Working with PDFs
Published March 3, 2026 · Last updated June 24, 2026 · 2 min read
Upload a PDF to your project and the agent can read it — extract text, answer questions about the contents, summarize sections, or pull data into a sheet. No manual copy-pasting required.
Upload a PDF
Drop the file directly into the chat alongside your request — the agent picks it up immediately. You can also click the paperclip icon in the chat input to browse and select a file, or click + in the toolbar and select Upload file to add a PDF without starting a conversation. Uploaded PDFs appear in the Files panel in the right sidebar.
What the Agent Can Do
Once a PDF is in your project, the agent reads the full document — text, tables, and layout. You can ask it to extract data from a table into a workbook (Extract the data table from page 3 and put it in a sheet), summarize at any level (What are the main findings in this report?), answer targeted questions without reading the whole thing (What’s the termination clause in this contract?), or highlight matching passages in the PDF viewer (Highlight all the liability clauses in this contract).
Be specific with your prompts. “Summarize this PDF” works, but “Summarize the risk factors section in three bullet points” works better. If you know the data is on a specific page, say so.
What to Expect
- Scanned PDFs (image-only, no selectable text) are harder to work with. PDFs with selectable text give the most reliable results.
- Large PDFs (100+ pages) may take a moment longer to process. The agent still reads the full document.
- Password-protected PDFs need to be unlocked before uploading. Obvious can’t open encrypted files.
Related articles
- Uploading & Managing Files — getting files into your project and organizing them.
- Files & Media Overview — how all file types work in Obvious.