AI / LLM Engineer

Hi, I'm Pradhumn.

I build production RAG, agentic search, and the systems that make LLMs actually work in the real world.

Interactive · The RAG Challenge

Can you tune a production RAG pipeline?

Balance accuracy against latency and cost across three levels. It's the balancing act every real RAG system lives or dies by — made playable.

Latest writing

All posts

July 8, 2026/2 min

Why RAG fails in production — and where

When RAG breaks, the model usually isn't the problem — retrieval is, about 73% of the time. Here's the real failure map and what to fix first.

Read

#rag #production #retrieval

July 8, 2026/2 min

Why I don't use LangChain in production RAG

Frameworks are great for a demo. In production, the abstraction you can't see into costs more than it saves.

Read

#rag #llm #production

July 8, 2026/3 min

When NOT to use RAG (RAG vs fine-tuning vs prompting)

RAG became the default reflex for every LLM problem. Often it's the wrong tool. A straight decision framework for RAG vs fine-tuning vs just prompting.

Read

#rag #llm #architecture

July 8, 2026/2 min/reference

A reference architecture for production RAG

The stages every production RAG system needs — indexing, query-time retrieval, and always-on evaluation — and how to order them.

Read

#rag #production #architecture

Get new essays by email

Occasional field notes on production RAG and LLM systems. No spam, unsubscribe anytime.