Edit
Automate document modifications and form filling using natural language instructions.
The Edit module allows you to programmatically modify documents and fill out forms by providing natural language instructions or structured data. By providing a source document and a set of edits, the AI engine maps your instructions to the correct fields and returns a newly generated, populated document.
┌─────────────────┐ ┌──────────────────────┐ ┌─────────────────┐
│ Source Document │ ────► │ Edit Engine │ ────► │ Modified File │
│ (Blank Form, │ │ + Instructions │ │ (Populated PDF/ │
│ Contract, etc.) │ │ (e.g., "Fill name") │ │ DOCX) │
└─────────────────┘ └──────────────────────┘ └─────────────────┘- Automated Form Filling: Instantly populate tax forms, insurance applications, or legal contracts without manual data entry.
- Natural Language Instructions: Describe the changes you want to make in plain English (e.g., "Set the effective date to Jan 1, 2026").
- High-Fidelity Output: The system returns a downloadable, modified version of the original file. Supported formats for editing include PDF and DOCX. The resulting file seamlessly applies your changes while preserving the original layout.
🏗️ Configuration
The Edit module is defined within the editConfig block. You provide the instructions to guide the AI on what fields to fill or modify.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
instructions | string | Yes | Natural language instructions detailing the edits to apply. |
llmId | UUID | No | Reference to a pre-saved LLM configuration ID. |
llmConfig | object | No | Inline LLM configuration overrides. |
🛠️ Edit Operations
Editing is typically performed as part of a stateless process run. For a detailed technical reference of every field and parameter, see the API Process Reference.
Execute an Edit Run
To modify documents, submit a process request to your workspace with an editConfig.
curl -X POST "https://api.axelered.com/v1/w/{workspace_id}/process" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"config": {
"editConfig": {
"instructions": "Fill in the applicant name as Jane Doe and set the date to 2026-05-25."
}
},
"files": [
{
"url": "https://example.com/blank_form.pdf"
}
]
}'The modified document will be available as a downloadable file via the editUrl returned in the task documents list once the run reaches a completed state.
Read & List Results
To track the status of your edit tasks and retrieve the modified files, use the following endpoints:
- List Process Runs: Retrieve all process runs within your workspace.
- Read Process Run: Fetch the current status and result links for a specific
run_id.