AI and retrieval
- Mistral-embed Vectorization
- Supabase pgvector Vector store
- Two-pass chunking Low-resource retrieval
- RAG evaluation CI/CD quality gates
Tech stack
How I build AI products.
Not a list of logos. These are the tools I actually use to take an AI product from idea to deployed, tested system. Three layers, one hub.
Hub
Shipping AI products end to end
From idea to deployed, tested, real
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