Javlon Baxtiyorov
Plate V  ·  Production system  ·  in production
V

Soffia — AI Academic Assistant

Presentations, papers and tests — generated in seconds, for 20K+ users.

Fig. 7 — Generation Engine: AI composing machine accepting prompts through authenticated inlets, driving a geared engine that outputs academic documents PROMPT GOOGLE TELEGRAM GENERATION ENGINE GOVERNOR DRIVE GEAR SLIDES PAPERS TESTS REPORTS OUTPUT MAIN 20K+ USERS fig. 7 — generation engine PROMPT INLET TO DOCUMENT OUTPUT
fig. — soffia — ai academic assistant

Abstract

soffia.uz — the AI academic assistant of the Soff ecosystem. It generates presentations, course papers, reports, tests and research documents in seconds, serving 20K+ users through a web platform and a Telegram bot, with Google and Telegram authentication.

The Problem

Turning a one-line prompt into a finished, correctly-formatted academic document is slow, heavy work — and users expect it in seconds, from a browser or from inside Telegram, without ever knowing what's happening underneath. Users forgive a spinner. They don't forgive a wrong document.

The System

FastAPI generation services wrap LLM and voice (STT/TTS) models, with NLP automation behind them. The slow generation runs as async jobs (Celery + Redis) so the API answers immediately; one engine is fronted by both a web platform and a Telegram bot. Google and Telegram OAuth keep sign-in friction near zero. The bot and the website are the same engine wearing two coats.

The Decisions

Generation never blocks a request — it's a job, with a status. One generation engine, many front doors (web, bot), so the product can meet students where they already are. Make the model's slowness the queue's problem, not the user's. Async isn't an optimisation here — it's the only honest design.

Specifications

20K+ usersGenerates in secondsFastAPI · LLM / AISTT / TTS · NLPCelery · RedisGoogle + Telegram authTelegram bot + web