Articles

Notes from building real things

Web, React and Next.js, AI and RAG, and mobile. Written from production work, not tutorials about tutorials.

RAG, Fine-Tune, or Just Prompt? A 2026 Decision Tree for Million-Token Context Windows

Cheaper long context in 2026 broke the old always-RAG advice. Here is the decision tree I use: when full-context prompting beats a pipeline, when RAG is mandatory, when fine-tuning earns its keep, plus the hybrid stack and a cost and latency comparison.

Jul 10, 2026· 9 min read

RAG, Fine-Tune, or Just Prompt? A 2026 Decision Tree for Million-Token Context Windows - article cover

RAG in Practice

Adding Semantic Search to an Existing SaaS in a Weekend: pgvector Before You Reach for Pinecone

If your SaaS already runs on Postgres, you can add real semantic search in a weekend with pgvector and one Next.js route, no second database. Here is the embed-on-write migration, the HNSW query, a semantic cache, and the vector count where Pinecone or Milvus actually starts to make sense.

Jun 25· 9 min read

Building something similar?

I take on a few projects at a time: web apps, AI features, and mobile. Tell me what you are working on.

Start a conversation