How an Agent Finds Your Docs, and Which Files It Actually Reads
Five file conventions claim to be the standard for AI agents. Here is what each one answers, who really reads it, and the evidence behind both claims.
Retrieval and RAG08
I build the layer between a language model and software that already exists.
Five-plus years on the same stubborn question: how do you take something that works in a notebook and make it survive real users? Mostly that has meant backend systems, production machine learning, and the harness layer in between. Lately a fourth thread has crept in, machine learning for biology, where the datasets are small, the labels are noisy, and being honest about your numbers matters more than beating a leaderboard.
Now
Since Aug 2026
Senior Software Engineer, Mevrik
An AI customer-experience platform used by telecom operators and several hundred smaller businesses. I work on the AI side: agents, retrieval, and the serving infrastructure underneath.
Since 2024
Founder, AlgolyzerLab
A small studio for applied AI that does not fit a product roadmap: sports science for elite cricket, clinical software for doctors, agriculture AI, and research engineering.
What I think about
01
Agent harnesses
A model is only as useful as the surface you hand it. Most teams give an LLM raw tables and generated specs instead of the intent-named operations their own code already has.
02
Machine learning for biology
Anti-inflammatory peptide prediction, and structure-aware virtual screening of natural products against understudied viral proteases. Both taught the same lesson: the dataset you choose decides the result long before the model does.
03
Recent writing
Before You Retrieve Anything, Someone Has to Read the PDF
Every retrieval method assumes clean structured text. Getting it out of a PDF is its own problem, and Docling is the 2026 answer worth knowing.
Retrieval and RAG07
Several Retrievers, One Small Machine
How to run keyword, dense, fusion and reranking together on modest hardware: where the memory actually goes, and which famous constants are folklore.
Retrieval and RAG06
Do You Actually Know If It Works?
The scarce skill now is not writing code but knowing your own system: what you solved, how it works, and whether a new bug is even yours.
How Computers Guess by Asking the Neighbours
A gentle, playful look at k-nearest neighbours, the lazy way a computer labels something new by asking the dots closest to it.
Why a Light Weight Can Lift a Heavy One
A friendly beginner guide to why a see-saw balances, how torque works, and why a light weight far out can lift a heavy one close in.