Field notes
Field notes from engineers who ship AI every week
Practical perspectives on AI strategy, model deployment, GenAI architecture, and what is actually working in production. Written for builders, with the rough edges left in.
- Engineering
- Research
- Industry
- Tutorials
- Case Studies
What we write about
Three threads, written for builders
Pick a thread. The posts inside the same thread compound, so reading two or three in order is more useful than one.
01Generative AI
Architecture, RAG, and copilots
How retrieval, evaluation, and tool-use actually play out in production, beyond the demo.
02Machine learning
Model lifecycle and ops
Training, evaluation, drift, and the unglamorous infra that keeps models honest after launch.
03Product engineering
Shipping AI inside real products
Frontend patterns, latency budgets, observability, the engineering layer most posts skip.
Field notes
Start here
Bring the messy version. That is the useful conversation.
An idea, a workflow that is eating your team's week, or a model that works in a notebook and nowhere else. Any of those is enough to start.
- A first roadmap on the call
- Not a brochure. What we would build first, what we would leave out, and why.
- Architecture and cost in plain English
- Where the model sits, what it touches, what it costs to run at your volume.
- The honest version
- If your data is not ready, or the use case does not need AI, we will tell you on the call.