Okafor Charles@Wessfago

Bob Debug Pipeline is an AI-assisted developer workflow built around IBM Bob 2.0 that helps developers turn a failing test into an understood, validated fix. The problem we address is a common but time-consuming debugging workflow: developers must inspect failing tests, trace the underlying implementation, identify the root cause, determine the expected behavior, create or validate a regression test, implement a fix, and verify that the change does not break existing functionality. These steps can require repeated manual investigation and context switching. Our MVP demonstrates this workflow using a concrete Jest debugging scenario. The test project contains a getUserById(999) case where the test expects null, but the implementation returns undefined. IBM Bob investigates the relevant files, analyzes the failing behavior, identifies that JavaScript Array.find() returns undefined when no matching element is found, and determines that the implementation does not satisfy the test contract. The proposed minimal fix normalizes the missing result to null. IBM Bob then implements the fix in the relevant service file and runs the focused Jest test. The final validation confirms that both tests pass. We built a React/Vite frontend connected to an Express/TypeScript backend to present the workflow as a clear developer tool. Users can see the bug scenario, root-cause analysis, regression test, generated fix, validation result, and the next GitHub workflow step in one interface. The target users are developers who regularly debug failing tests and maintain existing codebases. The creative aspect of the project is combining IBM Bob's repository-aware investigation and implementation capabilities with a structured debugging pipeline that makes each stage visible and verifiable. The prototype demonstrates a practical workflow from failing test to validated fix, while keeping the debugging process understandable and reproducible.

Intelligent Packing Assistant is a voice-driven robotic packing prototype built by Team 15 for the Intel Bimanual VLA Manipulation with Multi-Modal Reasoning track. The system demonstrates how a natural-language packing instruction can be transformed into structured and executable robot actions. A user provides a spoken instruction, Speechmatics performs real-time speech-to-text, and the resulting instruction is processed by our Python/FastAPI backend. The backend extracts the relevant packing constraints and generates a structured packing plan. For the MVP scenario, the system works with three object types: Heavy, Normal, and Fragile. The generated plan explicitly assigns robotic actions and arms: the Heavy object uses a coordinated bimanual pick-and-place action with arm1 and arm2, while Normal and Fragile are handled by individual arms. The structured plan is exposed through a deployed FastAPI service on Render and connected to a Three.js simulation. The simulator visualizes the robot execution and demonstrates the coordinated two-arm manipulation required by the challenge. The demonstrated workflow is: Voice Command → Speech-to-Text → Instruction Understanding → Packing Plan → Robot Actions → Bimanual Execution → Final Placement The project focuses on building a practical end-to-end prototype that combines voice interaction, structured task planning, backend APIs, and robotic simulation within a modern AI infrastructure workflow.

DevFlow AI is an intelligent hybrid AI coding assistant designed to demonstrate the power of the AMD AI ecosystem by combining AMD GPU acceleration, ROCm, and Fireworks AI into a seamless developer experience. Unlike traditional cloud-only coding assistants, DevFlow AI follows a local-first, privacy-first architecture. Routine coding tasks such as code completion, bug detection, explanations, documentation generation, and optimization are processed locally on AMD GPUs using a fine-tuned lightweight language model accelerated by AMD ROCm. This provides significantly lower latency, improved privacy, reduced API costs, and the ability to work even with limited internet connectivity. For more computationally demanding tasks—such as complex debugging, architecture design, multi-file code analysis, and advanced reasoning—DevFlow AI intelligently routes requests to Fireworks AI, ensuring developers receive the capabilities of powerful cloud models only when necessary. This hybrid routing approach minimizes cloud dependency while maintaining high-quality AI assistance. The project also includes a Personalized Learning Engine that analyzes coding habits, identifies recurring mistakes, reviews Git commit history, and generates tailored recommendations to help developers continuously improve their programming skills. Instead of acting only as a chatbot, DevFlow AI serves as a long-term AI mentor that adapts to each developer's workflow. Key Features 🚀 AMD GPU accelerated local AI inference using ROCm ⚡ Hybrid routing between local AI models and Fireworks AI 🔒 Privacy-first architecture with local code processing 🐞 Intelligent bug detection and debugging assistance 💡 Real-time code explanations and optimization suggestions 📚 Personalized learning recommendations based on coding patterns 📈 GitHub commit analysis and developer insights 💰 Reduced cloud API costs through intelligent request routing 🖥️ Designed for future VS Code integration and developer workflows

Six Matches. One leaderboard. Build on AMD, earn points and compete for prizes.

🌎 Hybrid Hackathon | 💻 Online Build: 12-17 October 2026 | On-site phase: 17-18 October 2026 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. The AMD Developer Hackathon: ACT III is a hands-on event for developers, founders, engineers and builders who want to push what’s possible with AI on real infrastructure. 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.

🌎 Online Hackathon | 💻 Online Build: Sept 26 - Oct 5, 2026 A virtual, global hackathon. Build from anywhere in the world. Dark Factory is the official hackathon of WeAreDevelopers World Congress North America, presented by BAND, but you don't need to be in San Jose to take part. For one week, you build a software factory in BAND Desktop: a band of coding agents that plans work, implements it and checks its own results. 🎟️ Bonus for sign-ups: you are eligible for a free ticket to WeAreDevelopers World Congress North America in San Jose (Sep 23–25). If you do go, stop by the BAND booth: a surprise is waiting for you.

💻 Online Hackathon | ⏳ Build: 48 hours | 📅 September 25–27, 2026 The official IBM Bob 2.0 hackathon. Build what's next in AI-assisted development, alongside the developers and experts shaping it. ⭐ Get help from experts throughout the event 🤝 Join a team or build solo 💰 Prize pool: $12,000 🧑🏻‍💻 Register before the Kick-Off Stream to start building with Bob