Niches · Human approval & handoff

Keep a record of who approved what, and what they saw

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
6companies, fit with a limit
7companies carry the tag
8share of the category's work
3first-hand accounts

What counts as done

Each decision is logged with requester, approver, the payload hash shown, decision, reason, timestamps and any timeout, is append-only and exportable, and links to the execution that followed.

How agents ask for it: who approved this payment, export last month's approvals, show what the reviewer was shown

Does the job, with a limit 6

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
gotoHuman D
gotoHuman UG (haftungsbeschränkt)
Each result carries reviewer email, decision, timestamp and the reviewed data, and review history shows deliveries. Audit logs and custom retention are Enterprise only (from $950 a month); no payload hash or append-only export is documented. source
Orkes Conductor Human tasks C
Orkes, Inc.
Audit logs record HUMAN_TASK writes with user, timestamp and a state snapshot, but they are off by default (enable through support), admin-only, and the page gives no retention or payload hash. source
Permit MCP Gateway C
Permit Inc.
History lists deciding admin, time taken and outcome; audit logs record each permit.check with agent, human and decision. Retention is periodic deletion per plan, approval reasons and argument hashes are not described in the audit entries, and export is not documented. source
Pushary C
RalphNex OÜ
The README mentions a production ledger and Teams recording whoever answered next to whose agent asked, but no log schema, export, retention or payload record is documented. source
Temporal BB
Temporal Technologies Inc.
Each decision Signal is recorded in the append-only workflow event history, linked to the run. The approver, reason and payload fields are whatever the builder sends, and retention follows the namespace setting. source
withHuman BB
Metoro Inc
approval.created, claimed and decided events record actor, timestamp, status and note, with the pipeline path and request history. The page shows no export, retention period or payload hash. source

Doesn't do this job 5

Listings in the category that do something else, with the reason.

ListingWhy
Big Arrow BB
Franz Enzenhofer (individual, Vienna)
No decision log of any kind; answers go to the waiting process as JSON and are not stored. source
Hatchet B
Hatchet Technologies, Inc.
Audit logs (Business plans and above, 6-year retention, export by support request) record token, member and run-trigger actions, not event pushes or decisions. source
Inngest BB
Inngest Inc
Decisions appear only in run traces (24 hours on Free, up to 90 days); audit trails are Enterprise and the approver record is whatever the builder puts in the event. source
Restate BB
Restate GmbH
No decision log with approver or reason; only the invocation journal, kept per service retention (1 day of history on Free per the listing). source
Trigger.dev B
API Hero Ltd
Tokens record tags, createdAt and output, but not who completed them, which the map names as this listing's blocker. source

What stops agents finishing

  • audit logs only on high tiers ($950 a month, Business, Enterprise)
  • no record of who completed a token (Trigger.dev)
  • control-plane logs omit data-plane events (Temporal Cloud)

Around it

Before: human-in-the-loop.approve-action. After: agent-observability.trace-calls.

Where this comes from

Weight 8 of 100 in Human approval & handoff: 3 of 26 accounts, all from the n8n approvals thread; buyer check 4

The same as data: /api/v1/use-cases/human-in-the-loop.audit-decisions.json, or the MCP tool get_use_case with id human-in-the-loop.audit-decisions. Other jobs in this category: /api/v1/niches?category=human-in-the-loop.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.