Ayush Kumar

@ayush115

Exloring | Learning | Building in AI

Delhi, IndiaJoined March 2026

About

Exploring developments in AI and building things that I learn. Currently diving deep into LLMs, RAG systems, and Agentic AI. Here to document what i learn.

Available for

Nothing here yet.

Ayush Kumar's blogs

Ayush Buildsayushbuilds.hashnode.dev3 posts

Articles Threads Comments

Recently published

AKAyush Kumarayushbuilds.hashnode.dev

0

What Actually Happens When You Add Tools to a LangGraph Agent

1d ago · 7 min read · Most LangGraph tutorials stop at "it works." This post is about what breaks right after that. There's a big difference between understanding tool calling in theory and wiring it into a production-grad

Join discussion

AKAyush Kumarayushbuilds.hashnode.dev

0

Building Narad: A Stateful AI Chatbot That Actually Remembers

3d ago · 10 min read · Most AI chatbot demos share the same fatal flaw — refresh the page and the conversation is gone. The "memory" is an illusion, held together by session state that evaporates the moment the process rest

Join discussion

AKAyush Kumarayushbuilds.hashnode.dev

0

From Prototype to Production: Lessons Building a YouTube RAG App with Vector Search

Mar 25 · 7 min read · TL;DR Built a YouTube Q&A app using RAG — paste a URL, ask questions Hybrid search (dense + BM25) + Cohere reranking for better retrieval Pinecone for cloud vector storage, deployed on Render Went

Join discussion

Ayush Kumar

About

Available for

Ayush Kumar's blogs

Recently published

What Actually Happens When You Add Tools to a LangGraph Agent

Building Narad: A Stateful AI Chatbot That Actually Remembers

From Prototype to Production: Lessons Building a YouTube RAG App with Vector Search

Search Hashnode

Ayush Kumar

About

Available for

Ayush Kumar's blogs

Recently published

What Actually Happens When You Add Tools to a LangGraph Agent

Building Narad: A Stateful AI Chatbot That Actually Remembers

From Prototype to Production: Lessons Building a YouTube RAG App with Vector Search