← Back to the App

Library Tools

The Library suite provides semantic search and retrieval over DataGrout’s documentation, tool references, feature guides, and research papers. Use these tools to find answers about how DataGrout works without leaving your agent workflow.

library.search

Search documentation and papers by natural language query. Returns ranked results with titles, sections, snippets, and refs for retrieval.

0 credits — pure discovery.

Parameters

Parameter Type Required Description
query string yes Natural language search query
type string no Filter by content type: reference, tutorial, paper, overview, all (default: all)
suite string no Filter to a specific tool suite slug, e.g. warden, flow, logic
limit integer no Max results, 1-15 (default: 5)

Example

{
  "query": "how does flow.route branching work",
  "type": "reference",
  "limit": 3
}

Response:

{
  "success": true,
  "results": [
    {
      "ref": "flow-inspect-tools#flow-route",
      "title": "Flow & Inspect Tools Reference",
      "section": "flow.route",
      "snippet": "Routes execution across branches based on field conditions...",
      "score": 0.89,
      "type": "reference"
    }
  ],
  "total": 1,
  "query": "how does flow.route branching work"
}

Tips

  • Use specific questions: “how does warden.canary differ from warden.intent” works better than “warden”
  • Filter by suite when you know which tool area you’re looking for
  • Use type: "paper" to search research papers specifically
  • The ref field in results is the key for library.get

library.get

Retrieve documentation or paper content by ref. Use refs from library.search results, or pass a known slug directly.

0 credits — pure retrieval.

Parameters

Parameter Type Required Description
ref string yes Document slug or slug#section from search results. Prefix with paper: for research papers.
goal string no If provided, returns only the section most relevant to this goal.

Ref Format

Refs follow these patterns:

  • "flow-inspect-tools" — full library document
  • "flow-inspect-tools#flow-route" — specific section within a document
  • "paper:ail" — research paper
  • "paper:ail#search-endpoint" — section within a paper

Example

{
  "ref": "warden-tools#which-tool-to-use"
}

Response:

{
  "success": true,
  "ref": "warden-tools",
  "title": "Warden Tools Reference",
  "type": "reference",
  "content_markdown": "## Which tool to use\n\n| Situation | Tool | Why |\n...",
  "word_count": 450,
  "url": "https://library.datagrout.ai/warden-tools"
}

Goal-Directed Retrieval

When you know what you’re looking for but not which section contains it, pass a goal:

{
  "ref": "flow-inspect-tools",
  "goal": "how to validate a workflow before executing it"
}

This returns only the most relevant section instead of the full document, reducing token consumption.

Workflow: Search then Get

The typical pattern is:

  1. Search for what you need: 

    {"query": "prompt injection detection", "limit": 3}

  2. Get the most relevant result: 

    {"ref": "warden-tools#warden-ensemble"}

  3. Read the returned markdown content and apply it.

This two-step pattern keeps token usage minimal — search returns lightweight summaries, get returns only the content you need.

Available Content

The library includes:

  • Tool references — Detailed docs for every tool suite (Warden, Flow, Logic, Prism, etc.)
  • Feature guides — Multiplexing, discovery engine, policy & security, credits
  • Getting started — Quick start, core concepts, Conduit SDK
  • Connectivity — Authentication, JSON-RPC, tool naming conventions
  • Guides — Playground, sandbox, inspectors, building workflows
  • Research papers — AIL, Semio, CTC, Governor, Arbiter, Warden, and more

Use library.search with type: "paper" to find research papers, or type: "tutorial" for step-by-step guides.