Jerry King Deveza@Kermit

The Challenge As software architectures grow in complexity, a costly disconnect emerges between high-level architectural intent and actual code implementations. Feature plans, architecture decision records (ADRs), and design specifications are traditionally trapped in static documentation, wikis, or planning tickets that quickly become outdated. When engineering teams open Pull Requests, human code reviewers suffer from review fatigue, often missing subtle architectural drift, unexpected blast-radius regressions, unapproved dependencies, or security vulnerabilities before merging. Our Solution LooPR is an AI-driven architectural governance and continuous verification platform designed to bridge the gap between feature planning and code implementation. LooPR formalizes design intent into structured, machine-verifiable Architectural Contracts and continuously audits incoming GitHub Pull Requests directly against those contracts to prevent architectural decay and technical debt. Target User LooPR is built for Software Architects, Tech Leads, Engineering Managers, and Full-Stack Development Teams building complex web applications, microservices, or enterprise codebases where architectural integrity, consistency, and velocity are mission-critical. How Users Interact with LooPR 1. Repository Integration: Users connect their GitHub repositories through secure OAuth authentication. 2. Feature Planning: Architects and developers define feature specifications in natural language. LooPR analyzes repository structure and generates an enforceable Architectural Contract detailing affected components, boundaries, expected schemas, and security requirements. Pull Request Audit: When a developer opens a PR, LooPR fetches the real-time git diff and runs its automated Review Engine against the associated contract. 4. Inspection & Governance: Reviewers inspect an interactive dashboard highlighting Intent Drift, blast radius risk, and security impacts, and can export compliant audit dossiers directly to their workstation. What Makes It Creative & Unique Unlike traditional static analysis tools or linters that only inspect syntax, and unlike generic AI code reviewers that lack system context, LooPR introduces the Architectural Contract paradigm: 1. Intent Drift Detection: Evaluates semantic alignment between what was planned and what was actually coded. 2. Closed-Loop Governance: Unifies the planning phase (pre-code) with the review phase (pre-merge) into a single auditable lifecycle. 3. Architectural Blast Radius Assessment: Dynamically maps which subsystems, modules, or services are exposed to unintended side effects. Effectiveness in Addressing the Issue LooPR eliminates the subjective guesswork and review blind spots that plague modern engineering teams. By anchoring AI evaluations to pre-approved, repository-aware architectural contracts, LooPR catches architectural violations, scope creep, and dangerous design departures before code reaches production—saving hundreds of hours in refactoring, minimizing regression risks, and preserving codebase health without slowing development velocity.

NATS (Notes-to-Action Task Synthesizer) is an AI-powered engineering intent orchestration platform that bridges the gap between human communication and autonomous code modification. The system transforms raw meeting transcripts and project notes into highly structured, context-aware engineering instructions specifically designed for IBM Bob. Built with a Fastify backend and React frontend, NATS leverages IBM Fireworks AI Speech-to-Text for audio transcription and IBM Watsonx.ai for intelligent intent extraction. The platform analyzes conversations to generate comprehensive system blueprints, risk assessments, affected file mappings, and implementation sequences. It automatically creates GitHub issues with detailed acceptance criteria and produces ready-to-use prompts for IBM Bob. Key features include interactive task management, real-time AI chatbot assistance for architecture discussions, GitHub OAuth integration for seamless issue creation, and a developer-focused dark mode interface. The system supports both text and audio input, making it ideal for converting meeting recordings into actionable development plans. NATS streamlines the workflow from ideation to implementation, ensuring that autonomous coding agents receive precise, well-structured instructions that maintain project context and technical accuracy.

💻 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

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.

Build solutions that improve how software is built. Work with an AI that understands your codebase, helping you reduce repetitive work and build with real context. ⏳ Build your project in 48 hours. 🚀 Get hands-on with IBM Bob and explore how AI fits into real development workflows before it becomes standard. 💡 Build tools and workflows that developers would actually use. ⭐ Learn directly from experts throughout the event. 🤝 Join a team or build solo. 💰 Prize pool: $10,000 🧑🏻‍💻 Register before the Kick-Off Stream and start building with Bob.