LoopQuest
← All integrations

Dify

AI framework

A published Dify Marketplace plugin with Create review task, Wait for verdict and Get task status nodes.

In plain English

LoopQuest is a place where a person quickly checks the work an AI or automation has done. Connecting Dify means that whenever Dify 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 Dify so the rest of your process can carry on, with a real person accountable for the call.

When you'd use it

A Dify agent drafts a customer response or a contract clause. Drop in the Wait for verdict node so the flow blocks until a human approves, then branch on the result — a real human-in-the-loop gate, without leaving Dify. Or use Create review task to review in the background without slowing the agent down.

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 Dify proves it's allowed to send you work.
  • An account on Dify itself, with the workflow or agent you want to add a human check to.

How to set it up

  1. 1In Dify, open Plugins → Marketplace, search for LoopQuest, and install it in one click.
  2. 2Open the plugin's settings and paste your project API key.
  3. 3To MONITOR (non-blocking): add the Create review task node, pick a module (swiper, grounding, redact…), map your output into Content, and carry on. The verdict is logged; poll Get task status or set a callback_url if you want it back.
  4. 4To GATE (blocking): add the Wait for verdict node instead. A Dify chatflow can't natively pause on a callback, so this node polls server-side and blocks until a human decides (or the fail-closed timeout fires). Then wire an IF/ELSE on the returned verdict — approve → continue, flag → fallback or escalate.

Recipes: gate or monitor

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

For gating, Dify sits in the native pause & resume group. How it works →

Gate — block until approved

Dify can pause a run and resume it when the verdict arrives, which makes it a clean blocking gate.

⚙️Difyyour flow
Gate taskmode: "gate"
Run pauseswaits
👤Humandecides
Approve, run resumes
Reject, run stops
  1. 1In your Dify flow, send the output to LoopQuest with the mode set to "gate", plus a callback so it can be resumed.
  2. 2Dify pauses at that step (a Wait node or resume URL) instead of carrying on.
  3. 3A reviewer approves or flags it; LoopQuest calls back and the run picks up exactly where it left off.
  4. 4Branch on the verdict, and set a timeout so a missing decision never blocks the flow forever.

Monitor — review without blocking

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

⚙️Difyproceeds 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. 2Dify 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.