> ## 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.

# Meet Smaya

> Smaya is Exterview's in-app AI companion, delivered as three tiers of escalating autonomy on one governed foundation: read-only answers first, then acting with human approval, then external reach.

Smaya is Exterview's in-app AI companion. It opens from a persistent **Ask** control in the header as a docked side panel that reflows the workspace rather than covering it, so it reads as part of Exterview, not a popup. It understands what's on your screen, answers grounded in your organization's knowledge with citations, and is built to grow, under human control, from answering into acting.

<Note>
  Smaya is one companion delivered as three tiers of escalating autonomy on a
  single governed foundation. What ships first is deliberately narrow and
  read-only. Every tier beyond that acts only with a human approving each step.
  Smaya never makes an autonomous adverse decision.
</Note>

## The three tiers

The foundation stays the same at every tier: grounded and cited, specific to your organization, human-approved, and audited. Each tier adds capability on top of that line, it never loosens it.

```mermaid theme={null}
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#EEF2FF','primaryBorderColor':'#4B6CFE','primaryTextColor':'#0F172A','lineColor':'#64748B','clusterBkg':'#F8FAFC','clusterBorder':'#E2E8F0'}}}%%
flowchart TD
  F([One governed foundation])
  F --> S([Tier 1 — Simple])
  F --> U([Tier 2 — Super])
  F --> M([Tier 3 — MCP])
```

*One governed foundation carries three tiers of increasing autonomy. Tier 1, read-only, ships first; Tiers 2 and 3 are on the roadmap and never loosen the foundation's controls.*

<CardGroup cols={3}>
  <Card title="Simple: read-only Q&A" icon="comments">
    **Available first.** Grounded, cited, state-aware answers about the record on screen and your organization's knowledge. Smaya knows which candidate, job, and organization you are viewing, and says "I don't know" rather than inventing an answer. No data ever changes.
  </Card>

  <Card title="Super: agentic co-pilot" icon="wand-magic-sparkles">
    **On the roadmap.** Smaya reasons, plans a multi-step approach, acts, and
    observes the result in a loop. Every step that changes data passes through a
    human approval gate first. Nothing consequential executes on its own.
  </Card>

  <Card title="MCP: external surface" icon="plug">
    **On the roadmap.** Reach Exterview from approved external assistants, such as Microsoft 365 Copilot, through a governed gateway scoped to your organization's access rules. See [MCP](/smaya/mcp).
  </Card>
</CardGroup>

## The line that does not move

These controls hold identically at every tier. This is what makes escalating autonomy safe to adopt.

<CardGroup cols={2}>
  <Card title="Grounded and cited" icon="quote-left">
    Every answer traces to a source. Empty or low-confidence retrieval returns "I don't know," never an invented answer.
  </Card>

  <Card title="Specific to your organization" icon="shield-halved">
    Every retrieval is filtered to your organization, with no access to another
    customer's data, and sensitive fields are redacted by the viewer's role.
  </Card>

  <Card title="Human-approved actions" icon="user-check">
    Read and navigate assist you directly. Anything that changes data is proposed,
    not performed, and waits for a person to approve it. See [Human
    Oversight](/smaya/oversight).
  </Card>

  <Card title="Fully audited" icon="clipboard-list">
    Every answer, proposed action, and approval is recorded with its trace, so a reviewer can see exactly what Smaya did and why.
  </Card>
</CardGroup>

## Where to go next

<CardGroup cols={2}>
  <Card title="How It Works" icon="arrows-spin" href="/smaya/how-it-works">
    The agent loop behind the tiers, and how Smaya decides it is done.
  </Card>

  <Card title="Human Oversight" icon="user-check" href="/smaya/oversight">
    The approval gate and the control model, from the first release onward.
  </Card>
</CardGroup>

## FAQs

<AccordionGroup>
  <Accordion title="What can Smaya do today versus later?">
    The first release is Tier 1: read-only, grounded, cited answers. Tier 2 (acting) and Tier 3 (external reach) are on the roadmap and add autonomy in stages, always with a human approving each action that changes data.
  </Accordion>

  <Accordion title="Can Smaya change data on its own?">
    No. Read and navigate assist you directly. Any action that changes data is
    proposed and held at a human approval gate. Smaya never executes a
    consequential action autonomously.
  </Accordion>

  <Accordion title="Where does Smaya get its answers?">
    From your organization's indexed knowledge and the record on screen, specific
    to your organization. Every answer carries a citation back to its source.
  </Accordion>

  <Accordion title="Is Smaya available now?">
    Tier 1 is on the near-term roadmap. See [Upcoming](/product-updates/upcoming) for timing, and treat Tier 2 and Tier 3 as later steps on the same foundation.
  </Accordion>
</AccordionGroup>

## Related

<CardGroup cols={2}>
  <Card title="How It Works" icon="arrows-spin" href="/smaya/how-it-works">
    The perceive, reason, act, and observe loop.
  </Card>

  <Card title="Responsible AI" icon="scale-balanced" href="/trust/responsible-ai">
    How human review and no autonomous adverse decisions are enforced.
  </Card>
</CardGroup>