AI Agents

Replayarealrunbeforeyouchangetheprompt

Replay any past step against a new prompt or model with write tools stripped, then diff what changed.

Pick a step from a real execution, save it as a fixture, and replay it whenever the prompt, model or tools change. Replays run in test mode with every write tool removed and denied, so nothing reaches GitHub or Jira. Assertions on the output turn a suite of fixtures into a CI gate — from the app, a GitHub Action, or the MCP server.

Early access — turned on per workspace. Ask us to enable it for yours.

Fixtures saved from real executions, not hand-written transcripts
Read-only replay: write tools stripped and deny-listed
Output diff and claim checks between the original and the replay
GitHub Action and MCP server run suites outside the app

All features Get started

Related in AI Agents

Base agent types

Senior Developer, Code Reviewer, Tech Writer, Product Manager, and fully Custom agents.

Agent memory

Persistent memory tools let agents recall conventions, recurring issues, and decisions.

Multi-agent sessions

A coordinator delegates work across specialist agents and synthesizes the result.

MCP servers

Connect stdio or SSE MCP servers and their tools appear namespaced in every agent run.

Agent identity & ledger

Each agent gets a stable identity, a signed short-lived token, and a ledger of everything it touched.