AP
Agent Provider Depot
Opinionated picks for agents
OpenAPI

Agent classes / Multi-agent orchestrator / Event-driven agent jobs with great DX

Event-driven agent jobs with great DX for a multi-agent orchestrator

Updated 2026-10-27 (newest stored date on this page) · score asOf 2026-09-14 (stale)

The class: A lead assigns subtasks to workers and accepts a result only when it matches the assignment.

  • A written assignment per worker
  • A budget for the whole fan-out

Depot Pick: Inngest

When not to use it: Polyglot extreme scale — Temporal; raw HTTP delayed callbacks without a workflow runtime — Upstash QStash; pure Python GPU jobs — Modal.

Runner-up: Trigger.dev.

No single-unit sourced price comparison for this job (no_candidate_has_sourced_price_in_job_unit:queue_event).

Failure modes this class and job share (9)

  • Partial tool success: Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.
  • Inter-agent misalignment: Log the assigned subtask next to the worker's stated result. The lead rejects a result that does not match the assignment.
  • Observability gap: Alert on a drop in trace ingestion and on certificate expiry for the trace host. Do not treat a missing trace as a successful quiet run.
  • Runaway spend: Set a budget and a tool-call cap per task. Alert when spend jumps. Stop the run at the cap instead of summarizing a partial trace as success.
  • Tool loop: Hash the last several tool names and arguments. Stop when the same call repeats and the observation did not change. Cap tool calls per task.
  • Hallucinated tool arguments: Reject a call that fails the current schema or names an unknown id, and do that before the tool runs a side effect.
  • Identity confusion: Bind every tool call to a user or tenant id. Refuse the call if that id changed mid-task. For a public bot, the operator owns the words the bot shows.
  • Instruction drift: Restate the stop condition in the trace. End the run when it is met. Review long traces for steps that do not serve the original task.
  • Weak verification: Success requires an end-state check the agent does not grade for itself: tests, a database diff, or a separate judge that cannot see the gold label.

Free options this class uses (1)

  • Hatchet (dev_tool, oss) — source, asOf 2026-10-25