LoopQuest
← All integrations

Make

Workflow automation

A custom app with three modules — send output for review, check status, and trigger on every verdict.

In plain English

LoopQuest is a place where a person quickly checks the work an AI or automation has done. Connecting Make means that whenever Make produces something that should be looked at by a human, it sends that item to LoopQuest. Someone on your team reviews it in a few seconds, and their decision is sent straight back to Make so the rest of your process can carry on, with a real person accountable for the call.

When you'd use it

A Make scenario drafts a reply, scores a lead, or proposes a refund with AI. Send the output to LoopQuest as a gate — the consequential step waits until a person approves — then a second scenario resumes the moment the verdict lands. Or run it as a monitor: the scenario carries on while reviews happen in the background for quality and audit.

The modules you get

Drag these into a Make scenario — each does one job so you can mix them to fit your flow.

Create a Review Task

Sends your AI output to a human. Pick the game (Swiper, Sorter, Redact, Grounding…) and the mode: gate blocks a downstream action until someone approves; monitor reviews in the background without pausing. Set a timeout and an on-timeout fallback (escalate, approve, or reject) so nothing hangs forever.

Watch Verdicts

An instant trigger that fires the moment any review resolves. Gives you the verdict, choice, reason, and flags (escalated, timed_out) plus the external_id you set — so you can branch with a Router: approve → do the action, flag → route to a person or fallback. This is how you build a blocking gate in a linear tool.

Get Task Status

Look up a single review on demand (verdict, reviewer, timing). Handy for a polling loop or a manual check when you'd rather pull than wait on the trigger.

What you'll need

  • A free LoopQuest account. Sign up if you don't have one.
  • A project and its API key — find it under Workspaces → your project → API keys. The key is how Make proves it's allowed to send you work.
  • An account on Make itself, with the workflow or agent you want to add a human check to.

How to set it up

  1. 1Install the LoopQuest custom app from Make, then create a connection with your project API key.
  2. 2In your automation scenario, add Create a Review Task — choose a game, set mode to gate (to block) or monitor (to observe), and map your content. For a gate, set a timeout and on-timeout fallback.
  3. 3In a second scenario, add the Watch Verdicts trigger, connect the same key, and turn the scenario ON — Make auto-subscribes it to your workspace's verdicts.
  4. 4Add a Router after Watch Verdicts: on approve, run the real action; on flag or timeout, route to a fallback. The external_id ties the verdict back to the item you sent.

Recipes: gate or monitor

Two ways to put a human in the loop with Make. A gate blocks until someone approves; a monitor reviews in the background without slowing anything down.

For gating, Make sits in the two-step (webhook-triggered) group. How it works →

Gate — block until approved

A single Make run can't pause for an external callback, so the gate is split across two flows joined by the verdict webhook.

⚙️Flow Asends gate
LoopQuestholds it
⤿Verdict webhookfires Flow B
Flow Bacts
Approve, it proceeds
Reject, it stops
  1. 1Flow A: send the output to LoopQuest as a gate, then let the flow finish.
  2. 2Add a webhook trigger that listens for the verdict.
  3. 3Flow B: triggered by that webhook, it performs the action only when the verdict is an approval.
  4. 4Pass an external_id on the task so Flow B knows which item it belongs to.

Monitor — review without blocking

Monitor mode never holds Make up. The flow proceeds immediately and LoopQuest reviews a copy for quality.

⚙️Makeproceeds now
Doneno wait
👤Copy reviewed by a human
📈Quality metrics & alerts
  1. 1Send the output with a mode of "monitor" and don't wait on the result.
  2. 2Make carries straight on, nothing is blocked.
  3. 3Verdicts are logged and scored over time. Sample a fraction for QA, or review every item.

What happens after a review

The moment a reviewer decides, LoopQuest sends the result back to the web address you gave it (your callback_url). The message says what was decided, whether it was approved, flagged, which option was picked, or the corrected values, so your automation can act on it automatically.

For developers: each callback is signed with an X-LoopQuest-Signature HMAC header. Verify it before trusting the payload. Full details are in the API reference.

Stuck, or want this set up for you? Email tom@tomphillips.uk and we'll walk you through it.