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

# Sales-call intelligence as an API

> Submit a recording. Get back 6-pillar AI scoring, coaching feedback, action plans, and rep-level intelligence — typically in 30 to 90 seconds.

Submit a recording. Get back **6-pillar AI scoring**, **coaching feedback**, **action plans**, and **rep-level intelligence** — typically in 30 to 90 seconds.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/quickstart">
    Submit your first analysis in 5 minutes — REST or MCP, your pick.
  </Card>

  <Card title="Install the MCP server" icon="plug" href="/mcp/installation">
    Drop one config block into Claude Desktop, Cursor, or Windsurf. 63 conversational tools.
  </Card>
</CardGroup>

## See it in 30 seconds

<Tabs>
  <Tab title="REST">
    ```bash theme={null}
    curl -X POST https://api.goparlay.io/v1/analyses \
      -H "Authorization: Bearer pk_sandbox_..." \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "org_id": "acme",
        "rep_id": "alex-smith",
        "recording_url": "mock://perfect-pitch"
      }'
    ```

    Returns a queued job. Poll `GET /v1/analyses/:id` until `status: "completed"` (or use webhooks). The response includes 6-pillar scoring, per-pillar feedback, action plan, KPIs (filler words, words-per-minute, questions asked), and the full transcript.
  </Tab>

  <Tab title="MCP">
    Once the MCP server is wired into Claude Desktop, you can just ask:

    ```
    Analyze this call for me: https://my-cdn.com/call.mp3.
    Rep is alex-smith in acme. Once it's done, ask Scout where Alex
    needs the most help.
    ```

    The model calls `analyze_recording`, polls until complete, and then `ask_scout_about_call` — all in one paragraph of natural language. No partner-side code.
  </Tab>
</Tabs>

## What you can build

<CardGroup cols={2}>
  <Card title="Coaching automation" icon="graduation-cap">
    Submit every rep call. Auto-tag persona + methodology. Generate weekly synthesis with action plan. Pipe into Slack, email, or your CRM.
  </Card>

  <Card title="Win/loss analysis" icon="chart-line">
    Tag every call with sold / lost / canceled. Correlate scoring patterns to deal outcomes. Generate org-level insights monthly.
  </Card>

  <Card title="AI-drafted playbooks" icon="wand-magic-sparkles">
    Upload top-performer call notes and methodology docs. Parlay synthesizes a publishable playbook in about 20 seconds. Push it to every future analysis.
  </Card>

  <Card title="In-app coach" icon="messages">
    Embed Scout — Parlay's call-aware coach — in your app. Multi-turn chat against any completed analysis. Welcome questions tuned to the rep's weakest pillars.
  </Card>
</CardGroup>

## How it works

<Steps>
  <Step title="Submit">
    `POST /v1/analyses` with a recording URL (HTTPS audio file or pre-signed S3/GCS URL). Returns immediately with a job id.
  </Step>

  <Step title="Process">
    Parlay transcribes (Deepgram), then analyzes (Gemini 2.5 Flash) using your org's playbook + custom prompts. Typical latency: 30 to 90 seconds for a 5-minute call.
  </Step>

  <Step title="Notify">
    Webhook fires when complete (`analysis.completed`). Or poll `GET /v1/analyses/:id` if you prefer.
  </Step>

  <Step title="Query">
    Pull scores, transcripts, feedback. Aggregate at the rep, org, or pillar level. Chat with Scout for deeper insight.
  </Step>
</Steps>

## What you get back

A completed analysis includes structured data ready to ingest into your dashboards.

<CardGroup cols={3}>
  <Card title="6-pillar scoring" icon="chart-bar">
    Clarity, influence, objection handling, discovery, delivery, close — each scored 0 to 100.
  </Card>

  <Card title="Per-pillar feedback" icon="comments">
    Positive observations + specific improvement areas, citing moments in the call.
  </Card>

  <Card title="KPIs" icon="gauge">
    Words-per-minute, filler-word count, questions asked, plus call duration.
  </Card>

  <Card title="Action plan" icon="list-check">
    Double-down on strengths, general improvement, quoted principle to remember.
  </Card>

  <Card title="Full transcript" icon="file-lines">
    Speaker-diarized transcript with timestamps, ready for replay or further analysis.
  </Card>

  <Card title="Rep-level rollups" icon="user-magnifying-glass">
    Persona, methodology, coaching synthesis. Computed across many calls.
  </Card>
</CardGroup>

## Pricing model

You're billed per AI operation, not per seat. Mock-fixture URLs (`mock://perfect-pitch`, etc.) cost \$0 — use them freely while integrating.

| Operation                         | Approx. cost   |
| --------------------------------- | -------------- |
| Analyze a 5-min real recording    | $0.02 to $0.04 |
| Assign rep persona (over N calls) | $0.01 to $0.05 |
| Generate playbook draft           | $0.01 to $0.10 |
| Scout chat turn                   | under \$0.01   |
| All read endpoints                | free           |

Sandbox keys (`pk_sandbox_*`) bill at \$0 against test data — no real charges until you flip to a live key (`pk_live_*`).

## Get started

<CardGroup cols={3}>
  <Card title="Quickstart" icon="bolt" href="/quickstart">
    5-minute integration walkthrough
  </Card>

  <Card title="Authentication" icon="key" href="/authentication">
    Bearer keys, sandbox vs live, idempotency
  </Card>

  <Card title="MCP install" icon="plug" href="/mcp/installation">
    Connect Claude, Cursor, Windsurf, Zed
  </Card>

  <Card title="First analysis" icon="microphone" href="/guides/first-analysis">
    Mock fixture → real audio → webhooks
  </Card>

  <Card title="API reference" icon="book-open" href="/api-reference/introduction">
    Every endpoint with try-it-now panels
  </Card>

  <Card title="Errors" icon="circle-exclamation" href="/errors">
    Stable error codes and remediation
  </Card>
</CardGroup>