Hey HN! We're Dudu and Topaz from Vespper. Vespper is an MCP that lets AI agents efficiently edit Word documents, powered by our fine-tuned model. It's currently 3× faster, 2× cheaper and more accurate than the closest alternative.

We came to work on this problem after spending a year building an AI document editor for pharma companies. Before that, Topaz was a senior SWE at Snyk, working on distributed systems, and Dudu was a deep learning engineer at Viz.ai, building computer vision models for stroke detection. Our editor helped pharma companies generate regulatory documents (e.g. CSRs) to speed up their submissions.

AI agents aren't great at editing Word documents. A Word document is a zip file of verbose XML files following the OOXML spec. Even 'small' changes require backflips. This makes editing the zip directly a bad idea for agents because they burn a lot of time + tokens on these mechanics.

That's when we shifted our focus. We designed an MCP that lets agents edit Word docs as if they were editing HTML. The agent receives HTML, makes find-and-replace edits, and we reconcile those edits back into the original .docx file. After an agent sends us an edit request, we apply it to the original file, preserving fidelity.