> ## 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.

# The Scout Explained

> See how Scout evaluates every closed conversation and where to find each part of your operation's diagnosis.

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 conversation closed by your team or by Tino, asks the Cérebro (the company's brain) what the company's standard is, and returns a summary, a score, and what to adjust. You open a single place and know where the operation needs your attention. And over time, your corrections and Scout's findings teach the Cérebro how your company actually serves customers and how it wants to serve them.

<Note>
  Scout appears in the menu for every role. Each person sees the data for their own scope: the whole Company, an Area, a Unit, or just their own service. Processes and adherence requires the Scale plan. The Tartini interface is in Portuguese. Screen and button names appear here exactly as on screen, with the translation in parentheses.
</Note>

***

## What Scout Evaluates

In every closed conversation, Scout gives a score from 0 to 10 for up to six criteria:

| Criterion               | Who receives the score |
| ----------------------- | ---------------------- |
| Tone of Voice Adherence | Tino and agents        |
| Guideline Adherence     | Tino and agents        |
| Compliance              | Tino and agents        |
| Problem Resolution      | Tino and agents        |
| Process Use             | Only Tino              |
| Process Adherence       | Only agents            |

Each responsible party's final score is the combination of these criteria. A criterion without a standard set up in the Cérebro, such as tone of voice or compliance, appears marked as not evaluated for this company.

***

## When a Conversation Enters the Queue

Scout starts evaluating as soon as someone turns on **Ativar Scout ao finalizar conversa** (Turn on Scout when closing a conversation), in [Set the conversation rules](/en/atendimento/regras-de-conversa). From then on, every closed conversation (by the agent, by Tino, or due to inactivity) enters the queue and receives an automatic analysis.

<Note>
  Each analysis consumes AI credits, and generating the monthly performance analysis does too. Track your usage in [Track your credit balance and statement](/en/creditos/creditos-e-extrato).
</Note>

***

## The Scout Cycle

<Steps>
  <Step title="Scout evaluates">When the conversation closes, Scout asks the Cérebro for the standard (personality, rules, and processes), and the conversation receives a summary, an overall score, and scores per criterion, with recommendations for improvement.</Step>
  <Step title="You validate">A manager opens the analysis and agrees with the score or corrects the criteria they judge to be wrong, with a justification.</Step>
  <Step title="Scout learns and gives back">The correction becomes the effective score for that service in the team's numbers and helps Scout calibrate the next analyses. What it finds goes back to the Cérebro: each finding points to the screen where the correction gets written.</Step>
</Steps>

This cycle is what makes the standard mature. At first, the Cérebro knows only what you registered. With every correction you make and every finding from Scout, it also learns how the company actually serves customers and what you consider good service. Over time, the standard stops being generic and becomes your company's own standard.

***

## Choose What Reaches You

You don't need to review everything. On the **Conversas** (Conversations) screen, filters define what appears in your queue: only the pending ones, only the low scores, only one criterion within a score range. Someone who wants to see only conversations with compliance below five sets **Critério** (Criterion) to **Compliance** and the range to **0–4**, and the list then shows only that. Scout keeps the filters between visits, so the queue opens the way you left it.

On the Panorama, the **o que precisa de você** (what needs your attention) section does the reverse triage: Scout itself chooses the priorities of that scope, by severity, and each one leads to the right screen. See [Read Scout's evaluations](/en/agentes/scout/avaliacoes).

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

***

## What Each Role Sees

| Role                                          | What they see                                   |
| --------------------------------------------- | ----------------------------------------------- |
| Account owner, Administrator, Company Manager | The whole company: all areas, units, and agents |
| Area Manager                                  | Their own area, its units, and agents           |
| Unit Manager                                  | Their own unit and its agents                   |
| Agent                                         | Only their own service                          |

Agreeing, correcting, dismissing an evaluation, and approving the monthly analysis are manager actions: Administrator, Company Manager, Area Manager, or Unit Manager. The Agent reads everything about themselves but doesn't edit.

***

## The Scout Submenu

| Item                          | What it shows                                                                                                                      | Article                                                          |
| ----------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------- |
| **Panorama**                  | The ready-made snapshot of the scope: a verdict, health signals, the priorities that need you, and the average score per criterion | Entry screen, no dedicated article                               |
| **Satisfação** (Satisfaction) | The satisfaction survey score and Scout's read on the customer                                                                     | [Track customer satisfaction](/en/agentes/scout/satisfacao)      |
| **Processos** (Processes)     | Where the processes registered in the Cérebro aren't being entered, aren't progressing, or are worsening the experience            | [See process adherence](/en/agentes/scout/processos-e-aderencia) |
| **Conversas**                 | The list of evaluations and the full analysis of each one                                                                          | [Read Scout's evaluations](/en/agentes/scout/avaliacoes)         |
| **Desempenho** (Performance)  | The team's and Tino's score by level, and each agent's monthly analysis                                                            | [Track team performance](/en/agentes/scout/desempenho-da-equipe) |

On every screen, the scope bar sits at the top: the level (Company, Area, Unit, or agent) on the left and the period on the right. Panorama is the starting point: it summarizes the chosen scope and points, with a button, to which of the other screens you should go to first.

***

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="Do I need to turn something on for Scout to start evaluating?">
    Yes. Turn on **Ativar Scout ao finalizar conversa** in [Set the conversation rules](/en/atendimento/regras-de-conversa). Without it, no conversation enters the queue.
  </Accordion>

  <Accordion title="Does Scout use credits?">
    Yes, at two moments: the automatic analysis of each closed conversation, and generating or regenerating the monthly analysis in Desempenho.
  </Accordion>

  <Accordion title="Why does a criterion show as not evaluated for this company?">
    Because the company hasn't yet registered the corresponding standard in the Cérebro, such as tone of voice, guidelines, or compliance.
  </Accordion>

  <Accordion title="Can the Agent see colleagues' evaluations?">
    No. The Agent sees only their own conversations and their own performance.
  </Accordion>
</AccordionGroup>

***

## Related Articles

<Lista>
  <Artigo titulo="Read Scout's evaluations" href="/en/agentes/scout/avaliacoes">The list of evaluated conversations and the full analysis of each one.</Artigo>
  <Artigo titulo="Agree with Scout or correct the score" href="/en/agentes/scout/concorde-ou-corrija">How to validate the score and what changes afterward.</Artigo>
  <Artigo titulo="Track team performance" href="/en/agentes/scout/desempenho-da-equipe">The score by Area, Unit, and agent, and the monthly analysis.</Artigo>
  <Artigo titulo="Track customer satisfaction" href="/en/agentes/scout/satisfacao">The survey score and where it varies.</Artigo>
  <Artigo titulo="See process adherence" href="/en/agentes/scout/processos-e-aderencia">Where the Cérebro's processes are failing.</Artigo>
  <Artigo titulo="Set the conversation rules" href="/en/atendimento/regras-de-conversa">Turn on Scout when closing conversations.</Artigo>
</Lista>


## Related topics

- [The AI agents explained](/en/agentes/os-agentes-explicados.md)
- [Tracking Your Team with Scout and Sotto](/en/primeiros-passos/guias/acompanhando-a-equipe.md)
- [Processes explained](/en/cerebro/processos-explicados.md)