Blog
Writing
Life, tech, and everything in-between.
Agentic RAG
8 minAI
Semantic RAG is a fixed pipeline. Agentic RAG hands retrieval control to the model: when to retrieve, what to query, how to combine, when to stop. A short guide to the patterns that matter and how to ship them.
Persistence and Checkpointing: Time Travel and Recovery for LLM Agents
8 minAI
A long-running agent that loses its state on the next deploy is not a production system. Checkpointing saves agent state after every step, enabling conversational memory, human-in-the-loop pauses, time travel for debugging, and fault-tolerant resumption.