---
title: "Document AI"
description: "8 posts about Document AI, summarised, each linking to the original."
---

# Document AI
> 8 posts about Document AI, summarised, each linking to the original.

## Articles

### [What is Document AI?](https://yomu.fyi/post/what-is-document-ai.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: Jun 15, 2026

Document AI uses machine learning, natural language processing (NLP) and optical character recognition (OCR) to extract, classify and understand information from structured, semi-structured and unstructured documents. Unlike OCR alone, it interprets layout and context, turning files such as invoices, contracts and emails into structured, actionable data through ingestion, OCR, layout parsing, entity extraction, classification, validation and, when needed, human review. Modern systems add large language models for summarization, document Q&A and zero-shot extraction, but hallucination risk makes validation and human oversight essential, particularly in regulated settings. The guide also describes Databricks Document Intelligence, which processes and stores documents alongside organizational data under Unity Catalog, using AI Functions, Variant and Lakeflow Jobs to create governed, queryable workflows without moving data between systems.


### [Transforming solar and wind maintenance reports with Genie and AI agents](https://yomu.fyi/post/transforming-solar-and-wind-maintenance-reports-with-genie-and-ai-agen.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Maria Vallarelli
- Published: Jun 8, 2026

Plenitude and Databricks built an agent-based system that turns solar and wind plant maintenance PDFs into structured data for cross-plant analysis. Event-driven ingestion uses Databricks Jobs and the ai\_parse\_document AI Function to extract text, tables, figures, and metadata, then stores page- and object-level JSON records in Delta Lake with coordinates, version history, and links to source reports. A Genie space uses Unity Catalog metadata, knowledge-store instructions, and SQL generation to answer natural-language questions, produce visualizations, and export results, while Agent Bricks can orchestrate multi-step workflows and downstream actions. The design also applies automatic liquid clustering to dynamic queries and row-level security to restrict results by country. The resulting data layer supports historical trends, plant comparisons, recurring-fault analysis, and a foundation for predictive maintenance, although the source frames predictive use as a future improvement.


### [Unlocking the Archives: Turning Unstructured Documents into a Searchable Database for Groundwater Discovery](https://yomu.fyi/post/unlocking-the-archives-turning-unstructured-documents-into-a-searchabl.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Andres David Blandon Restrepo, Mofeed Nagib
- Published: May 11, 2026

MapAid and the Sudan Association for Archiving Knowledge (SUDAAK) needed to make nearly 700 scanned geological reports searchable and recover well data for MapAid’s WellMapr groundwater models. Databricks built a Databricks-only pipeline that renders pages as images, uses multimodal AI Functions for page classification and schema-constrained JSON, and applies targeted sampling to cut classification processing by more than 70%. Water-relevant documents receive page-by-page OCR through the Foundation Model API, with well and borehole identifiers linking information across pages before structured records capture locations, depths, static water levels, and yields. In its first full run, 654 documents and 5,570 pages were classified in under three hours; 95% received excellent or good evaluations, about half contained water data, and 299 well or borehole records were extracted.


### [How to transform document activation workflows with Genie and Agent Bricks](https://yomu.fyi/post/how-to-transform-document-activation-workflows-with-genie-and-agent-br.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Elena Tesser
- Published: Apr 22, 2026

Enterprise document workflows often require people to read PDFs, copy fields into spreadsheets, and re-enter data into business systems, creating delays, error risk, and weak auditability. The proposed alternative combines AI/BI Genie for natural-language queries over Delta tables, Agent Bricks for production agents, and Unity Catalog for permissions, lineage, and traceability. A five-phase workflow extracts fields into Lakeflow Bronze, Silver, and Gold layers, then supports structured queries, clause-level RAG answers, multi-agent routing, and actions through MCP servers. Examples include syncing validated rights data to ERP or CRM systems, updating billing entitlements, and triggering workflows from detected obligations. The approach targets media, advertising, ad tech, and telecommunications, where customers see improvements including faster month-end close, recovered revenue, reduced leakage, and lower operational risk.


### [Why your agents can't read enterprise documents — and how to fix it](https://yomu.fyi/post/why-your-agents-can-t-read-enterprise-documents-and-how-to-fix-it.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Archika Dogra, Sergei Tsarev, Erich Elsen
- Published: Apr 16, 2026

Enterprise agents often reason well over clean text but struggle with scanned PDFs, inconsistent layouts, nested tables, images, and handwriting, making document processing an accuracy ceiling for business workflows. The post announces Document Intelligence, a pipeline of chainable AI Functions: ai\_parse\_document converts scans into layout-enriched structured text, while ai\_classify and ai\_extract support routing and entity extraction. On OfficeQA treasury-bond documents, preprocessing with ai\_parse\_document produced a 16% average performance gain across tested agent frameworks without changing their reasoning harness. Across invoice, contract, medical-note, and financial-filing extraction tasks, it reportedly delivered the highest accuracy at 5–7x lower cost than comparable pipelines, with serverless batch infrastructure scaling the same SQL call from 100 to 100,000. Databricks integrates ingestion, orchestration, governance, and agent building through Lakeflow Connect, Lakeflow Jobs or Spark Declarative Pipelines, Unity Catalog, and Agent Bricks, aiming to replace fragmented services with reusable workflows.


### [Building with Databricks Document Intelligence and Lakeflow](https://yomu.fyi/post/building-with-databricks-document-intelligence-and-lakeflow.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Giselle Goicochea, Joanna Zouhour
- Published: Apr 16, 2026

The post presents a production-oriented approach to Intelligent Document Processing (IDP) that brings PDFs, images, and office documents into Databricks’ governed data lifecycle. Lakeflow Connect ingests files from sources such as SharePoint and Google Drive into Unity Catalog Volumes and tables, applying access control, lineage, and auditing while supporting incremental reads and writes. Databricks’ Document Intelligence then uses ai\_parse\_document to preserve structure in VARIANT output, with ai\_extract, ai\_classify, and ai\_prep\_search available for enrichment, routing, and retrieval preparation. Lakeflow Jobs productionizes the workflow with orchestration, control flow, retries, triggers, serverless scaling, and observability across ingestion, parsing, and serving tasks. The post also recommends joining extracted data to master data, using service principals, and monitoring drift and extraction accuracy, presenting the combined platform as a way to create trusted, queryable datasets from unstructured content.


### [Financial Benchmarks](https://yomu.fyi/post/financial-benchmarks.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Kedar Thakkar, Anton Biryukov, Ashwin Kumar, Ryne Carbone
- Published: Mar 9, 2026

Ramp describes how it benchmarks large language models (LLMs) used in financial products against day-to-day tasks such as invoice extraction, financial-statement OCR, policy review, accounting autocoding, compliance detection, and fund routing. These benchmarks combine task-specific metrics with cost, latency, reasoning effort, human decisions, historical context, and ground-truth datasets where available. For contextual invoice OCR, perfect extraction requires every field to match the user's final bill, while financial-statement OCR uses a 1% relative-error threshold against transcriptions from over 500 real P&L documents. Results show application-specific trade-offs: Gemini 3 Flash is described as a cost-efficient leader for several visual and financial tasks, while Claude models lead some high-accuracy or low-miss-rate settings, and behavior can differ within one provider. The framework emphasizes Pareto trade-offs and continuous testing, with plans to expand from benchmarking current performance to hill climbing on capabilities.


### [How we built a custom vision LLM to improve document processing at Grab](https://yomu.fyi/post/how-we-built-a-custom-vision-llm-to-improve-document-processing-at-gra.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Jia Chen
- Published: Nov 4, 2025

Grab developed a specialized Vision LLM for extracting text and key information from Southeast Asian identity cards, driver’s licenses, and registration certificates, where varied languages and layouts challenged traditional OCR and existing models. It selected Qwen2-VL 2B for its efficient size, SEA language tokenizer coverage, and dynamic native-resolution image handling, while synthetic Common Crawl text images and Documint supplied reviewed training labels for detection, orientation, OCR, and KIE. LoRA fine-tuning improved Latin-script documents but struggled with Thai, Vietnamese, and dense unstructured layouts, leading to two-stage full-parameter training with synthetic SEA text images followed by task-specific document fine-tuning. The fully fine-tuned 2B model raised Thai accuracy by 70 percentage points and Vietnamese accuracy by 40 points over baseline, while a custom roughly 1B-parameter model combining Qwen2-VL 2B’s vision encoder with Qwen2.5 0.5B’s decoder stayed within a 3-point accuracy gap across most document types and achieved lower latency.