AI Hackathon SFxHamburg Coderabbit x Windsurf Christmas edition
$ Sponsors.log
[DIAMOND] 5
$ Projects.log (28)
Check out the amazing projects built during this event
VoiceOps
# VoiceOps **Amir Mirmehrkar** **VoiceOps AI** **Voice-First Incident Ingestion & Compliance Review for Production Services** --- ## Overview VoiceOps is an enterprise-ready FastAPI service that transforms voice incident reports into structured, production-grade JSON incidents. It enables teams to report incidents via voice (phone, web, mobile) and automatically converts them into validated, schema-compliant incident records ready for integration with Jira, PagerDuty, and other incident management tools. ### Core Capabilities - **Voice-First Input**: Accepts voice reports via VAPI (phone, web, mobile) - **AI-Powered Structuring**: LLM converts voice transcripts into structured JSON incidents - **Strict Schema Validation**: JSON Schema 2020-12 with `additionalProperties: false` for production safety - **Deterministic Severity**: Rule-based severity classification (sev1-sev4) - auditable and testable - **PII Safety**: Real-time PII (Personally Identifiable Information) detection and redaction for GDPR/HIPAA compliance - **Secure Development**: Integration with CodeRabbit for AI-assisted code and schema reviews --- ## The Problem Modern engineering teams struggle with: 1. **Time Pressure**: When incidents occur, operators don't have time to fill out forms 2. **Inconsistency**: Subjective severity scoring during high-stress moments leads to misclassification 3. **Compliance Risks**: Unintentional PII exposure in logs and error messages violates GDPR/HIPAA 4. **Slow Triage**: Manual review cycles delay critical fixes and increase MTTR (Mean Time To Repair) 5. **Unstructured Data**: Voice reports are lost or poorly documented, making post-incident analysis difficult --- ## The Solution VoiceOps introduces a voice-first incident ingestion layer that acts as a bridge between voice reports and incident management systems: 1. **Voice Ingestion**: Accepts voice input via VAPI (phone calls, web interface, mobile app) 2. **AI Structuring**: VAPI agent asks exactly 4 questions and outputs schema-valid JSON directly 3. **Validation**: Strict JSON Schema validation ensures production-ready output 4. **Severity Scoring**: Deterministic, rule-based severity classification (not AI guessing) 5. **PII Redaction**: Automatic detection and redaction of PII before storage 6. **Integration Ready**: Webhook delivery to Jira, PagerDuty, SIEM systems 7. **Feedback Loop**: Uses CodeRabbit to validate schema changes and generate test suggestions directly on Pull Requests --- ## Tech Stack - **Backend**: Python 3.11+, FastAPI, Pydantic - **Voice Processing**: VAPI (Voice API) for voice-to-transcript conversion - **AI/LLM**: OpenAI / Anthropic for transcript-to-JSON structuring - **Validation**: JSON Schema 2020-12 with jsonschema library - **AI/LLM Tools**: CodeRabbit (Security & PR Review), Windsurf/Cursor (Agentic Development) - **Testing**: Pytest (Unit testing & Schema validation with table-driven tests) --- ## Data Interface ### Example Input (POST /api/v1/incidents) Voice transcript from VAPI webhook: ```json { "type": "end-of-call", "call": { "id": "call_abc123", "transcript": "Production API is completely down. All services offline. Started at 6 PM. About 1200 users affected. This is critical." } } ``` ### Example Output ```json { "schema_version": "1.0.0", "incident_id": "f9847182-1827-40c1-988f-088f329c395b", "title": "Production API is completely down. All services offline.", "summary": "Production API is completely down. All services offline. Started at 6 PM. About 1200 users affected. This is critical.", "category": "service_outage", "severity": "sev1", "confidence": 0.85, "status": "new", "impact": { "services_down": true, "users_affected_estimate": 1200 }, "systems": [ { "name": "production-api", "environment": "production" } ], "pii": { "contains_pii": false, "redaction_applied": false }, "source": { "channel": "voice", "vendor": "vapi", "call_id": "call_abc123" }, "detected_at": "2025-01-12T18:00:00Z", "reported_at": "2025-01-12T18:05:00Z" } ``` --- ## AI Usage (Beyond the Hype) This project focuses on **Agentic Workflows** rather than simple API calls: ### CodeRabbit Integration We utilize CodeRabbit to perform deep-context reviews of incident-related PRs, identifying: - Security vulnerabilities (PII exposure, injection risks) - Edge cases in severity classification - Schema validation gaps - Test coverage improvements ### Windsurf / Cursor The core logic of this service was built using prompt-driven development, allowing for: - Rapid iteration during the hackathon - Refactoring with AI assistance - Schema-first design validation ### Human-in-the-Loop All AI suggestions are treated as "proposals"—they require explicit engineer review before being committed. This ensures: - Production safety - Compliance adherence - Auditability --- ## Key Concepts ### Severity Levels - **sev1 (Critical)**: Services down, security breach, patient safety risk - **sev2 (High)**: Severe degradation, high user impact (>100 users) - **sev3 (Medium)**: Moderate impact, limited scope - **sev4 (Low)**: Minor issues, cosmetic problems ### Category Types - `service_outage`: Complete service failure - `security_incident`: Security breach, unauthorized access - `performance_degradation`: Slow response, timeouts - `data_issue`: Data corruption, loss, or inconsistency - `patient_safety`: Healthcare-specific safety incidents - `other`: Unclassified incidents ### PII Detection Scans for and redacts: - Email addresses - Phone numbers (US, International, Iranian formats) - Credit card numbers - Social Security Numbers (SSN) - IP addresses (IPv4, IPv6) - Patient IDs - Names (heuristic-based) ### Confidence Score 0.0 to 1.0 based on: - Completeness of extracted data - Presence of required fields - PII detection (reduces confidence) - System identification accuracy --- ## Hackathon Goals & Future ### Completed ✅ - [x] Voice-first incident ingestion with VAPI - [x] LLM-powered transcript-to-JSON conversion - [x] Strict JSON Schema validation - [x] Deterministic severity classification - [x] PII detection and redaction - [x] CodeRabbit integration for PR reviews - [x] Table-driven tests for validation - [x] Production-ready error handling ### Future Roadmap 🚀 - [ ] Real-time VAPI webhook integration - [ ] Jira/PagerDuty webhook delivery - [ ] Historical trend analysis using Vector Databases - [ ] Multi-language support - [ ] Voice quality scoring - [ ] Compliance reporting dashboard - [ ] Slack integration for notifications --- ## How to Run ### Prerequisites - Python 3.11+ - VAPI API key (for voice processing) - OpenAI or Anthropic API key (for LLM structuring) ### Installation 1. **Install dependencies**: ```bash pip install -r requirements.txt ``` 2. **Set up environment variables**: Create `.env.local`: ```bash VAPI_API_KEY=your_vapi_key VAPI_PUBLIC_KEY=your_vapi_public_key OPENAI_API_KEY=your_openai_key # Optional ANTHROPIC_API_KEY=your_anthropic_key # Optional ``` 3. **Launch service**: ```bash uvicorn main:app --reload ``` 4. **Explore API**: Visit http://localhost:8000/docs for interactive API documentation ### Testing Run table-driven tests: ```bash python -m pytest tests/test_incident_table.py -v ``` ### Demo See `/demo` folder for: - Example incident JSON outputs - Sample voice transcripts - Demo flow walkthrough --- ## Project Structure ``` VoiceOps/ ├── api/ # Core API code │ ├── incident.py # Incident creation & processing │ ├── scoring.py # Confidence & severity calculation │ ├── schema.py # Schema validation │ ├── llm.py # LLM integration │ └── vapi_webhook.py # VAPI webhook handler ├── tests/ # Test files │ └── test_incident_table.py # Table-driven tests ├── schemas/ # JSON schemas │ └── incident.v1.json # Strict incident schema ├── prompts/ # LLM prompts │ ├── incident_prompt.txt │ └── repair_prompt.txt ├── demo/ # Demo materials ├── engineering/ # Technical documentation ├── coderabbit/ # CodeRabbit integration docs └── main.py # FastAPI application entry point ``` --- **Built for AI Hackathon SFxHamburg** With ❤️ using AI-assisted development (CodeRabbit, Windsurf, Cursor, VAPI)
CodeRabbitVapiWindsurfNeural Draft
A cover letter generator based on your personal work history, the job description of the company you are applying for, the company work as a whole and your motivation of past life for that particular job
QdrantGeminiDeepstory Voice Chat
A web-based interactive voice chat app that lets users have a casual conversation with a Witcher character (in-character by default), while grounding every answer in the text of the Witcher books via retrieval-augmented generation (RAG). The app also visualizes what the character is saying as an expandable “relationship explorer” (people, factions, kingdoms, alliances) with source-backed context from the books.
VapiWindsurfQdrantProofFoundery
# ProofFoundery MVP (Hackathon Build) ProofFoundery (“Build Your Own Product”) is a social product discovery platform for **physical products** where ideas are tested publicly, contributors take **stakes**, creators get analytics, and only market-validated products qualify for a **capital trigger** (status + admin action only; no real money flows). This repository contains a running end-to-end demo built with **Next.js**, **Supabase (Postgres)**, **Qdrant**, and **HuggingFace**. ## Primary goal Deliver running software (not slides) with an end-to-end demo: - Create - Publish - Feed interactions (including stake rules) - Threshold gate + Market Decision Card - Creator analytics dashboard - Profile stake history ## Non-goals (MVP) - No blockchain - No external social integrations - No stake marketplace - No complex manufacturing workflows - No real payments ## Tech stack - **Frontend + Backend**: Next.js (App Router) - **Relational DB**: Supabase Postgres - **Vector DB**: Qdrant - **Embeddings/AI**: HuggingFace Inference API (feature extraction) ## Core concepts ### Stake rules (MVP) - Users can place stakes on an idea as either: - `SUPPORT` - `SKEPTIC` - A product qualifies when: `support_total - skeptic_total >= NEXT_PUBLIC_STAKE_THRESHOLD` ### Capital trigger (MVP) There is **no real money flow**. “Capital trigger” is represented as a **status** and an **admin override** action. ## Data model (Supabase) Defined in `supabase/schema.sql`. - `users` - `id`, `handle`, `created_at` - `products` - `id`, `creator_id`, `title`, `description`, `feedback_prompt`, `status`, `created_at`, `published_at`, `qualified_at`, ... - `comments` - `id`, `product_id`, `user_id`, `body`, `created_at` - `stakes` - `id`, `product_id`, `user_id`, `type`, `amount`, `created_at` - `market_decisions` - `product_id`, `decision_card` (json), `admin_override`, `updated_at` - `product_stake_totals` (view) - `support_total`, `skeptic_total` aggregated per product ## Qdrant usage (non-decorative) Qdrant is used for two concrete platform features: 1) **Semantic discovery** in search/feed 2) **Grounded evidence retrieval** for analytics/insights (top evidence snippets) ### Collections - `product_ideas` - Points represent product-level text: title + description + feedbackPrompt + tags + targetUser + useContext - Payload includes: `productId`, `creatorId`, `status`, `createdAt`, `category` - `product_evidence` - Points represent comment-level evidence - Payload includes: `productId`, `commentId`, `userId`, `createdAt` ### Ingestion rules - On publish: upsert into `product_ideas` - On comment create: upsert into `product_evidence` - On edit: re-embed relevant product fields and upsert `product_ideas` ## Demo pages - `/` — Feed - `/create` — Create a draft idea - `/products/[id]` — Product detail (publish, stake, comment, decision card) - `/dashboard` — Creator analytics (by handle) - `/profile/[handle]` — Stake history - `/admin` — Admin override for Market Decision Card ## API endpoints (high level) ### Core - `POST /api/users/ensure` - `GET /api/feed` - `POST /api/products` - `GET /api/products/:id` - `POST /api/products/:id/publish` - `POST /api/products/:id/stakes` - `POST /api/products/:id/comments` - `GET /api/dashboard?handle=...` - `GET /api/profile/:handle` - `POST /api/admin/products/:id/override` (requires `x-admin-secret`) ### Qdrant-required (task) - `GET /api/search/products?q=...` (semantic search via Qdrant) - `GET /api/products/:id/similar` (nearest neighbors on `product_ideas`) - `GET /api/products/:id/evidence?q=...` (top-k evidence snippets from `product_evidence`, filtered by productId) ## Local setup 1) Install dependencies: ```bash npm install ``` 2) Create `.env.local` from `.env.local.example` and fill in values. 3) Create Supabase tables by running `supabase/schema.sql` in the Supabase SQL editor. 4) Start dev server: ```bash npm run dev ``` ## Demo walkthrough 1) Open `/` and set a **demo handle** (no auth) 2) Go to `/create` and create a draft 3) Open the product and **publish** it 4) Return to `/` to see it in the feed 5) Place stakes and add comments 6) Once qualified, Market Decision Card becomes visible 7) View creator analytics in `/dashboard` 8) View stake history in `/profile/[handle]` ## Security notes - Do **not** commit secrets. - Use `.env.local` for local development. - The Supabase **service role key** must remain server-side only.
WindsurfQdrantDAVINCI-AI
Da’vinci is an AI-Agency Startup focused on building enterprise-ready automation that actually ships into production, not just slideware. It targets support-heavy businesses that want to cut costs and response times without sacrificing compliance or customer experience. TARA_X1 is Da’vinci's modular multi‑agentic RAG customer service stack, designed to act as a 24/7 multilingual support team-in-a-box for enterprises. It combines specialized agents for intent routing, workflows, and retrieval‑augmented generation, so companies can deploy voice, chat, and email agents that stay grounded in their real documentation while scaling to thousands of conversations reliably
WindsurfQdrantDr. Voice
Online tool to get fast diagnosis and suggestions for treatment
CodeRabbitVapiWindsurfDr. Voice
Online tool to get fast diagnosis and suggestions for treatment
CodeRabbitVapiWindsurfHomevisit.ai
The project is to build an AI assistant for expats on the process of visiting houses for renting, the tool should generate real-time translations and voice output to power the communication. During the conversation, it should also suggest follow up questions based on the conversation.
VapiWindsurfQdrantOmnomnomnicon
Having a hard time deciding what you want to cook tonight? Your food is getting a second life in the fridge while you're sitting at Burger King? If you talk to the Omnomnomnicon nicely it'll provide you with a healthy recommendation out of your personal recipes. Input via VAPI: Describe what's in the fridge. Tell the Omnomnomnicon about your handwritten recipes. Tell the Omnomnomnicon how you're feeling today. Rate the recipe you cooked today. Recommendation engine via Qdrant: Recommend based on the metrics past usage of recipes, health score of recipes, available Ingredients.
VapiQdrantDr. Proptimus
46% of small and medium-sized businesses in Germany fail to meet the minimum standard of digitalization. Most of the rest are only at the beginning. This means their processes don’t live in systems, they live in people’s heads. When employees leave, knowledge leaves with them. That’s where Dr. Proptimus comes in. Using text and voice input, our AI captures business processes, makes them visible, and maps them digitally in a clear, structured way. It then analyzes these processes, identifies optimization potential, and improves them. The result: Clear processes. Less dependency on individuals. More efficiency and future readiness.
CodeRabbitWindsurfTLDRAW, Supabase, OpenAI ?, FramerDeskResearcher
DeskResearcher: Autonomous R&D Surveillance Engine 🚀 The Elevator Pitch R&D departments are drowning in information but starving for insights. DeskResearcher is an autonomous agentic pipeline that transforms the chaos of academic publishing into structured intelligence. Built during the hackathon using Windsurf and Qdrant, it monitors arXiv in real-time, performs deep semantic retrieval, and delivers AI-synthesized technical reports directly to your inbox. ✨ Key Features • Autonomous Ingestion: Real-time polling of arXiv for the latest technical breakthroughs. • Vectorial Intelligence: High-performance semantic search powered by Qdrant. • Instant Synthesis: Context-aware summaries using Groq (Llama 3.3 70B) for near-zero latency. • Automated Delivery: Daily or on-demand email reports via Resend. • Zero-Cost Stack: Engineered entirely using 100% free-tier APIs and open-source tools. 🛠️ Tech Stack • Orchestration: Windsurf (Agentic IDE) • Vector Database: Qdrant • Inference: Groq (Llama 3.3) • Email: Resend • Environment: Docker & Python 3.10+ 🏗️ Architecture User → Frontend → Research Engine (Agentic Loop) → Qdrant Vector Store ↓ Groq LLM Synthesis ↓ Resend Email Service
WindsurfQdrantStudyFlow
Create a clear study plan, run distraction-free focus sessions, and capture lecture notes in one place. Everything connects, what you plan, what you study, and what you learn, so you can see what works and improve over time.
WindsurfSchuldenKompass
The problem 2.9 million people in Germany who are heavily in debt wait between three months and two years for a debt counseling appointment. During this time, they fall into a state of fear and helplessness. The solution SchuldenKompass is a 24/7 AI coach that provides immediate help: Acute crisis: Empathetic chatbot reduces anxiety and provides concrete immediate measures Structure: Automatic recording of income, expenses, and debts Support: AI motivation coach throughout the entire repayment period Business model Freemium for users (B2C) + SaaS license for counseling centers (B2B2C). Impact Millions of people get immediate access to structure and emotional support—regardless of waiting lists.
WindsurfPerplexityShipSure
Large repositories receive many pull requests (PRs) every day. Some PRs introduce hidden risks and Manual review does not scale. We need a systematic, automated way to: Understand what a PR changes, Identify its risk surface, Enforce evidence-based validation before merge and show all the risks to the reviewer. ShipSure let's you ship with confident.
CodeRabbitCallSensei
CallSensei is an AI-powered real-time emotional intelligence layer for customer support calls. It analyzes the caller’s mood and communication style from the very first sentence—capturing tone, pacing, and vocabulary—and instantly prepares the support agent with tailored guidance inside the CRM. As the conversation unfolds, CallSensei continues to monitor emotional shifts and delivers subtle, live coaching on tone, pace, and approach. The agent stays fully in control, while CallSensei acts like a behind-the-scenes mentor that helps resolve issues faster, reduce escalations, and create smoother, more human conversations.
VapiWindsurfMindflayer
Our scarce attention is our most valueable asset and tons of adversaries are constantly trying to hijack it. We present the semantic content bouncer (named Mindflayer) for social media posts for the internet. X feeds us its feed. But we own the computer. Put an end to triggering posts so we can finally find our peace.
CodeRabbitWindsurfSentryMyWebsite
Project demo: https://parutkin.com/mywebsite Your Portfolio, Without the Hassle Drop your photos. Describe your style. Get a beautiful website in minutes. No coding required. Perfect for photographers, stylists, and creatives. A PHP-based portfolio website builder with AI-powered content generation.
Join Our Next Event
Don't miss out on future events. Sign up to stay updated on upcoming hackathons and meetups.
View All Events