In this final post of my Testing AI series I take a look at LangSmith. A powerful observability and monitoring tool for AI and Large Language Models.
Author: Stuart
Engineering manager with a passion for delivering high quality software at pace, for solving the impossible problems, and for helping individuals be the best version of themselves that they can be.
Testing AI – How To Assess LLM Quality With TruLens
Want to objectively measure the quality and effectiveness of your LLM-based applications? In this post I discuss Trulens, the perfect tool for the job.
Testing AI – How to create Automated Prompt Testing With Playwright
AI is here to stay, and if you work in Quality, you might want to learn how to test it. In this post I discuss how to leverage Playwright to test an LLM.