OpenAI Hackathon Finalist
| 86k+ | 1,000+ | Finalist |
|---|---|---|
| production queries studied | users reached at Wonka | OpenAI Hackathon |
| LLM routing research | shipped AI products | built under pressure |
Customer-facing AI products and integrations used by 1,000+ people.
I work across product, engineering, and deployment: building integrations, agent infrastructure, and features shaped directly by customer workflows.
TypeScript · Python · MCP · LLM infrastructure
Client landing page for a professional painter in the Lille metro area.
Production site showcasing services, portfolio, and contact integration for a local painting contractor. Built with modern TypeScript stack for performance and conversion.
Next.js · TypeScript · SEO · Client work
Install work into your company — bounded missions on your stack.
Turn a repeating job into a supervised mission: test the deliverable, check sources and unknowns, then activate under your control. Vertical landing pages for hosts, creators, coaches, and more.
Next.js · TypeScript · SEO · CRO
A self-hosted voice-agent appliance for outbound sales teams.
Sales reps manage fleets of AI callers that qualify leads, update the CRM, and improve from each campaign. Every operator owns their SIP trunk, models, data, and costs instead of depending on a shared calling platform.
Bun · React · MCP · Pipecat · LiveKit SIP · Postgres
Turn niche research into ready-to-shoot video scripts.
Creator tooling that bridges research and production: identify trending topics, generate structured scripts, and prepare video content optimized for engagement. Built for creators who need repeatable workflows from insight to publish.
TypeScript · Next.js · fal · Creator tooling
Multi-objective routing for production LLM systems.
Routes each query according to performance, cost, latency, and environmental impact instead of relying on a single default model.
Developed from my ENSAM engineering thesis and validated against 86k+ production queries.
Python · FastAPI · LLM evaluation · multi-objective optimization
OpenAI Hackathon finalist — safe phone actions for software agents.
A local MCP lets Codex and other compatible agents turn a task into a real, consented phone call. Classification, preview, confirmation, strict allowlists, and structured results are part of the action contract.
Python · MCP · Twilio · Deepgram Voice Agent
| Project | What it explores |
|---|---|
| wonka-audit | Local AI usage audit CLI for Claude Code, Codex, Cursor and Git — track usage, costs, and patterns across your dev tools. |
| Bowimi MCP | MCP server for Bowimi field sales CRM — connect Claude to routes, locations, contacts, orders and operational workflows. |
| agent-secrets (private) | Store MCP server credentials in macOS Keychain — scan configs for plain-text secrets, migrate them to the keychain, and rewrite configs to reference them. |
| break-coach (private) | Take verified breaks during long Claude tasks — suggests pauses when Claude works, verifies you left the screen, learns what you do, and tracks progression. |
| Mirror | Local-first macOS workflow assistant that recognizes repeated work and prepares reviewable automation drafts without collecting screenshots, keystrokes, or page content. |
| signal-studio (private) | Signal processing and observability tooling for production systems. |
| sillon (private) | Operational cockpit for barbershops — appointments, clients, retention (coiffeurs-only positioning). |
| focusweekly (private) | Weekly focus planning and execution framework. |
| goji-hiring-mvp (private) | Hiring workflow MVP for candidate pipeline management. |
Boring · Chiant |
Computer-vision parking assistant combining control-vehicle detection, geofencing, and programmatic parking payment. |
| Gauntlet | Parallel AI-agent harness for evidence-backed QA, code review, security audits, and implementation loops. |
| Vulcan | Feature-shipping cockpit — agents, skills, and templates to turn specs into shipped product. |
| Forge | Local-first Life OS for morning execution, habits, training, focus, and personal progression. |
| Career OS | Native Mac workspace for application tracking, CV tailoring, interview preparation, and a live copilot. |
See the full portfolio at iamgabriel.xyz.
- LLM routing and evaluation;
- agent infrastructure that remains observable in production;
- integrations grounded in real operational workflows;
- working directly with users to turn vague needs into deployed systems.
Growing toward Forward Deployed Engineering: deep enough in the stack to build the system, close enough to users to know which system should be built.
See CODE_OF_CONDUCT.md and SUPPORT.md for contribution guidelines and how to reach out.