Process PDF, Word, and Excel files with AI
Process contracts, invoices, and reports without uploading them anywhere. Built-in skills extract, merge, and convert PDF, Word, Excel, and PowerPoint files on your machine.
- 1-click uninstall
- Cancel anytime
- Files never leave your computer
Impact
What changes
The same task, two ways — how it plays out by hand today, and what changes once Lapu AI runs it for you.
Without Lapu AI
A team lead spends 30 minutes uploading PDFs to an online extractor, copying text, pasting into a Word doc, and reformatting. Sensitive contracts go through a third-party web tool.
With Lapu AI
Lapu AI extracts text from all PDFs, merges the content, and generates the summary document — all locally, in under 5 minutes. No uploads, no third-party tools.
The challenge
Processing documents — extracting text from PDFs, converting formats, merging files — usually means uploading to a web service, installing single-purpose tools, or writing custom scripts. For sensitive documents like contracts, financial reports, or HR files, uploading to third-party services is a non-starter.
How Lapu AI solves this
Drop your PDFs, Word docs, spreadsheets, or slides on Lapu AI and tell it what you need: pull the text out, merge these contracts, turn this spreadsheet into a summary. It handles the format wrangling and saves the result where you want it. Nothing gets uploaded to a web tool, so even sensitive contracts and financial files stay on your computer.
Document processing runs locally through built-in skills. Files are not sent to third-party services.
Workflow
How it works
Point the agent at your documents
Tell Lapu AI which files to process. The agent reads the file metadata and uses the appropriate skill — PDF, DOCX, XLSX, or PPTX — based on the file type.
Describe the operation
Ask for what you need in plain language: 'Extract the text from these 5 invoices and combine them into a single summary document.' The agent activates the right skill and runs the operation.
Review and save the output
The agent produces the result — extracted text, merged PDF, new DOCX, or reformatted data — and writes it to your chosen location. You approve the file write before it happens.
Under the hood — for the technically curious
Lapu AI ships with built-in document skills for PDF, DOCX, XLSX, and PPTX, run as typed operations through its Skills Runtime: no third-party services, no uploads, no API keys. For scanned PDFs it can call a local OCR tool like Tesseract through the shell when one is installed.
Permissions it asks for
- Skill — to activate document processing skills (PDF, DOCX, XLSX, PPTX)
- Skill Operation — to run extraction, merge, and conversion operations
- File Read — to access source documents
- File Edit — to write output files (requires permission)
Each is permission-gated — Lapu AI asks before it runs.
Just ask
Say it in plain words
No commands to learn. Tell Lapu AI what you want the way you would tell a coworker.
You
Extract the text from all PDF files in ~/invoices/ and save each as a .txt file with the same name.
You
Merge these 3 PDF contracts into a single document in the order they are listed.
You
Read the data from quarterly-report.xlsx and create a summary document in Word format.
Ready to try this workflow?
Download Lapu AI and run it on your own machine. Free to start — see exactly what it looks like first.
- 1-click uninstall
- Cancel anytime
- Files never leave your computer
FAQ
Common questions
Which document formats are supported?
Lapu AI has built-in skills for PDF (text extraction and merging), DOCX (creation and text extraction), XLSX (spreadsheet operations), and PPTX (presentation operations). For other formats, the agent can use shell tools or Python scripts via sandbox execution.
Are my documents sent to the cloud?
Document processing runs locally through built-in skills. The files themselves are not uploaded anywhere. When the agent needs AI reasoning (e.g., to summarize extracted text), relevant context is sent to AI model providers — but the raw documents stay on your machine.
Can it handle scanned PDFs?
The built-in PDF skill extracts text from text-based PDFs. For scanned/image-based PDFs, the agent can use OCR tools if they are installed on your machine (like Tesseract), running them via the Shell tool.
Explore more
Related use cases
Desktop Automation
Stop copy-pasting between apps. The agent sees your screen, clicks buttons, fills forms, and moves data between applications — so you do not have to.
See how it worksDataData Processing
Describe the transformation you need in plain English. The agent writes and runs the Python script, shell pipeline, or Node job — you just approve and get clean output.
See how it worksProductivityFile Organization
500 files in your Downloads folder? The agent reads them, understands what they are, sorts them into labeled folders, and renames everything — in minutes, not hours.
See how it works