> ## 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.

# Deploy Exterview

> Overview of the Exterview deploy phase, covering the session-based lifecycle and the split between live agent sessions and document-workflow sessions.

A configured Exterview workflow is **deployed** when it's made available for a candidate, recruiter, interviewer, or downstream system to use, as a live agent session or a document workflow.

## The Exterview lifecycle

Deploy is the middle step of the Configure, Deploy, Monitor lifecycle.

<CardGroup cols={3}>
  <Card title="Configure" icon="sliders" href="/configure/overview">
    Set up your organization structure, evaluation rules, and governance.
  </Card>

  <Card title="Deploy" icon="rocket" href="/deploy/overview">
    Launch agent sessions and document workflows, and integrate with your systems.
  </Card>

  <Card title="Monitor" icon="chart-line" href="/monitor/overview">
    Review reports, analytics, and post-hire outcome intelligence.
  </Card>
</CardGroup>

## Specialized agents, not one model

Exterview is built as a set of specialized agents. Each one owns exactly one session type and holds the full context for that role and candidate, and every agent produces one specific output. There is no single monolithic model trying to do everything.

```mermaid theme={null}
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#EEF2FF','primaryBorderColor':'#4B6CFE','primaryTextColor':'#0F172A','lineColor':'#64748B','clusterBkg':'#F8FAFC','clusterBorder':'#E2E8F0'}}}%%
flowchart LR
  CTX([Role + candidate context]) --> AGENT([One specialized agent]) --> RPT([One specific report])
```

*Each session type runs on its own specialized agent that carries the full role and candidate context and produces exactly one report. The full list of agents is below; there is no single monolithic model doing everything.*

<Info>
  Smaya, Exterview's in-app companion, is upcoming. Its first release answers
  questions about your hiring data read-only; it does not select or run agents.
  See [Smaya](/smaya/overview).
</Info>

<Note>
  One agent, one session type, one output. The agent carries the role and
  candidate context end to end, which is what makes its output specific and
  reproducible.
</Note>

## The agents

<Info>
  **Availability:** **Available** means usable today. **Upcoming** means
  planned, not yet available; all upcoming agents target before December 2026.
</Info>

<CardGroup cols={2}>
  <Card title="EX Scan" icon="magnifying-glass">
    **Available.** Resume screening and role creation. Output: Resume Match Report.
  </Card>

  <Card title="EX Phone Screen" icon="phone">
    **Available.** Short phone screening. Output: Phone Call Report.
  </Card>

  <Card title="EX Voice" icon="microphone">
    **Available.** AI voice interview. Output: Voice AI Screening Report.
  </Card>

  <Card title="EX Avatar" icon="video">
    **Available.** AI avatar interview. Output: Avatar AI Screening Report.
  </Card>

  <Card title="EX Panel" icon="users">
    **Coming soon.** Panel evaluation with consolidated scoring. Output: Panel AI
    Report.
  </Card>

  <Card title="EX HR" icon="user-tie">
    **Coming soon.** HR and behavioral round, including offer and
    likelihood-to-join signals. Output: HR AI Report.
  </Card>

  <Card title="EX Skill Assessment" icon="clipboard-check">
    **Upcoming.** Role-relevant skill assessment. Output: Assessment AI Report.
  </Card>

  <Card title="EX Code" icon="code">
    **Launching Aug 31, 2026.** Coding assessment with structured scoring. Output:
    Code AI Report.
  </Card>

  <Card title="EX Onboarding Buddy" icon="handshake">
    **Upcoming.** Post-hire onboarding support. Output: Buddy AI Screening Report.
  </Card>

  <Card title="EX Role Fit" icon="chart-line">
    **Upcoming.** Post-hire role-fit check-in. Output: Rolefit AI Screening Report.
  </Card>
</CardGroup>

<Note>
  Available today: EX Scan, EX Phone Screen, EX Voice, and EX Avatar. EX Code is
  launching Aug 31, 2026. Coming soon: EX Panel and EX HR (around Q1 2027). Also
  upcoming: EX Skill Assessment, EX Onboarding Buddy, and EX Role Fit. See
  [Session Types](/deploy/session-types).
</Note>

<Info>
  **Role creation** is part of **EX Scan** and runs as an included document
  workflow rather than a separate agent. **Offer recommendation and
  join-likelihood** is delivered through **EX HR**; the offer document and
  e-signature are handled as an integration and are upcoming.
</Info>

## Two ways an agent runs

<Tabs>
  <Tab title="Live agent sessions">
    Real-time interactions where the candidate engages directly with the agent:
    phone, voice, and avatar rounds today, with panel and HR rounds, and
    post-hire companions, coming soon. The agent conducts the session and
    produces its report on completion.
  </Tab>

  <Tab title="Document workflows">
    Non-live tasks the agent runs against submitted material: resume screening
    and role creation (EX Scan) today. There is no candidate session; the output
    is generated from documents.
  </Tab>
</Tabs>

## How an agent deploys

<Steps>
  <Step title="Enable the agent">
    Turn on only the agents a role needs, and deploy by role, department, or
    region.
  </Step>

  <Step title="Trigger the session or workflow">
    A candidate is invited, or a document workflow runs. The agent takes it from
    there.
  </Step>

  <Step title="Agent produces its output">
    The agent completes and generates its one specific report.
  </Step>

  <Step title="Route to review">
    The output moves into Monitor for human review, with no autonomous adverse
    decisions.
  </Step>
</Steps>

## The lifecycle

```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 deploy lifecycle: a configured agent is deployed, runs as an active session, completes, and its output moves into Monitor for human review.*

## FAQs

<AccordionGroup>
  <Accordion title="Why is each session type an agent?" icon="diagram-project">
    Because the agent holds the role and candidate context for that evaluation. That's what makes its output specific to your role and reproducible over time.
  </Accordion>

  <Accordion title="Do we deploy all agents at once?" icon="toggle-on">
    No. Enable only the agents a role needs, and deploy by role, department, or
    region.
  </Accordion>

  <Accordion title="Where do I see what each agent produces?" icon="file-chart-column">
    Each agent's output is detailed in Session Types, and reviewed in Monitor.
  </Accordion>
</AccordionGroup>

## Related

<CardGroup cols={2}>
  <Card title="Session Types" icon="layer-group" href="/deploy/session-types">
    Each agent in detail: what it does and what it produces.
  </Card>

  <Card title="Production Checklist" icon="circle-check" href="/deploy/production-checklist">
    Confirm readiness before going live.
  </Card>
</CardGroup>