The Deep Tensors blog

A practical LLM evaluation harness you can build in a day

You do not need an evaluation platform. You need fifty cases, a runner, and the discipline to look at the output before you ship.

Top libraries for Deep Learning

Why most AI agents fail in production

The demo works, the pilot stalls, the rollout quietly dies. Four failure modes we see in almost every agent project — and what a system that survives contact with real users looks like.

RAG is not a product: retrieval patterns that hold up

Chunk, embed, search, stuff into a prompt. That pipeline gets you a convincing prototype and a support queue full of confidently wrong answers. Here is what we build instead.

Fine-tuning vs prompting: a decision you can defend

Fine-tuning is rarely the first answer and occasionally the only one. A short decision procedure for choosing between prompt engineering, retrieval, and training.