---
title: VETTING
description: Have an independent reviewer check each reply against your rules, and decide what learners see when none passes.
updated: 2026-10-29
---

> All VIABLE docs, for people and their agents: https://developers.viablelab.org/llms.txt

# VETTING

A VETTING step has an independent reviewer check each reply against your rules. Use it when replies must follow rules you can state.

VETTING (Verification and Evaluation Tool for Targeting Invalid Narrative Generation) comes from classroom research ([a middle school study](https://doi.org/10.1016/j.caeai.2026.100646)). Use it for a tutor that never gives the answer away, or an assistant that says only what its sources say.

::: figure stage-checks

## How it works

The **reply model** writes a reply. The **reviewer model** checks it in a separate call and gives a verdict and a reason. A failed reply goes back with that reason, until one passes or the **Attempts** run out.

The reviewer's rules live in the step, apart from the reply model's instructions, so a learner can't talk the reviewer out of them. Each reply and each review is a model call. A review is a judgment, not a guarantee.

## Set it up

::: steps
1. **Choose what it checks against.** Under **Checks against**, pick **A guideline** or **A question and its answer key**. The **Answer key** is seen only by the reviewer.
2. **Set the reply model.** Choose a **Reply model** and, if you like, **Reply instructions**. Safety rules are always added.
3. **Choose the first answer.** Under **Answer to review**, pick **The reply model writes it** or **An earlier step's answer**.
4. **Set the reviewer.** Choose a **Reviewer model**. Left empty, it uses `gpt-6-luna`.
5. **Set the limits.** Choose **Attempts** (1–10, default 3) and **End every reply with a question** (on by default). Connect each outcome to a step.
:::

A guideline can add a **Reference for the reviewer**, such as `{{search.context}}`, to check facts against. To try the **VETTING tutor** template, open **Try it → Reference data → JSON** and enter:

```json
{"question": "Solve 3x = 12", "answer_key": "x = 4"}
```

## Outcomes

- **Passed**: the reviewer approved the reply.
- **Unverified**: no reply passed, or a review couldn't run. Later steps get the last reply, not approved.
- **Needs attention**: the reply model found the conversation unsafe, such as self-harm. It wrote a caring reply instead, which isn't reviewed.

## What learners see

Learners see only what the Reply step on each path says. They never see drafts, the reviewer's reasons or the answer key.

> [!WARNING]
> Decide what the **Unverified** path says. The VETTING templates give a fixed message instead of the unapproved reply.

**Insights** lists replies that didn't pass.

## When a teacher sets How the AI helps

In a course activity, a teacher uses **How the AI helps** to say how far the AI may go. Say a Grade 6 teacher writes "hints only". The reply model gets it as instructions, headed "From the teacher of this activity". The reviewer checks each reply against it too.

The agent profile's **What it reads** decides which steps get it. With **Only as template variables**, nothing is added; use `{{context.workspace.teaching}}` yourself.

::: cards
- [How the AI helps](/docs/teach/ai-helps): what a teacher tells the AI in an activity.
- [Testing and run history](/docs/build/testing): read each VETTING round in a run's trace.
- [Knowledge bases](/docs/build/knowledge): give the reviewer sources to check facts against.
:::