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.
Found 4 contracts expiring this quarter ($283,000 total). Flagged 4 overdue invoices totaling $51,450.
Contracts Q2
Video guide
See Metadata Views in action
Watch how to extract structured data from any document in minutes.
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.
Penalty amounts, policy exclusions, handwritten totals, or roof types. If a human could read it, AI can extract it.
The end of templated extraction
Three tired workflows that Views quietly retires.
Traditional IDP tools
- Rigid per-document templates
- Breaks on new layouts
- Weeks to onboard a doc type
Manual spreadsheets
- Data-entry bottleneck
- Silent human error
- Stale the day you finish
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
No tagging, no folders, no manual assignment. Gemini 2.5 Pro reads your files and classifies them.
See what will match before you run anything
Before a single field is extracted, preview-match shows you the exact files a View's description and schema will run across your workspace. Review the candidate list, deselect anything that shouldn't be there, then commit. Nothing is processed until you approve the set.
- Run the match against your whole workspace and see candidates ranked before extraction starts
- Tighten the description and re-preview until the file set is right, with no wasted extraction
- Approve the final set, then schema design and extraction run only on the files you confirmed
Confirm the match first. You never extract across files you haven't seen.
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.
From a folder of penalty notices to a sortable database
A property developer drops a folder of municipal penalty notices into Fastio. One View later, every notice is a queryable row.
Thousands of pages of scanned notices, stop-work orders, and zoning correspondence. Some are clean PDFs, some are photographed pages, and the penalty amount is often buried deep in the document. There's no easy way to answer "which sites have an open notice past its response deadline?"
"Municipal penalty notices." That's the whole prompt. AI matches the notices, suggests roughly 10 typed columns, and extracts every field across thousands of pages into one sortable grid. One loosely formatted field, case officer, gets added manually.
Now sortable, filterable, and ready for workflows.
Same pattern works for bank statements, insurance policies, job-site videos, 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
Find files by what's inside them
Once a field is extracted, it becomes something you can search on. Query files directly by their extracted values, with number ranges, date windows, and text matches, then click straight through to the source document behind every result.
"Every invoice where amount > 10,000"
"Contracts with renewal_date in the next 30 days"
"Penalty notices where response_deadline is past due"
This is the other half of Metadata Views. Extraction turns documents into typed fields. Search by value turns those fields into a way to pull up exactly the files you need, even across thousands of documents, without opening a single one.
Numeric and date fields compare and range. Text fields match. Every result links back to its original file.
Four steps, no setup
From a messy folder to a queryable database in minutes.
Describe what you want
Name your View and write a one-sentence description. That's the whole setup.
AI finds the files
Gemini 2.5 Pro scans your workspace and returns candidate matches for you to approve.
AI designs your schema
Typed columns with example values pulled from your real files. Accept, tweak, or rewrite.
Query your data
Sort, filter, edit inline, and re-extract single fields on demand. Your files are now a database.
Built for every industry's documents
Teams across property, insurance, field services, and finance use Metadata Views to turn manual review processes into searchable knowledge.
Legal & Compliance
Extract case numbers, property addresses, zoning, penalty amounts, and response deadlines from every municipal notice.
Insurance & Claims
Pull exclusions, endorsements, and form codes from every policy in your book.
Media & Creative
Tag every job-site video with equipment, project type, roof type, and whether the footage is aerial.
Finance & Accounting
Extract P&L line items by year, plus entity, period, balances, and deposits from bank statements.
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-matchAI-match files against a description -
suggest-fieldsGet AI-suggested columns with example values -
extract-allAsync batch extraction with job polling
Pair with Ripley or your own agent for conversational Q&A over extracted fields, or trigger workflows automatically when new files land.
Storage that scales with your documents
Every plan includes Metadata Views. Start on Solo with 1 TB of storage and scale to 50 TB on Growth. Every plan includes a 14-day trial so you can test real workspaces first.
Start on the Solo plan
Create Views and extract data on Solo with 1 TB of storage, then scale up as your library grows. Every plan includes a 14-day trial.
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. Start on the Solo plan with 1 TB of storage. Every plan includes a 14-day trial.