> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://conductorai.ferndocs.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://conductorai.ferndocs.com/_mcp/server.

# Agentic search

> Search across millions of pages of structured and unstructured data with AI-powered citation tracking.

Conduit's agentic search enables organizations to search across millions of documents, emails, images, and other materials. Every result is cited back to the specific document, page, and portion.

## Supported data types

| Format         | Extensions              | Notes                                         |
| -------------- | ----------------------- | --------------------------------------------- |
| Documents      | `.pdf`, `.docx`, `.doc` | Full text extraction with layout preservation |
| Spreadsheets   | `.xlsx`, `.csv`         | Cell-level indexing and cross-reference       |
| Presentations  | `.pptx`                 | Slide content and speaker notes               |
| Images         | `.png`, `.jpg`, `.tiff` | OCR with confidence scoring                   |
| Web content    | `.html`, `.mhtml`       | Rendered content extraction                   |
| Email archives | `.pst`, `.mbox`         | Thread reconstruction and attachment indexing |

## Search modes

### Semantic search

Natural language queries matched against document meaning, not just keywords:

```bash
curl -X POST https://api.conductorai.com/v1/search \
  -H "Authorization: Bearer $CONDUIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "export control policies for dual-use technologies",
    "mode": "semantic",
    "limit": 50
  }'
```

### Agentic search

Multi-step search that decomposes complex queries into sub-tasks, retrieves evidence from multiple sources, and synthesizes results with full citations:

```bash
curl -X POST https://api.conductorai.com/v1/search \
  -H "Authorization: Bearer $CONDUIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "identify out-of-date policies and suggest revisions",
    "mode": "agentic",
    "collections": ["policy-library", "regulatory-updates"]
  }'
```

## Citation tracking

Every search result includes a citation chain linking back to the source:

```json
{
  "results": [
    {
      "content": "Section 4.2.1 restricts export of...",
      "citation": {
        "document": "ITAR-Policy-2025.pdf",
        "page": 47,
        "paragraph": 3,
        "confidence": 0.97
      }
    }
  ]
}
```