HARIPRIYA

How to Evaluate Your LLM App: Building a Simple Eval Set

Posted on Sun 25 October 2026 in Tutorial • Tagged with GenAI, LLM, evaluation, evals, testing, Python, prompt-engineering

The Question I Couldn't Answer

For a long time, my process for improving a prompt was embarrassingly simple: change the wording, try two or three inputs, decide it "feels better," and move on. Then one day someone asked me a basic question: "Is the new version actually better than the …

Why Some Prompts Work Perfectly in Testing and Fail in Production

Posted on Wed 23 September 2026 in GenAI • Tagged with GenAI, LLM, prompt-engineering, production, testing

Why This Keeps Happening

You spend hours refining a prompt. You test it with ten, twenty, fifty example inputs. It works beautifully every time. You ship it. A week later, real users start hitting it with inputs you never imagined, and the same prompt that felt bulletproof starts producing broken …