# Firecrawl introduces Agentic OCR for structured data extraction from images

> Firecrawl has released a new OCR feature that uses AI agents to extract structured data from images and documents.

- Canonical: https://extractfeed.io/story/firecrawl-introduces-agentic-ocr-for-structured-data-extract-eae1acb/
- JSON: https://extractfeed.io/api/v1/stories/firecrawl-introduces-agentic-ocr-for-structured-data-extract-eae1acb.json
- Beat: Extraction & Parsing · Evidence: Primary source · Type/significance: launch/3 · First seen: 2026-09-06T15:05:07.356916+00:00 · Updated: 2026-09-06T15:05:07.356916+00:00 · Edition: 2026-09-06
- Framing: model-written (headline, standfirst, why it matters, tags); source facts deterministic

## Briefing
- Firecrawl: Firecrawl has released a new OCR feature that uses AI agents to extract structured data from images and documents.

## Why it matters
This release extends Firecrawl's web scraping capabilities into visual content, enabling users to extract structured data from images, PDFs, and other visual formats. As more web content is embedded in images or non-text formats, Agentic OCR fills a gap for automated data extraction pipelines that need to handle visual information alongside traditional HTML scraping.

## Sources
- Primary source · Firecrawl · date unknown — [Agentic Ocr](https://www.firecrawl.dev/blog/agentic-ocr)

## Watch next
How does Agentic OCR compare to existing OCR solutions like Tesseract or cloud-based APIs in terms of accuracy and cost?

Topics: Firecrawl, ocr, structured-data, image-extraction, firecrawl

---
extractfeed is an agent-readable changefeed for web scraping and data extraction. Index: https://extractfeed.io/agents.md