Rafael Varela@_VarelaRC

Research Crew V2 is a multi-agent AI system built with CrewAI that autonomously researches any technical topic and produces a comprehensive, structured report without any human intervention during execution. This project was developed as a hands-on learning experience during the AMD Developer Hackathon, with the goal of understanding how to architect, configure and run collaborative AI agent pipelines from scratch. The system is composed of two specialized AI agents that work sequentially. The first is a Researcher Agent, a senior research specialist that uses real-time web search powered by Serper to gather information from scientific articles, news, journals and reports about the given topic. The second is a Reporting Analyst Agent, which receives the researcher's findings and produces a polished, professional report including an executive summary, main sections with analysis and insights, and future recommendations. Both agents are powered by LLaMA 3.3 70B running on Groq, making inference extremely fast. For this hackathon submission, the crew was tasked with researching edge computing applied to embedded systems and IoT with ESP32, integrated with cloud platforms such as AWS, Google Cloud Platform and Microsoft Azure. The topic was chosen to reflect a real-world architecture vision of using low-cost microcontrollers at the edge with AI agents in the cloud handling reasoning, analysis and decision-making. This project was my first contact with AI agents. Starting from zero, not even knowing what an AI agent was, I went through the full journey of understanding the difference between a static LLM and an autonomous agent, configuring agents and tasks via YAML, connecting a real LLM provider to a multi-agent framework, debugging dependency conflicts and environment setup on Windows, and running a fully functional multi-agent pipeline end-to-end. The journey itself, from confusion to a working crew, is the real deliverable of this submission.

📅 May 11–19, 2026 • May 11 – 19: Online Build Phase. • May 18 (Hybrid Build Day – Online & Onsite) • May 19 (Demos & Awards – Online & Onsite) 🌍 Hybrid event. Join online from anywhere or build onsite at the venue. 🏆 Winners will be announced live on stage at the AI & Big Data Expo North America on May 19 📍 On-site Venue (May 18–19): San Jose McEnery Convention Center, CA, USA 🤝 Join solo or with a team. 🎟 FREE AI & Big Data Expo North America ticket included for participants that are able to join the on-site phase. 🏆Compete for a $10,000 prize pool 🧑‍💻 Apply now to design, prototype, and showcase enterprise-ready innovation.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.