Use cases
Six concrete scenarios where peer-to-peer agent orchestration makes the difference. Each is something we've seen work, or that the mesh's design specifically enables.
Codebase exploration before a refactor
Solo developerBefore touching a large codebase, spawn three agents: one to map the current structure, one to find the highest-risk areas, one to draft a refactor plan. The three agents can message each other — the planner asks the explorer for clarification, the risk-finder flags concerns. You get a synthesis in minutes, not hours.
spawn_fleetsend_messagecollect_results Multi-perspective design review
Product teamA new feature spec is ready. Spawn a frontend-developer, a security-auditor, and a code-reviewer agent. Each reviews the spec from their angle. They debate via P2P questions, converge on concerns, and surface a unified review document. No more scheduling three meetings.
spawn_fleetsend_messagelist_agentsattach_agent Test failure triage
Backend teamA CI run failed across 47 tests. Spawn an agent to categorize the failures (regression, flaky, infrastructure, real bug), then attach a debugging agent to the real-bug subset. Each debugging agent works in parallel and posts its findings to the orchestrator.
spawn_fleetroute_workattach_agentsend_message Long-running research with checkpointing
ResearcherSpawn a deep-research fleet that runs for hours, not minutes. Per-fleet timeouts mean individual agents can think deeply without breaking the wall. Event log gives you a complete audit trail of who did what. Pick up where you left off after a restart.
spawn_fleetset_fleet_timeoutfleet_statuslist_fleets Migration with parallel verification
Platform teamMigrating from one library to another. Spawn an agent to do the migration, another to write tests, another to verify no regressions. The migrator and the verifier can message each other: 'I changed this file, does the test still pass?'
spawn_fleetsend_messagecollect_resultslist_fleets Self-healing monitoring agent
SREA long-running fleet stays in the background. If an alert fires, the alert handler broadcasts to the fleet. Peers with relevant skills (database, network, auth) respond. If a peer can fix it, they reply with the fix. If not, they escalate to a human via request_help.
send_messagealertrequest_helpfleet_status Working examples
Drop these into spawn_fleet as-is or save them as templates. Each one is a real fleet config that ships in the agent-mesh repo.
Got a scenario of your own?
Open an issue with the use-case label. If it's a good fit, we'll add it here and write a worked example.