> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tartini.com.br/llms.txt
> Use this file to discover all available pages before exploring further.

# Tracking Your Team with Scout and Sotto

> Turn on Scout, read the Overview, review evaluations, and track performance and satisfaction, with Sotto alongside your agents.

export const Artigo = ({titulo, href, children}) => <a className="lista-artigos-item" href={href}>
    <span className="lista-artigos-texto">
      <span className="lista-artigos-nome">{titulo}</span>
      {children ? <span className="lista-artigos-desc">{children}</span> : null}
    </span>
    <svg className="lista-artigos-seta" viewBox="0 0 24 24" width="18" height="18" aria-hidden="true">
      <path d="M9 6l6 6-6 6" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round" />
    </svg>
  </a>;

export const Lista = ({titulo, children}) => <div className="lista-artigos">
    {titulo ? <p className="lista-artigos-titulo">{titulo}</p> : null}
    <div className="lista-artigos-itens">{children}</div>
  </div>;

Scout reads every closed conversation, asks the Cérebro for the company's standard, and returns a score, a summary, and recommendations, both to the manager and back to the Cérebro. This guide turns on Scout, teaches you how to review evaluations, and shows you where to track your team.

We've split it into steps:

1. [Turn on Scout](#step-1-turn-on-scout)
2. [Read the Overview](#step-2-read-the-overview)
3. [Review evaluations](#step-3-review-evaluations)
4. [Track performance](#step-4-track-performance)
5. [Measure satisfaction](#step-5-measure-satisfaction)
6. [Give the team Sotto](#step-6-give-the-team-sotto)

<Note>
  Scout is available on every plan. Process adherence requires Scale. Each analysis consumes AI credits.

  The Tartini interface is in Portuguese. Screen and button names appear here exactly as on screen, with the translation in parentheses.
</Note>

***

## Step 1: Turn on Scout

Scout evaluates a conversation when it closes. The toggle is in Conversation Rules: **Ativar Scout ao finalizar conversa** (Enable Scout when conversation ends). The rubrics it uses come from the Cérebro: tone of voice, guidelines, compliance, and, on Scale, processes. A criterion with no rubric registered shows up as not evaluated.

* [Set the conversation rules](/en/atendimento/regras-de-conversa).
* [Scout explained](/en/agentes/scout/o-scout-explicado).

***

## Step 2: Read the Overview

The Overview is a snapshot of the selected scope: a first-person verdict, health signals, the **o que precisa de você** (what needs you) queue, and the average score per criterion. The scope bar picks the level (Company, Area, Unit, or agent) and the time period. With few conversations evaluated, Scout says it doesn't have enough data yet and suggests widening the period.

* [Scout explained](/en/agentes/scout/o-scout-explicado): the scope bar and the Overview.

***

## Step 3: Review evaluations

Open the evaluations and say whether you agree. Correcting a score and explaining why teaches Scout to evaluate the way you do.

* [Read Scout's evaluations](/en/agentes/scout/avaliacoes).
* [Agree with Scout or correct the score](/en/agentes/scout/concorde-ou-corrija).

***

## Step 4: Track performance

The Performance screen shows the score by agent, Unit, and Area, with the period's analysis and feedback for each person. Agents can see their own performance on the same screen.

* [Track your team's performance](/en/agentes/scout/desempenho-da-equipe).
* [See process adherence](/en/agentes/scout/processos-e-aderencia) (Scale).

***

## Step 5: Measure satisfaction

With the satisfaction survey turned on, the Satisfaction screen shows customer scores from 1 to 5, by Unit and by type of support: AI only, team only, or AI that started and handed off to the team.

* [Configure the satisfaction survey](/en/atendimento/pesquisa-de-satisfacao).
* [Track customer satisfaction](/en/agentes/scout/satisfacao).

***

## Step 6: Give the team Sotto

Sotto is Scout's feedback applied in real time: it answers the agent based on the Cérebro and, in active mode, suggests the reply and flags when something contradicts the knowledge base. Grant access person by person.

* [Use Sotto](/en/agentes/sotto/use-o-sotto).
* [Invite and manage users](/en/equipe/usuarios): Sotto access per person.

***

## Next steps

<Lista>
  <Artigo titulo="Turning on Tino" href="/en/primeiros-passos/guias/ligando-o-tino">The AI on the front line, with Scout evaluating.</Artigo>
  <Artigo titulo="Operation metrics" href="/en/metricas/operacao">Your team's numbers by period.</Artigo>
</Lista>


## Related topics

- [Getting Started with Tartini](/en/primeiros-passos/guias/comecando-com-o-tartini.md)
- [Sotto explained](/en/agentes/sotto/o-sotto-explicado.md)
- [The Cérebro Explained](/en/cerebro/o-cerebro-explicado.md)