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

# Victoria AI Agents

> 4 specialized AI chat agents with deep expertise in family law

## Multi-Agent AI System

Victoria AI is not a single chatbot—it's a team of specialized AI legal assistants working together through an intelligent orchestrator. Each agent has:

* **Domain-specific expertise** trained on relevant legal knowledge
* **Access to CaseMind memory** for contextual awareness
* **LexVault integration** for document-grounded responses
* **Cost optimization** using the right model for each task

## The 4 Chat Agents

Victoria provides 4 interactive chat agents for different users and use cases:

<CardGroup cols={2}>
  <Card title="Co-Counsel" icon="scale-balanced" href="/victoria/co-counsel">
    **For Law Firms**: General legal strategy, motion drafting, and legal research
  </Card>

  <Card title="Financial Analyst" icon="calculator" href="/victoria/financial-analyst">
    **For Law Firms**: Asset division, spousal support, and financial calculations
  </Card>

  <Card title="Discovery Manager" icon="magnifying-glass" href="/victoria/discovery-manager">
    **For Law Firms**: Discovery strategy, document requests, and interrogatories
  </Card>

  <Card title="Client Liaison" icon="user-headset" href="/victoria/client-liaison">
    **For Clients**: 24/7 case questions, document search, and general guidance
  </Card>
</CardGroup>

<Note>
  Victoria also includes specialized **onboarding agents** (firm, case, and client setup) and **backend AI functions** (case insights, memory extraction, deadline tracking) that work automatically behind the scenes. See [Backend AI](/advanced/backend-ai) for technical details.
</Note>

## How Agent Routing Works

When you ask Victoria a question, here's what happens:

<Steps>
  <Step title="Request Analysis">
    The Orchestrator analyzes your question to determine which specialist agent should handle it
  </Step>

  <Step title="Context Assembly">
    The selected agent gathers relevant information from:

    * CaseMind memory (past conversations and extracted facts)
    * LexVault documents (uploaded case files)
    * Case metadata (parties, dates, jurisdiction)
  </Step>

  <Step title="Expert Processing">
    The specialist agent processes your request using:

    * Domain-specific prompts and knowledge
    * Appropriate Claude model (Haiku/Sonnet/Opus)
    * Relevant legal frameworks and templates
  </Step>

  <Step title="Response Delivery">
    You receive a detailed, contextual response with:

    * Direct answer to your question
    * Relevant citations or references
    * Follow-up suggestions
  </Step>

  <Step title="Memory Update">
    New information is extracted and stored in CaseMind for future reference
  </Step>
</Steps>

## Model Selection

Victoria automatically chooses the right Claude model for each task:

| Task Type                      | Model             | Speed   | Cost     | Best For        |
| ------------------------------ | ----------------- | ------- | -------- | --------------- |
| Routing & Classification       | Claude Haiku 4.5  | \~200ms | $0.80/$4 | Quick decisions |
| Legal Strategy & Drafting      | Claude Sonnet 4.5 | \~2-5s  | $3/$15   | Most tasks      |
| Complex Financial Calculations | Claude Opus 4.1   | \~5-10s | $15/$75  | Precision work  |

<Tip>
  Victoria automatically uses the most cost-effective model for each task. Most requests use Sonnet, with Haiku for routing and Opus reserved for complex calculations.
</Tip>

## Conversational Context

Victoria maintains conversation context within each chat session:

* **Short-term memory**: Recent messages in the current conversation
* **Long-term memory**: All extracted facts stored in CaseMind
* **Document grounding**: Relevant content from uploaded documents

This means you can have natural, flowing conversations without repeating context.

<Warning>
  Each AI agent conversation starts fresh but has access to all CaseMind memory. If you need to reference a previous conversation, mention it explicitly (e.g., "As we discussed earlier about asset division...")
</Warning>

## Cost Tracking

Every Victoria AI request is tracked with:

* **Token usage** (input/output)
* **Model used** (Haiku/Sonnet/Opus)
* **Cost calculation** in real-time
* **Attribution** to case, lawyer, and agent

View detailed usage in **Settings** → **AI Usage Dashboard**.

## Best Practices

<AccordionGroup>
  <Accordion title="Choose the Right Agent" icon="bullseye">
    * **Co-Counsel**: Legal strategy, motions, general questions
    * **Financial Analyst**: Calculations, asset division, support
    * **Discovery Manager**: Discovery planning and document requests
    * **Client Liaison**: Client-facing 24/7 support (in Client Portal)
  </Accordion>

  <Accordion title="Provide Context" icon="message-dots">
    The more context you provide, the better Victoria's responses:

    * Reference specific documents: "Based on the financial affidavit..."
    * Mention jurisdiction: "Under California law\..."
    * State your goal: "I need a motion to modify support because..."
  </Accordion>

  <Accordion title="Upload Documents First" icon="upload">
    Before asking Victoria about a case:

    1. Upload key documents to LexVault
    2. Wait for AI processing to complete
    3. Then ask questions that reference those documents
  </Accordion>

  <Accordion title="Review AI Output" icon="eye">
    Always review and edit Victoria's output before filing or sending:

    * Check facts against source documents
    * Verify calculations independently
    * Ensure jurisdiction-specific requirements
    * Add your professional judgment
  </Accordion>
</AccordionGroup>

## Agent Capabilities Matrix

| Capability               | Co-Counsel | Financial | Discovery | Client Liaison |
| ------------------------ | ---------- | --------- | --------- | -------------- |
| Motion Drafting          | ✅ Expert   | ❌         | ❌         | ❌              |
| Legal Research           | ✅ Expert   | ⚠️ Basic  | ⚠️ Basic  | ❌              |
| Financial Calculations   | ⚠️ Basic   | ✅ Expert  | ❌         | ❌              |
| Asset Division           | ⚠️ Basic   | ✅ Expert  | ❌         | ❌              |
| Discovery Strategy       | ⚠️ Basic   | ❌         | ✅ Expert  | ❌              |
| Document Requests        | ❌          | ❌         | ✅ Expert  | ❌              |
| Client Q\&A              | ⚠️ Basic   | ❌         | ❌         | ✅ Expert       |
| Document Search (Client) | ❌          | ❌         | ❌         | ✅ Expert       |
| General Legal Info       | ⚠️ Basic   | ❌         | ❌         | ✅ Expert       |

<Tip>
  **Case insights, task extraction, and deadline tracking** run automatically in the background via Victoria's Backend AI functions. See [Backend AI](/advanced/backend-ai) for details.
</Tip>

## Next Steps

<CardGroup cols={2}>
  <Card title="Learn About CaseMind" icon="database" href="/features/casemind">
    Understand how Victoria remembers everything
  </Card>

  <Card title="Explore LexVault" icon="folder" href="/features/lexvault">
    Master document management and AI processing
  </Card>
</CardGroup>