Bring Files Into the Agent Conversation: OCR Support in Boomi Agentstudio Now Available

by Karina Kwok
Published Jul 30, 2026

Key Takeaways

  • Boomi agents now accept files and images directly, extracting structured data without manual processing or separate OCR tools
  • Document-heavy processes like contract onboarding can now be automated and completed in seconds instead of requiring hours of manual work
  • Teams can redirect time previously spent on manual data extraction toward higher-impact, strategic business activities

Much of the business lives in documents. Think about invoices and contracts in PDFs, metrics in spreadsheets, and information captured in screenshots. Frustratingly, the data you need is right there, but getting it into a system that could act on it meant either a separate Optical Character Recognition (OCR) tool or doing it manually by hand. But now, transferring and acting on that data can be done with Boomi agents.

Agents in Boomi Agentstudio now accept files natively. Hand an agent a document or image directly right in the chat window, and let it do the work from there.

More Automations, Fewer Manual Hours

The data trapped in your documents now becomes something your agents can act on. Whether it’s an invoice, contract, spreadsheet, or scanned form, a Boomi agent can take them in and pull out the structured data you need. The work of reading, extracting, and passing information downstream happens inside a single agentic flow. But that’s not all. For files from upstream systems (such as invoices from a file server), route them directly to a structured agent using the Agent step in your integration process.

Images are also included. Agents can now analyze what they see from screenshots, diagrams, photos, and image-based PDFs, unlocking new automation capabilities.

See it in Action: Contract Onboarding

Contract onboarding involves taking a newly signed contract, for example a Master Services Agreement, and getting all of the important information into your business systems. In practice, this is slow and manual work. Someone reads the contract, transcribes the details by hand, and reconciles them against existing records to avoid duplicates. But let’s see how an agent can complete contract onboarding in a matter of seconds.

An agent can read the document, extract every piece of information it finds, and capture the commercial terms down to the annual contract value. Then it checks against the golden record, flags as a net-new subsidiary from an existing customer, and submits for matching. One PDF goes in, and a clean, governed set of records comes out.

This changes what your agents can take off your plate and lets you focus on higher-impact work. Document-heavy processes that once took hours of manual handling now move in a fraction of the time. Automations that were out of reach become part of how you work every day. More importantly, people who spent their days pulling numbers off invoices get that time back for the work only they can do.

Want to learn more? Explore Boomi Agentstudio today.