AI Agents

Workflows remember context across runs

Agents automatically read and write to a scoped memory layer. Use it to store architecture decisions, style guides, incident post-mortems, and anything else that should persist between executions.

• memory_write, memory_read, and memory_search auto-injected into every run
• Scoped per workflow so knowledge stays isolated
• Surfaces the right context before the agent acts

1. Base agent typesSenior Developer, Code Reviewer, Tech Writer, Product Manager, and fully Custom agents.
2. Multi-agent sessionsA coordinator delegates work across specialist agents and synthesizes the result.
3. MCP serversConnect remote MCP servers over streamable HTTP or SSE and their tools appear namespaced in every agent run.
4. Agent identity & ledgerOpt-inEach agent gets a stable identity, a signed short-lived token, and a ledger of everything it touched.
5. Eval harnessOpt-inReplay any past step against a new prompt or model with write tools stripped, then diff what changed.