tag
11 items · 7 projects · 4 feed items
Co-founded an end-to-end GenAI platform that automates the innovation workflow for Consumer Packaged Goods companies, from idea prototype through to production-ready concept. Full-stack React + Python + LLM integration, shipped to early customers.
An AI-powered Slack bot that reads a data-collection-plan document on Confluence, cross-references it against the live event registry and metrics catalog, optionally analyses a GitHub PR alongside, and posts a structured pass/fail review back into the thread. Multi-agent workflow with Agno + ChromaDB vector search + deterministic result caching.
Headless plugin giving any Vercel-AI-SDK-compatible LLM (Anthropic, OpenAI, Azure, Google) conversational control over a TomTom map. Contributed to design and implementation.
Two production Model Context Protocol servers giving AI agents structured access to TomTom APIs. Both open source, both authored end-to-end (TypeScript, design + impl + docs).
Production multi-agent system for traffic analytics, demoed by Product Management at CES 2026 Las Vegas. Five specialised agents (routing, route monitoring, junction analytics, area analysis, traffic volumes) orchestrated through Agno's Team abstraction, served over AG-UI v1.0 with persistent chat memory.
Full-stack AI app that takes an address and returns a comprehensive neighbourhood profile (POIs, accessibility, routing to key destinations, market signal, livability score) by orchestrating a multi-step agent workflow over the TomTom MCP servers. Hackathon project that showcases MCP usage.
A production agentic navigation system that turns natural-language queries ('find me a quiet café between my next two meetings') into structured plans grounded in real-time location data. Full-stack, React/Next.js + Python FastAPI + Azure OpenAI, with a RAG pipeline for semantic POI search and autonomous multi-step execution planning.
I needed a 2-minute walkthrough of a search system I'd just shipped. Instead of After Effects I wrote React components and prompted Claude. Here's what worked, what didn't, and the small list of habits I picked up.
Most agent evals measure the wrong thing. Output quality alone misses 80% of production failure modes. The five eval categories I now run on every agentic system, the LLM-as-judge gotchas, and how to ship a useful eval harness in a week.
Tool naming, description writing, argument schemas, error envelopes, idempotency. Lessons from authoring two production MCP servers, with the patterns I now reach for and the mistakes I've stopped making.
Counter-narrative to 'agents everywhere'. Multi-agent systems pay a real latency, complexity, and observability cost. Here's the decision framework I use to decide whether to split, and three concrete cases where a single call beats N agents in a graph.