Vercel AI SDK
Code / SDKRoadmap
A human-review tool for AI SDK agents and apps.
In plain English
LoopQuest is a place where a person quickly checks the work an AI or automation has done. Connecting Vercel AI SDK means that whenever Vercel AI SDK 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 Vercel AI SDK so the rest of your process can carry on, with a real person accountable for the call.
A one-click Vercel AI SDK connector is on our roadmap. In the meantime the steps below show how to wire it up today using our open API, and it works exactly the same.
When you'd use it
Add a tool to your AI SDK app so the model can hand off a decision to a person, then resume the stream with the verdict.
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 Vercel AI SDK proves it's allowed to send you work.
- An account on Vercel AI SDK itself, with the workflow or agent you want to add a human check to.
How to set it up
- 1Define a tool whose execute() calls the LoopQuest TypeScript SDK or REST API.
Recipes: gate or monitor
Two ways to put a human in the loop with Vercel AI SDK. A gate blocks until someone approves; a monitor reviews in the background without slowing anything down.
Gate — block until approved
With Vercel AI SDK 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 Vercel AI SDK 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.
- 2Vercel AI SDK 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 Vercel AI SDK tends to produce.