AI stacks & workflows
How the categories fit together to build something real - each stack walks the layers in order, with guidance on when not to reach for each.
The RAG stack
Retrieval-augmented generation grounds an LLM in your own data. A production RAG pipeline is four layers: ingestion, a vector store, orchestration, and evaluation.
The AI agent stack
Autonomous agents plan, call tools, and act over multiple steps. The stack pairs an agent runtime with model tooling, integration glue, and tracing.
The local / self-hosted LLM stack
Running open models yourself for privacy, cost, or control. The stack is a serving runtime, optional fine-tuning, and supporting tooling.