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

# Complete Enterprise Customer Onboarding Guide

> A complete step-by-step walkthrough for onboarding an enterprise organization to MITHUNAI: provisioning members, connecting knowledge, configuring assistants, evaluating grounding, and deploying production channels.

Enterprise onboarding onto MITHUNAI follows a structured six-phase journey that transitions your organization from initial workspace provisioning to production multi-channel deployment with verified factual grounding. Each phase establishes explicit boundaries, security controls, and verification gates before moving to the next.

```mermaid theme={"theme":{"light":"github-light","dark":"github-dark"}}
flowchart LR
    P1["1. Provision\nWorkspace & RBAC"] --> P2["2. Connect\nData Sources"]
    P2 --> P3["3. Ingestion &\nAST Chunking"]
    P3 --> P4["4. Configure\nAssistant & Models"]
    P4 --> P5["5. Grounding &\nTruth Evaluation"]
    P5 --> P6["6. Multi-Channel\nProduction Launch"]
```

***

## Phase 1: Workspace Setup & Member Provisioning

Every enterprise engagement begins with an isolated tenant organization governed by role-based access control (RBAC).

<Steps>
  <Step title="Verify Organization Provisioning">
    Your deployment administrator provisions your organization and assigns the initial **Owner**. Owners hold full administrative authority over members, collections, assistants, API keys, and branding.
  </Step>

  <Step title="Invite Team Members & Set Roles">
    Invite your core project team via the console or the members API:

    * **Administrators**: Knowledge engineers and security leads who configure connectors and manage API keys.
    * **Editors**: Technical writers and product managers who curate assistants and evaluate answers.
    * **Members**: Team members who query the assistant and review conversation histories.

    ```bash Add Member via API theme={"theme":{"light":"github-light","dark":"github-dark"}}
    curl -X POST https://app.mithunai.com/arukz/api/v1/members \
      -H "Authorization: Bearer $MITHUNAI_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "email": "engineer@example.com",
        "role": "admin"
      }'
    ```
  </Step>
</Steps>

***

## Phase 2: Connect Knowledge Sources

Connect the repositories, portals, and documentation spaces that form your factual ground truth.

* **Developer Documentation & Sitemaps**: Enter your public or internal sitemap URL (`https://docs.example.com/sitemap.xml`). MITHUNAI validates the safe-fetch boundary and establishes crawl limits.
* **GitHub & GitLab Repositories**: Connect your engineering repositories, specify branch targets (`main` or `release/v2`), and apply path globs (`docs/**`, `api/**/*.ts`).
* **Workspace Wikis (Notion & Confluence)**: Authorize enterprise OAuth to sync engineering spaces while preserving document hierarchies.
* **Document Archives**: Drag-and-drop architectural whitepapers, PDF runbooks, and OpenAPI specifications.

***

## Phase 3: Ingestion, Chunking & Verification

Trigger an asynchronous sync job to ingest, redact secrets, and vectorize the content into your organization's partitioned `pgvector` store.

1. **Secret & Credential Redaction**: Automated pre-index filters detect and mask API tokens, private SSH keys, and connection strings.
2. **Structural AST & Semantic Chunking**: Markdown and code are split along logical boundaries (headers, classes, functions) rather than arbitrary byte boundaries.
3. **Ingestion Verification**: Monitor job progress via `GET /knowledge/jobs/{id}` or the console dashboard. Ensure all pages commit with status `completed`.

***

## Phase 4: Configure Assistant & Inference Gateway

Create and tailor your AI assistant for your specific audience.

```mermaid theme={"theme":{"light":"github-light","dark":"github-dark"}}
flowchart TD
    CFG["Assistant Configuration"] --> LLM["Select Primary Model\n(Claude 3.5 Sonnet / GPT-4o / Gemini 2.0)"]
    CFG --> CORPUS["Attach Knowledge Collections\n(1 or more verified corpora)"]
    CFG --> INSTR["Define System Instructions\n(Tone, terminology, domain focus)"]
    CFG --> GW["Configure Gateway Rules\n(Semantic cache, rate limits, prompt fences)"]
```

* **Model Selection**: Choose your preferred upstream model or configure private on-premise inference (`vLLM`, `Ollama`).
* **Prompt Fencing**: Enable cryptographic nonces to isolate retrieved passages from system commands.
* **Semantic Caching**: Activate the sub-45ms cache to serve repeated technical questions instantly at zero inference cost.

***

## Phase 5: Grounding & Truth Evaluation

Before public deployment, validate answer quality against your domain's benchmark questions in the **Ask & Test Playground**:

1. **Direct Evidentiary Checks**: Verify that answers cite the exact line numbers and URLs of the source documentation.
2. **Abstention Verification**: Test out-of-scope questions (e.g., *"How do I configure product X that we don't build?"*). Ensure the assistant explicitly declines rather than hallucinating.
3. **Citation Click-Through**: Click each generated citation badge in the test UI to confirm the highlighted excerpt matches the assertion.

***

## Phase 6: Multi-Channel Production Launch

Deploy your assistant across the channels where your users and developers interact:

<Columns cols={3}>
  <Card title="Embeddable Web Widget" icon="message-square" href="/channels/widget">
    Generate an `arukz_wk_` key, configure your website's origin allowlist (`https://example.com`), and paste the `<script>` tag onto your documentation portal.
  </Card>

  <Card title="REST API Integration" icon="code" href="/channels/api">
    Mint an `arukz_sk_` service key with rate limits to build conversational intelligence directly into internal portals or ticketing bots.
  </Card>

  <Card title="Model Context Protocol" icon="plug" href="/channels/mcp">
    Distribute the read-only MCP configuration to your engineering team for integration into Cursor, Claude Desktop, and Windsurf IDEs.
  </Card>
</Columns>