> ## Documentation Index
> Fetch the complete documentation index at: https://levers9.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Scenarios

> Thousands of moments grouped into a few dozen situations, ranked by where the agent is weakest

> [!NOTE]
>
> In the game this is mission 2, **Find the hot spots**: where the agent is weakest, so review time goes there.

A call centre has thousands of calls and no one can review them one by one. **Scenarios** finds the situations
that repeat and ranks them.

## How they are found

Every agent turn is a *situation*: what the customer just said (weighted double) plus the agent's previous
reply. Situations are turned into vectors (by meaning when the embedding credentials are configured, by
character n-grams otherwise; the map says which with `grouped_by`), clustered, and each cluster becomes a
scenario with a stable id, a size, a mean score, a violation count and a **priority** that grows with size,
weakness and violations. **Regroup** reclusters after new calls arrive; it runs as a background job with a
progress bar. Every job running on a world (a regroup, a rescore, a seed, a training run) shows at the top of
that world's page whoever started it, including one started from the API or another tab. Grouping costs more than linearly in situations, so past six thousand of them the board is built
from a fixed sample of the calls and the header says `grouped from N of M calls`; every call is still scored
and still in Calls and the review queue. On real Arabic calls meaning-based grouping mattered: the same 5,867
situations made 1,305 scenarios by spelling and 349 by meaning, and the 398 spelling-scenarios that were all
the scripted opening became one.

## The board and the map

The board lists scenarios by priority with their size, mean score and an auto-generated name you can rename.
A name is the customer's line, or, when that is a word or two (half of real customer turns are), the line and
the reply it drew: `صحيح → تمام، عندي ثلاث أسئلة سريعة…`. With English on, names are translated by the
configured judge and cached; with no model there is no English name and the Arabic shows, rather than a
placeholder that made every row read "opening".
The map draws them: halos sized by how many situations they hold, points inside for the situations
themselves, the top scenarios labelled.

* pan and zoom with the mouse; wheel zooms about the cursor;
* **2D / 3D**: the third axis is another component of the same embedding; drag to rotate, it drifts when idle;
* hover a point for the customer's words and the score; click for **Review this moment**;
* **Select** (or Shift-drag) draws a rectangle: the panel shows the count, mean score and violations of what is
  inside, with **Review these** (a Compare queue, weakest first) and **Name as a scenario** (a manual scenario
  that survives regrouping).

## Reviewing a scenario

Open a scenario for its situations, weakest first, and **Review this scenario**. Compare opens with the
scenario preselected and walks through its worst real replies one by one, so a reviewer's ten minutes go to the
situations that matter most.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.