Workflow Automation

Automate Tasks & Deploy Agents

Turn processed data into active workflows. Replace manual data entry and unverified answers with type-safe extraction and grounded reporting.

Structured output from unstructured data: Extract schemas, not strings

Use the summarize endpoint with a Pydantic model to extract structured data

bookwyrm summarize data/country-of-the-blind-phrases.jsonl \
  --model-class-file data/summary.py \
  --model-class-name Summary \
  --model-strength smart \
  --output data/country-structured-summary.json \
  --verbose

Join the Beta Read the Docs

Structured Output from Unstructured Data

Don't parse strings; extract schemas. Pass a Pydantic model to the summarize endpoint to get validated JSON back—perfect for automating invoice processing or product enrichment.

Type-Safe

Returns data matching your exact Pydantic schema.

Validated

Ensures required fields are present and correctly typed.

Automated

Ideal for piping directly into downstream APIs or databases.

Developer Implementation

bookwyrm summarize data/country-of-the-blind-phrases.jsonl \
  --model-class-file data/summary.py \
  --model-class-name Summary \
  --model-strength smart \
  --output data/country-structured-summary.json \
  --verbose

Report on Actual Data

Generate answers, not just text. The cite endpoint scans your chunks to provide answers backed by explicit source citations, quality scores, and reasoning chains.

Grounded

Every answer is tied to specific text chunks.

Scored

Quality scores (0-4) allow you to filter out weak matches.

Transparent

Reasoning chains explain why a chunk matches the query.

Developer Implementation

bookwyrm cite \
  --question "What are the top three client prospects by sales value from Graham Johnson?" \
  --url https://sales.com/sales-forecast-chunks.jsonl

Agentic Workflow Integration

Combine these tools to build autonomous agents. Use the Python client to loop through data, extract structures, and verify facts in real-time.

Structured Extraction

Extract validated data structures using Pydantic models for type-safe automation.

Real-Time Verification

Verify extracted data against source documents using citation endpoints for accuracy.

Autonomous Agents

Build agents that automatically process, validate, and act on structured data.

Developer Implementation

Use the async Python client to combine structured extraction with citation verification for robust agentic workflows.

# Python Agent Pattern
async with AsyncBookWyrmClient() as client:
    # 1. Extract Data
    summary = await client.summarize(
        content=text,
        model_name="Invoice",
        model_schema_json=invoice_schema
    )
    
    # 2. Verify with Citations
    citations = await client.get_citations(
        chunks=chunks,
        question="Is this invoice amount consistent with the contract?"
    )

Workflow Use Cases

Explore specialized BookWyrm use cases for building automated workflows and agentic systems.

Agentic Commerce

Enrich product data with sales and marketing collateral. Enhance discoverability and sales with agents that have a complete view of your inventory.

Back Office Automation

Build reliable, scalable back office automation pipelines with BookWyrm's data pipeline API. Transform unstructured documents into high-fidelity, AI-ready data.

AI for Research

Automate literature review and citation extraction with verifiable sources. Build research pipelines that reduce hallucinations and ground every AI output in real, citable evidence.

Business Reporting

Answer complex business questions by finding and verifying evidence within your source files using BookWyrm's cite endpoint. Generate trusted reports with explicit source citations.

Plugin RAG

Build powerful RAG systems with BookWyrm's easy-to-use endpoints. Perform phrasal extraction, summarization, and citation grounding in simple, composable steps.

Library Automation

Automate cataloguing and metadata extraction for libraries and archives. Transform scanned texts, PDFs, and articles into standardized records in seconds.

BookWyrm Delivers Your Agentic Workflows Strategy.

Your data pipeline is the foundation for your agentic workflows. Build it right. Get started with the API that's fast to set up, easy to extend, and built for developers.

Join the Beta Book A Design Session