LLMs
RAG, fine-tuning, evaluation and prompt engineering for real systems.
5 long reads · 82 minutes in total
Fine-Tuning vs RAG vs Prompting: A Decision Framework for Cost and Quality
Choose prompting, retrieval, fine-tuning, or a combination by separating knowledge from behavior—and measuring their full cost and quality trade-offs.
21 Nov 202613 min
LLM Interview Questions: Context Engineering and Trust Boundaries
A 12-question study guide to building reliable LLM contexts, resisting prompt injection, and keeping model-generated outputs inside application trust boundaries.
16 Nov 202614 min
Production RAG Pipeline: From Chunk Boundaries to Release Gates
A medium-scale AWS blueprint for building a production RAG pipeline, from document ingestion and hybrid retrieval to reranking, evaluation, and operational readiness.
10 Nov 202619 min
LLM Interview Questions: Evaluation and Release Gates
A 12-question study guide to measuring LLM quality, building trustworthy evaluations, and deciding when a prompt or model change is safe to ship.
4 Nov 202615 min
RAG for a Small Knowledge Base: pgvector Behind One API
A practical AWS blueprint for a small retrieval-augmented generation service: one API, PostgreSQL with pgvector, managed models, and an operational plan sized for a small team.
1 Nov 202621 min
Newsletter
Get new LLMs reads on Saturday.
The week’s new long reads on architecture, cloud and AI — with the diagrams left in. Delivered Saturday morning, no noise in between.