Edit

Fill PDF Forms and Modify DOCX

Edit auto-detects fields or follows a reusable form schema, then returns the filled document. No mapping field IDs by hand, no template setup.

Try the API free Request a demo

Helping everyone from startups to Fortune 10 enterprises unlock their data.

Edit

Fill forms and modify documents with instructions

Definition: Edit writes data into documents. It fills text, checkbox, and dropdown fields in PDFs (with or without existing form widgets) and modifies content in DOCX files. You provide instructions in plain English and the model maps them to the right locations in the document.

Who it's for: Teams whose pipelines need to output a finished document, not just read one. No template needed. Edit can fill any PDF, even without form widgets. Works for tax forms (W-9, I-9, G-1145), insurance applications, legal contracts, government filings, and DOCX files at scale.

The problem it solves: Traditional form filling tools rely on exact bounding box templates that break as inputs change. Edit uses vision to read labels and context directly, so it works on any PDF or DOCX without pre-built templates.

Edit in the platform

How Edit connects to the rest of the platform

Endpoint

Use when

Output

How it works with Edit

/parseParse

Structured content from any document is needed for LLM or RAG use.

Structured chunks with typed blocks, bounding boxes, and confidence scores.

Reads the document. Parse is the upstream step before Edit writes.

/extractExtract

The fields to pull are defined and typed JSON is needed.

Schema-typed JSON with optional citations on every value.

Returns data as JSON. Extract feeds values into Edit.

/splitSplit

One file contains multiple logical documents or sections.

Page ranges for each section, with confidence scores.

Finds sections. Split page ranges can scope Edit calls.

/classifyClassify

Files need to be routed by type before processing.

Best-matching category with per-criterion confidence.

Identifies document type. Classify picks which Edit recipe to use.

/editEdit

A PDF form needs filling or a DOCX needs updating.

A downloadable edited file, plus a reusable form schema.

Read the Edit docs

Try out Edit in Studio or via the API.

Open Studio Request a demo

Where AI teams ship Edit

Tax forms, claims, contracts, reports

When your workflow needs to produce a finished document, Edit is the last step.

Tax & onboarding forms

Fill W-9s, I-9s, W-2s, G-1145s, and other standard forms from extracted values, without mapping field IDs by hand.

Insurance applications & claims

Populate ACORD apps, claim packets, and renewal forms from policy data. Handles checkboxes and dropdowns.

Legal & financial contracts

Insert counterparty details, monetary terms, and effective dates into MSAs, NDAs, and SOWs.

DOCX reports & proposals

Modify Word templates with extracted data. Highlighting shows reviewers exactly what changed.

Scanned PDFs without form widgets

Edit detects fields visually, so scanned PDFs without embedded form layers still get filled correctly.

Reusable schemas across batches

Build a form_schema in Studio once, then reuse it across thousands of the same form, roughly 3× faster than re-detecting fields each time.

Try out Edit in Studio or via the API.

Open Studio Request a demo

Why Edit

Why teams switch to Edit

01
Natural-language instructions, not field IDs
Write what to fill, not where. “The applicant's full name” still finds the right field when the form is revised or the ID is opaque.
02
Vision-based field detection
No embedded AcroForm required. Scans and widget-less PDFs still fill correctly.
03
Reusable schemas for batches
Pass a saved form_schema to skip detection: ~3× faster and more consistent across thousands of the same form.
04
Highlights changes in DOCX
Modified DOCX sections get highlighted so reviewers see exactly what changed.
05
Overflow pages for long values
enable_overflow_pages: true appends an extra page when a value is longer than the field. Nothing gets truncated silently.
06
Composable with the rest of the platform
Parse reads the document, Extract pulls values, Edit writes them back in.

How Edit works

How Edit works in three steps

STEP 01
Send file + instructions
Upload a PDF or DOCX, or point at a URL. Provide instructions in plain language or pass a reusable form schema.
POST /edit
STEP 02
Detect & map fields
Edit identifies fillable fields visually, then matches each one to your instructions using labels, hints, and headings.
vision + form_schema
STEP 03
Apply edits, return the file
Values are written into PDF fields or DOCX content. The response includes a downloadable URL for the finished file.
result.url

Read the full Edit reference in the docs

Built for production

Enterprise-ready from day one

SOC 2 Type II
HIPAA
Zero Data Retention
VPC · On-prem · Air-gapped
EU · AU regional endpoints
99.9%+ uptime SLA
Enterprise support

Visit the Trust Center

Try out Edit in Studio or via the API.

Open Studio Request a demo

The rest of the platform

What feeds Edit

/parse

Common questions about Edit

Document work starts here

Describe the values. Get the document back

Drop a form in Studio or hit the API with one call. No setup, no credit card.

Try the API free Request a demo

API

Industries

Resources

Natural-language instructions, not field IDs

Vision-based field detection

Reusable schemas for batches

Highlights changes in DOCX

Overflow pages for long values

Composable with the rest of the platform

Send file + instructions

Detect & map fields

Apply edits, return the file

Enterprise-ready from day one

Parse

Extract

Split

Classify

Studio