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

# Core Concepts

> Core Exterview concepts including your organization, evaluations, agent sessions, rubrics, scorecards, human review, calibration, and outcome intelligence.

## Purpose

Understand the vocabulary and mental model before you go deeper. Every other page assumes these terms.

## Key objects

<CardGroup cols={2}>
  <Card title="Organization" icon="building">
    Your isolated organization environment. All data, configuration, and scoring are scoped to it.
  </Card>

  <Card title="Role" icon="briefcase">
    A job definition. The structure a candidate is evaluated against.
  </Card>

  <Card title="Candidate" icon="user">
    A person being evaluated for a role.
  </Card>

  <Card title="Evaluation" icon="clipboard-check">
    A scored assessment of a candidate against a role's rubric.
  </Card>

  <Card title="Agent Session" icon="headset">
    A live, real-time interaction (phone, voice, avatar, panel, HR, assessment, or
    post-hire) run by an Exterview agent.
  </Card>

  <Card title="Document Workflow" icon="file-lines">
    A non-live task: role creation, resume match, or offer generation.
  </Card>

  <Card title="Report / Takeaway" icon="file-chart-column">
    The structured output every completed session or workflow produces.
  </Card>

  <Card title="Rubric" icon="list-check">
    The set of dimensions a candidate is scored against.
  </Card>

  <Card title="Configuration Contract" icon="file-signature">
    The signed, versioned, frozen record of all setup decisions that every
    evaluation score traces back to.
  </Card>

  <Card title="Human Review" icon="user-check">
    A person reviews and approves outcomes; nothing adverse is decided
    autonomously.
  </Card>

  <Card title="Outcome Intelligence" icon="chart-line">
    Post-hire signals (D30, D60, D90) fed back to improve evaluation quality.
  </Card>
</CardGroup>

## Live sessions vs. document workflows

Exterview runs two kinds of work:

* **Live session.** A real-time interaction: phone, voice, avatar, panel, HR, assessment, and post-hire companions.
* **Document workflow.** A non-live task: role creation, resume match, and offer generation.

## AI and Core capabilities

Every capability in Exterview is one of two kinds, and the guides label each page accordingly:

* **AI.** Powered by Exterview's models: screening, interviewing, matching, and scoring.
* **Core.** Standard platform work: jobs, candidates, users and roles, billing, integrations, and configuration.

The split matters because AI capabilities produce scored evidence a human then reviews, while Core capabilities are the platform tasks that set them up and run around them. See the [guides](/guides/enterprise-setup) for the labelled how-to pages.

## Modules and agents

Exterview is delivered as **modules**. Each module is a specialized agent that owns one kind of evaluation and produces one report. You don't build agents; they ship pre-built, and you configure the context they evaluate against. See the full [module catalog](/get-started/modules).

Modules combine into **AI Coworkers**: a standing, chartered role for AI on your hiring team, with a defined mandate and human-approved authority, created and revoked the same way you'd manage a human hire. See [AI Coworkers](/get-started/ai-coworkers).

## The critic layer

Exterview is building a separate evaluation step every AI output will pass through before it reaches a reviewer, to catch quality problems automatically. This is not live yet. See [AI Observability](/monitor/ai-observability).

## Setting up: the guided journey

Enterprise setup is a guided, phased configuration led by your Customer Success team. You define org structure and what a strong candidate looks like, design the pipeline, set scoring and gates, connect systems, calibrate per domain, and set governance. Every decision is then signed and frozen into the [Configuration Contract](/guides/setup-freeze) before go-live. See [Enterprise Setup](/guides/enterprise-setup) for the full step-by-step path.

## Configuration tiers

How much you configure depends on your plan. Exterview is designed to land small and expand.

| Tier           | What you configure                                                                  |
| -------------- | ----------------------------------------------------------------------------------- |
| **Starter**    | Standard scoring, no configuration set, for quick proof on one team.                |
| **Growth**     | Light, department-based configuration with dynamic variables.                       |
| **Enterprise** | The full configuration set (Foundation, Operations, Governance), tuned to your org. |

See [Configure](/configure/overview) for the full model.

## Hyper-calibration

For **Enterprise** customers, Exterview builds a per-organization **hyper-calibration layer** during [Foundation](/configure/foundation) setup. Your competencies, role definitions, and scoring context are captured once, taken through a staging journey, and then **frozen**, so every evaluation is scored the same way and stays reproducible. This calibration is unique to your organization and compounds over time as post-hire outcomes feed back in. See [Calibration](/monitor/calibration) and [Outcome Intelligence](/monitor/outcome-intelligence).

## The evaluation lifecycle

Every evaluation moves through five states:

```mermaid theme={null}
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#EEF2FF','primaryBorderColor':'#4B6CFE','primaryTextColor':'#0F172A','lineColor':'#64748B','clusterBkg':'#F8FAFC','clusterBorder':'#E2E8F0'}}}%%
flowchart LR
  A([Configured]) --> B([Deployed]) --> C([Active]) --> D([Completed]) --> E([Monitored])
```

*The five states every evaluation moves through, from frozen configuration to a monitored result. Each state is defined in the table below.*

| State          | What it means                                                                                  |
| -------------- | ---------------------------------------------------------------------------------------------- |
| **Configured** | Agent, channel, rubric, and governance settings are frozen into the configuration.             |
| **Deployed**   | A live session or document workflow starts via invite, integration, workflow, or admin action. |
| **Active**     | The session runs in its channel: phone, voice, avatar, panel, HR, assessment, or post-hire.    |
| **Completed**  | The session closes and outputs are prepared for review.                                        |
| **Monitored**  | Results, analytics, quality signals, audit trails, and outcomes are reviewed.                  |

## Governance, by design

<CardGroup cols={2}>
  <Card title="Human Review" icon="user-check">
    People approve outcomes before they take effect. Roles are set by the nine [system roles](/guides/setup-roles-access).
  </Card>

  <Card title="Auditability" icon="clipboard-list">
    Every action and result is logged in a traceable record.
  </Card>

  <Card title="Data privacy" icon="lock">
    Data is scoped to your organization, with retention and consent controls.
  </Card>

  <Card title="Responsible AI" icon="scale-balanced">
    Content-based scoring, explainability, and no autonomous adverse decisions.
  </Card>
</CardGroup>

## FAQs

<AccordionGroup>
  <Accordion title="What is the difference between a session and a workflow?">
    A session is live and interactive (an interview). A workflow is a document task, such as creating a role, matching a resume, or generating an offer.
  </Accordion>

  <Accordion title="What is the difference between an AI feature and a Core feature?">
    AI features are powered by Exterview's models and produce scored evidence:
    screening, interviewing, matching, and scoring. Core features are standard
    platform tasks such as jobs, users, billing, and configuration. The guides
    label each page.
  </Accordion>

  <Accordion title="Does Exterview analyze a candidate's face or tone?">
    No. Scoring is content-based, meaning what a candidate says, not biometrics,
    facial analysis, or tone.
  </Accordion>

  <Accordion title="Can scores change over time?">
    Configuration is frozen per version in the Configuration Contract. When rules
    change through change control, scoring re-baselines to a new version so
    results stay reproducible.
  </Accordion>

  <Accordion title="Who can see evaluation data?">
    Access is role-based and scoped to your organization. See Trust & Compliance for details.
  </Accordion>
</AccordionGroup>

## Related

<CardGroup cols={2}>
  <Card title="Modules" icon="grid-2" href="/get-started/modules">
    The full catalog of Exterview modules and what each produces.
  </Card>

  <Card title="AI Coworkers" icon="user-group" href="/get-started/ai-coworkers">
    How modules combine into a chartered, governed AI Coworker.
  </Card>

  <Card title="Glossary" icon="book-a" href="/get-started/glossary">
    Every term, defined.
  </Card>

  <Card title="Enterprise Setup" icon="sliders" href="/guides/enterprise-setup">
    The guided journey to a frozen Configuration Contract.
  </Card>

  <Card title="Why Exterview" icon="lightbulb" href="/why-exterview/overview">
    The category, the moat, and how we're different.
  </Card>
</CardGroup>