maestro-automate
latest
false
Maestro Automate user guide
- Get started
- Build
- Deploy and run
- Examples
- Reference
Document processing
Dedicated canvas nodes that apply UiPath document intelligence: extraction, summarization, and more as discrete steps in a process.
Document processing nodes bring UiPath document intelligence directly onto the canvas as discrete, business-oriented steps. Each node represents one operation — extract structured fields, synthesize a long document — without requiring you to wire up a separate agent or understand the underlying model technology.
The nodes are in the Document (Preview) category of the Add node panel.
Available nodes
| Node | What it does |
|---|---|
| Extract | Pulls typed fields from a document using an Intelligent Xtraction and Processing (IXP) extraction model, either an existing model or a new one that you create in the node. Use when you need structured data — invoice totals, form values, named fields — returned in a typed shape for downstream nodes to act on. |
| Summarize document | Synthesizes across a document (up to 1,000 pages) and returns a grounded answer with citations. Use when the next step needs a reasoned answer or summary, not a fixed schema of fields. |
How document processing nodes differ from agent tools
Summarize also exists as a built-in agent tool that attaches to an Autonomous Agent. The distinction is where the decision is made:
- Document processing node — the step is deterministic. The workflow always calls Extract or Summarize at that point in the process, with the inputs you configure.
- Agent tool — the agent decides when to call the tool while reasoning. Use the Summarize agent tool when an Autonomous Agent needs to synthesize documents as part of broader open-ended reasoning.
Next steps
- Extract
- Summarize
- Summarize agent tool
- Autonomous Agent
- Community: ask questions and share workflows with other builders on the UiPath Forum.