency with full production visibility
• AI Governance - Govern every model, key, and tool. Virtual keys with budgets, routing policies, and a full audit trail
• Prompt Management - Version, deploy, and A/B test prompts as code, with full history and GitHub sync
• Voice AI - Test and simulate your voice AI agents at scale, before they talk to customers
• LLM Red-teaming - Simulated attacks that uncover safety and security gaps in AI agents
• Track your Claude Code Usage - Full trace history and token spend for Claude Code, Codex, and every coding agent