AI Applications

Retrieval-augmented generation, orchestration frameworks and the tooling around them.

2 articles

LangSmith: Seeing What Your LLM Application Did

An LLM application fails in ways logs do not capture: the right tool called with the wrong argument, a retrieval that returned nothing useful, a prompt change that quietly broke two other cases. Tracing shows what happened; evaluation tells you whether a change helped.

Rajiv Kumar·Aug 26, 2026·10 min read

RAG & Knowledge Retrieval

LangGraph State and Control Flow: A Practical Guide to Reliable AI Agents

LangGraph models an agent as nodes, edges and a shared state object. That structure buys three things a plain agent loop cannot: a place to put state, control over what happens next, and the ability to resume a run that was interrupted.

Rajiv Kumar·Aug 19, 2026·9 min read