MLOps.community  cover image

Treating Prompt Engineering More Like Code // Maxime Beauchemin // MLOps Podcast #167

MLOps.community

00:00

How to Monitor a Speed and B Cost in Production

The library does at its core is they will run your test, your prompt cases for you. It offers a little bit of a DSL like how do you define a prompt case? So that's a way to express in a very nice and syntactic sugar way the same way that you have these test suites. And then it will run them for you, run the eval function and produce a report. That report is in the form of a it's a little CLI application. You're like, AK, prompt, amized, run, find all the tests in this folder and run all the tests against each other. Then we'll output a yaml file for each prompt case with a bunch

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app