·1 min read
Welcome — what I'm writing about
Notes on shipping AI systems, RAG, agents, and the boring full-stack work that makes them production-grade.
This blog is where I'll write about the parts of AI engineering that don't fit into talks or tweets. Less hype, more production reality — what breaks, what scales, and what's worth your time.
What you'll find here
- RAG and retrieval — chunking, hybrid search, evaluation harnesses, observability.
- LLM agents — tool use, retries, failure modes, when not to use an agent.
- Cost-aware engineering — caching, model routing, prompt compression, when fine-tuning earns its keep.
- Full-stack glue — the unglamorous infra (queues, idempotency, schemas, auth) that production AI sits on.
What I won't be writing about
- Pure prompt engineering tips that age out in a month.
- Generic "10 best LLM tools" listicles.
- Hype takes on AGI or the model release cycle.
If you want to follow along, the RSS feed is the most reliable channel. Otherwise, you can find me on LinkedIn and GitHub.
More posts coming soon.