Category
AI & Agents
4 posts in this category.
Building AI agents with Claude tool use in production
·9 minWhat changes when an AI agent moves from demo to production — tool-call loops, error recovery, observability, cost controls, and the failure modes that only appear at scale.
RAG vs fine-tuning: when to pick each (and when to pick both)
·9 minA practical decision framework for retrieval-augmented generation vs fine-tuning vs prompt engineering — with cost, latency, and update-frequency trade-offs.
Self-hosting Llama vs Claude API: the real cost breakdown
·8 minWhen self-hosting an open-weight LLM beats the Claude API, when it doesn't, and the operational costs nobody includes in their comparison.
Choosing a vector database: pgvector vs Pinecone vs Qdrant
·9 minAn honest comparison of the three serious choices for production vector search in 2026 — what each one is good at, what they're not, and why pgvector wins more often than the marketing suggests.