// the knowledge base
Explore everything.
Every article, writeup and note across the platform β filter by world, difficulty, author or tag, sort your way, and save what matters.

π€ AI / ML
Advanced
Experimenting with LLM Agents (and Where They Fall Apart)
I built three small agents to understand where the capability boundary actually is. The pattern: they are brilliant at one tool call and unreliable at the fifth. Notes on what survives contact.
Sandesh BramhaneAug 22, 2026
#llm#ai-agents#experiments1 min1272

π€ AI / ML
Intermediate
Building a RAG Pipeline: From Chaos to 90%+ Recall
I rebuilt the same RAG system five times. Chunking strategy, embedding choice, and reranking moved my eval recall from 41% to 93% β here is each change, measured.
Sandesh BramhaneAug 8, 2026
#rag#llm#embeddings1 min13442