AI and retrieval
- Mistral-embed Vectorization
- Supabase pgvector Vector store
- Two-pass chunking Low-resource retrieval
- RAG evaluation CI/CD quality gates
Capabilities
How I build AI products.
Not a list of logos. These are the tools I use to take an AI platform from idea to a deployed, tested production AI system.
Three layers, one job: shipping AI products end to end.
From idea to a product that is deployed, tested and used.
Build and deploy
- Astro Static sites
- TypeScript Type safety
- Python Pipelines
- Cloudflare Workers Edge deploy
Product and delivery
- OKRs Outcomes
- Structured discovery Diagnosis
- SAFe Scaling agile
- Figma, Miro, Jira Operating system
Building something in this space?
Let us build together