Anu Kumar (@anukumar0)

@anukumar0Mohali, IndiaJoined October 2026

Senior AI Engineer working on LLM agents, retrieval pipelines and the infrastructure that keeps them running. I write about agent architecture, RAG, multi-agent systems and evals. More at https://anukumar.site

@anukumar0Mohali, IndiaJoined October 2026

Anu Kumar

About

Available for

Anu Kumar's blogs

Recently published

LLM evaluation: evals that catch regressions, and when to trust LLM-as-a-judge

Multi-agent systems: when splitting an agent helps and when it just costs more

RAG retrieval: hybrid search, reranking and measuring recall

Agentic AI in practice: tool design matters more than the prompt

Human-in-the-loop AI agents: where approval gates belong

Anu Kumar

About

Available for

Anu Kumar's blogs

Recently published

LLM evaluation: evals that catch regressions, and when to trust LLM-as-a-judge

Multi-agent systems: when splitting an agent helps and when it just costs more

RAG retrieval: hybrid search, reranking and measuring recall

Agentic AI in practice: tool design matters more than the prompt

Human-in-the-loop AI agents: where approval gates belong

Anu Kumar

About

Available for

Anu Kumar's blogs

Recently published

LLM evaluation: evals that catch regressions, and when to trust LLM-as-a-judge

Multi-agent systems: when splitting an agent helps and when it just costs more

RAG retrieval: hybrid search, reranking and measuring recall

Agentic AI in practice: tool design matters more than the prompt

Human-in-the-loop AI agents: where approval gates belong

Search Hashnode

Anu Kumar

About

Available for

Anu Kumar's blogs

Recently published

LLM evaluation: evals that catch regressions, and when to trust LLM-as-a-judge

Multi-agent systems: when splitting an agent helps and when it just costs more

RAG retrieval: hybrid search, reranking and measuring recall

Agentic AI in practice: tool design matters more than the prompt

Human-in-the-loop AI agents: where approval gates belong