Turn your documents
into a live database

Metadata Views extract structured data from PDFs, contracts, invoices, images, and handwritten documents. Describe what you want, and AI builds a sortable, filterable spreadsheet from your files. No templates, no OCR rules, no manual data entry.

Metadata Views showing extracted fields from documents in a searchable grid
Video thumbnail: See Metadata Views in action

Video guide

See Metadata Views in action

Watch how to extract structured data from any document in minutes.

Beyond OCR

Extract what other tools can't even see

Traditional IDP tools need rigid templates and only handle clearly printed fields. Metadata Views extracts structured data, handwritten notes, and even subjective judgments that require reading between the lines.

Reads like a human

Pulls handwritten data, inferred judgments, and loosely structured fields — not just perfectly formatted values.

Every file type

PDFs, images, Word docs, spreadsheets, presentations, scanned pages. If Fastio can read it, Views can extract from it.

Incremental by design

Add new columns without reprocessing. Re-extract specific fields on demand when files change.

Contract values, sentiment scores, handwritten totals, or property features. If a human could read it, AI can extract it.

What Views replace

The end of templated extraction

Three tired workflows that Views quietly retires.

The old way

Traditional IDP tools

  • Rigid per-document templates
  • Breaks on new layouts
  • Weeks to onboard a doc type
The old way

Manual spreadsheets

  • Data-entry bottleneck
  • Silent human error
  • Stale the day you finish
The old way

Custom scripts

  • OCR + regex duct tape
  • Maintenance burden
  • Brittle on edge cases

Views replace all three — with one sentence of description.

Describe it. AI finds the files.

Name your View and describe the content it should cover. AI scans your workspace, ranks candidates, and shows you what it found before anything else happens.

Describe things like

"Real estate purchase agreements and closing documents"
"Customer support transcripts and tickets"
"Product photography and marketing assets"

No tagging, no folders, no manual assignment. Gemini 2.5 Pro reads your files and classifies them.

Create New View dialog with name and description

AI designs your schema

Don't know what fields to extract? AI analyzes your matched files and suggests columns with types, descriptions, and real example values from your data. Edit, add, or remove anything before extraction.

  • 7 field types: Text, Integer, Decimal, Boolean, URL, JSON, Date & Time
  • Example values from your actual files, not generic placeholders
  • Refine suggestions with one click if the first pass isn't right

You control the schema. AI just gives you a head start.

AI-suggested columns with types and example values
Real example

From a folder of listings to a sortable database

A real estate brokerage drops a folder of property listings into Fastio. One View later, every listing is a queryable row.

Before

A folder of PDFs, scanned flyers, and agent-written markdown files. Some have clean tables, some are handwritten MLS sheets, some are photos of printed listings. There's no easy way to answer "show me every 3-bedroom listing under $500k with a pool."

listing-oak-street.pdf
mls-sheet-scan-047.jpg
notes-from-agent-call.md
open-house-flyer.pdf
+ 247 more files
After one View

"Real estate listings." That's the whole prompt. AI finds 251 matching files, suggests 9 columns, and extracts everything into a sortable grid. One handwritten field — listing agent — gets added manually.

Address City State Price Property Type Bedrooms Bathrooms Sq Ft Year Built Listing Agent

Now sortable, filterable, and ready for workflows.

Same pattern works for contracts, claims, receipts, research papers, or any other document type.

Your data, fully queryable

Extracted data isn't useful if you can't work with it. Sort, filter, and query across every field — then click any row to open the original document behind it. Your files become a live database, but you never lose the source.

Filter builder for any field

Toggle and reorder columns

Edit and re-extract inline

Questions your data can now answer

"Which contracts expire in the next 90 days?"
"Show me all invoices above $10,000 from Q3"
Filter builder for structured data queries
How it works

Four steps, no setup

From a messy folder to a queryable database in minutes.

01

Describe what you want

Name your View and write a one-sentence description. That's the whole setup.

Create new View dialog with description field
02

AI finds the files

Gemini 2.5 Pro scans your workspace and returns candidate matches for you to approve.

Preview of AI-matched files for the View
03

AI designs your schema

Typed columns with example values pulled from your real files. Accept, tweak, or rewrite.

AI-suggested columns with example values
04

Query your data

Sort, filter, edit inline, and re-extract single fields on demand. Your files are now a database.

Extracted metadata displayed as a sortable grid
Every document type

Built for every industry's documents

Teams across legal, insurance, media, and finance use Metadata Views to turn manual review processes into searchable knowledge.

Legal & Contracts

Extract effective dates, counterparties, renewal terms, and payment amounts from every agreement.

Insurance & Claims

Pull policy numbers, coverage limits, and expiration dates across your entire book.

Media & Creative

Tag thousands of photos with subjects, settings, brand mentions, and visual descriptions.

Finance & Accounting

Extract line items, totals, vendor names, and payment terms from invoices.

Built for AI agents too

The MCP server exposes Views programmatically. Agents can create schemas, match files, trigger extraction, and query results without a human in the loop.

  • preview-match AI-match files against a description
  • suggest-fields Get AI-suggested columns with example values
  • extract-all Async batch extraction with job polling

Pair with Ripley for conversational Q&A over extracted fields, or trigger workflows automatically when new files land.

AI Processing Jobs showing extraction progress
Available on every plan

Start extracting on the free plan

Every plan includes Metadata Views. Start with 10 custom columns per View on free through Pro, or 50 on Business. No credit card required to begin.

Free to start

Create Views and extract data on the free plan. Upgrade when you need more columns or higher file caps.

Your data stays yours

Extracted data lives in your workspace. No shared models, no leaked training data.

Extraction in seconds

Per-file extraction typically completes in seconds. Batch jobs run async with real-time progress.

Your files already have the answers. Make them queryable.

Create your first View in under a minute. 50 GB free, no credit card required.