Langflow
AI framework
A human-review tool component for Langflow agents — the agent waits for a human verdict before acting.
In plain English
LoopQuest is a place where a person quickly checks the work an AI or automation has done. Connecting Langflow means that whenever Langflow 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 Langflow so the rest of your process can carry on, with a real person accountable for the call.
When you'd use it
A Langflow agent is about to do something consequential — send a reply, issue a refund, change a record. Give it the LoopQuest tool: it sends the output to a human, blocks until someone approves or flags it, and returns the verdict so the agent proceeds or stops. A real gate, inside the agent's own reasoning.
The modules you get
Drag these into a Langflow scenario — each does one job so you can mix them to fit your flow.
LoopQuest Human Review (tool)
Exposes a request_human_review tool. Pick the game and mode; in gate mode it creates the review and blocks (polling) until a human decides, then hands the verdict back to the agent. Monitor mode reviews in the background without waiting.
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 Langflow proves it's allowed to send you work.
- An account on Langflow itself, with the workflow or agent you want to add a human check to.
How to set it up
- 1Add the LoopQuest Human Review component to your flow and set your project API key.
- 2Pick a game and set Mode to Gate (block until a human approves) or Monitor (review in the background).
- 3Connect it to your agent as a tool so it can call it before consequential actions.
- 4On a gate, the agent pauses on the tool call until the verdict returns (or the fail-closed timeout escalates), then branches on approve vs flag.
Recipes: gate or monitor
Two ways to put a human in the loop with Langflow. A gate blocks until someone approves; a monitor reviews in the background without slowing anything down.
Gate — block until approved
With Langflow you control the call, so you await the verdict directly before doing anything consequential.
- 1POST the output to /api/v1/tasks with a mode of "gate" and a timeout_seconds.
- 2Poll GET /api/v1/tasks/{id} until the status is no longer "pending", or receive the signed webhook.
- 3Continue on an approve, halt on a reject. If it times out, it resolves fail-closed on its own.
- 4Verify the X-LoopQuest-Signature on any webhook before trusting it.
Monitor — review without blocking
Monitor mode never holds Langflow up. The flow proceeds immediately and LoopQuest reviews a copy for quality.
- 1Send the output with a mode of "monitor" and don't wait on the result.
- 2Langflow carries straight on, nothing is blocked.
- 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.
Pairs well with
The review games that best fit the kind of output Langflow tends to produce.