LlamaIndex

Webinar: Building a life new business underwriting workflow with Llamaparse

Published 2026-11-18 · Duration 58:15

Summary

This webinar details the architecture of a life underwriting workflow, demonstrating how AI-driven document parsing, splitting, classification, and extraction can automate data ingestion from complex, multi-page medical records. The system emphasizes a Human-in-the-Loop (HITL) approach, utilizing confidence scores and deterministic checks to flag discrepancies, ensuring data reliability before final decision-making.

Download summary

Key takeaways

  1. The Role of the Parsing Pipeline 19:45

    The workflow relies on a sequence: Parse (converting documents to structured JSON/Markdown), Split (breaking large documents into granular parts), Classify (identifying document type with confidence scores), and Extract (pulling specific key-value pairs).

  2. Ensuring Data Trustworthiness 22:20

    The system incorporates critical checks, including checking for missing pages, verifying data consistency across sources, and flagging heavily degraded scans. Confidence scores are provided on a per-attribute basis.

  3. Model Reliability and Evaluation 7:10

    To maintain stability in production, models can be 'pinned' after formal evaluation. The company promotes the use of open-source tools like parsbench 2 for running independent evaluations.

  4. Workflow Automation vs. Human Judgment 27:20

    AI is used to handle the high-volume, repetitive tasks (reading, checking, cross-referencing), allowing underwriters to focus on the complex, human elements like reaching out to applicants or resolving discrepancies.

More digests on Document Parsing

Technical details

  • Parsing Tiers and Complexity 1070s

    Parsing solutions are categorized into tiers: Fast (text-only, digital text layer), Cost-Effective (basic charts/images), Agentic (complex tables), and Agentic Plus (most messy documents, stamps, dense tables). A 'cost optimizer' can automatically drop down the tier if a page is simple enough.

  • Parse vs. Extract Distinction 1270s

    Parse outputs the entire document content (JSON/Markdown) for agent consumption, while Extract builds on the parsed output to pull specific, defined key-value pairs based on a schema.

  • Data Storage and Retrieval 1890s

    Extracted information is stored in both relational databases and vector databases, enabling agents to perform comparisons and allowing humans to query the data via a chatbot with citation links.

  • Handling Complex Documents 1000s

    For large documents, the 'Split' solution breaks the input into granular components (e.g., fax cover sheet, lab results, office notes) before extraction, improving processing accuracy.

Mentioned resources

  • LlamaIndex (Platform/Solution)
  • parsbench 2 (Open Source Evaluation Tool)
  • light parse (Open Source CPU-centric Parser)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.