The skin report turns into a ready deck in minutes
The problem
The skin report had to be read and rewritten by hand into a patient presentation, one report at a time.
The solution
A Telegram bot takes the report link: a scraper pulls the data, AI turns it into a summary and treatment plan, and the system builds a ready-to-share Google Slides deck on its own.
(opens in a new tab)How it went
An aesthetic medicine practice gets a technical skin-analysis printout from the medical device for every patient: data on pores, spots, wrinkles, texture. Before this project, turning that into something to hand the patient, readable and with a treatment plan, meant reading the report and rebuilding it by hand in a presentation.
We built a system that starts from a simple Telegram message: staff paste the patient's report link. From there, everything happens automatically: a scraper reads and extracts the raw report data, four AI agents in sequence turn it into a plain-language skin analysis, a recommended treatment plan, and a morning/evening skincare routine. The system generates a Google Slides presentation from a template, complete with a QR code linking back to the original report, and sends the finished presentation link straight back on Telegram.
The whole pipeline, from data extraction to the finished deck, runs in 1-3 minutes. The system is self-hosted on the practice's own infrastructure, with OAuth 2.0 for Google Slides and prompts and template that can be edited without touching the code.