Skip to main content
Uploading files is the most common way to train an agent. Use it for manuals, policies, product guides, reports, and any document your team already has.

​
Prerequisites

  • An agent (see Create an agent).
  • A supported file: PDF, DOCX, or TXT.
  • Enough credits to process the document (large files cost more — see Credits).

​
Upload a file

1

Open the Knowledge Base

In the agent sidebar, go to Expertise → Knowledge Base.
2

Open the Files tab

Select New Knowledge Item, then open the Files tab.
3

Select your document

Pick a PDF, DOCX, or TXT file from your computer. You can add more than one.
4

Start processing

Confirm the upload. The source appears in your list with a Processing status while it’s indexed.
5

Wait for Completed

Once the status turns Completed, the document is live and your agent can answer from it.
The Files tab of New Knowledge Item with a document selected.

​
Supported files & limits

Scanned PDFs (images of text) extract less reliably than digital PDFs. If a scanned document indexes poorly, convert it to text first or add the key points as Q&A pairs.

​
Tips

  • Give files descriptive names — they help you manage sources later.
  • Split very large manuals into logical documents (e.g. one per chapter) so retrieval stays precise.
  • Re-upload or reprocess when the underlying document changes.

​
Troubleshooting

Large or image-heavy files take longer. Give it a few minutes. If it stays stuck or turns Failed, reprocess the source.
Confirm the source shows Completed. If it does, the content may not match how the question is phrased — try adding a Q&A pair for that question, or upload supporting material.
Check the file type (PDF, DOCX, TXT only) and that the file isn’t corrupted. Re-export it and try again.

Add a website

Add a Q&A

Manage & reprocess sources

Test your agent