Team Idea
Building an autonomous "screen-to-action" browser agent that watches a webpage and completes real tasks on its own, filling forms, navigating sites, scraping and summarizing info that is powered by an LLM served on AMD Developer Cloud. Frontend shows a live "reasoning trace" so you can watch it think and act step by step.
Looking for: a backend/AI teammate comfortable with LLM tool-calling and Playwright/Puppeteer automation, and/or anyone who wants to help with prompt design, testing, or the demo pitch. I'm covering the frontend/dashboard side.
Team Members
Unknown Hacker
ahmedhuzaifa009840658
Submission
Team Leader hasn't made a submission yet