I am a B.Tech student at IILM University.
My strongest project so far is the Competitor Intelligence Engine.
I switched from Beautiful Soup to Playwright, which fixed the scraping issue.
After the fix, we were able to scrape 12–13 competitors for the company.
The engine combines HTTPX requests with Playwright browser rendering, stores data in PostgreSQL, serves it via a FastAPI backend, processes it with background workers, and visualizes results on a React dashboard. I can advise on scraper selection, automation workflow structuring, LLM integration, and debugging pipelines that return incorrect data. The source code lives at https://github.com/mostlyunstable/competitor-intelligence-engine.