Feil Jasper Doria@feil_jasper_doria648

TokenGate is a hybrid LLM router built for the AMD Developer Hackathon ACT II that dynamically routes user prompts between a lightweight local model (Ollama/llama3.2:1b-instruct-q4_K_M) and paid cloud APIs (Fireworks AI) to maximize accuracy while minimizing token costs... The workflow operates through a multi-stage decision pipeline. Incoming prompts are first classified by category (code, math, reasoning, creative, factual Q&A, general) using keyword analysis. Most tasks are initially sent to the local model, which returns structured responses with confidence scores. The system evaluates this confidence against a configurable threshold. For math and reasoning tasks, a self-consistency check re-runs the prompt at a different temperature — if the two answers disagree, the task escalates to the cloud. Tasks requiring long-form outputs bypass local inference entirely and go straight to the cloud... When escalation occurs, tasks are routed to specialized cloud models — code tasks to kimi-k2p7-code and general tasks to minimax-m3 — with budget guards preventing overspending. The system is containerized with Docker using a multi-stage build that bakes the compact local model into the image, keeping the compressed size under 800 MB for fast pull times within the hackathon's 10-minute constraint. It supports batch processing, an interactive CLI, and a Streamlit web UI. The scoring model rewards both accuracy and token efficiency, making this hybrid approach a strategic competitive advantage... Team: Feil Jasper Doria, Julianna Raine Lacaden, Francie Galapate, Vincent Rafael Fajardo.

My partner and I decided to go for the first track which is use e-commerce companies to webscrape and to give GTM insights using the information provided from their website. For this project, we used Alibaba as the company. For the two sites of Alibaba, we usedaThe system focuses on Alibaba as the target company. It collects real-time web data from Alibaba’s public pages, including the homepage and investor relations pages. The data pipeline first scrapes the web content using Bright Data Web Unlocker, then falls back to direct scraping if Bright Data access is restricted. After collecting the raw web content, the parser converts it into structured fields such as page topics, report titles, fiscal year, document links, and summary text. The parsed data is then passed to the analysis layer, which generates GTM insights such as market positioning, strategic priorities, sales recommendations, and high-priority business signals. A desktop UI was also added so users can run the homepage pipeline, investor pipeline, combined analysis, or formatted report without using the terminal. their homepage and their investor site. For our technology, we used bright data's web unlocker API for the web scraper, and for the AI we used Hugging Face API.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.

🌍 Hybrid Hackathon | 💻 Online Build: May 25–30,2026 | 📍 SF Onsite Finale: May 30–31,2026 We’ve unlocked the web for your AI. Now build what wasn’t possible before. Build AI agents with live web data, then join the SF onsite finale at Bright Data’s new Web Data Loft. 🚀 The onsite experience will take place during the opening of Bright Data’s new SF space, The Web Data Loft. 📍 On-site Venue (May 30–31): The Web Data Loft 625 2nd St, San Francisco, CA 🏆 $18,300 cash prize + Bright Data AI Startup Program opportunities 🍕 Free food, drinks, networking, workshops, mentorship, and live demos 🎁 Onsite attendees are automatically entered into a live giveaway for 4 × $100 Amazon gift cards. 🧑‍💻 Apply now to build AI agents powered by real-time web access.