Testing it out

The result from ChatGPT using the 3.5 Model yielded the following:

USER : Who designed the Model T?
AI : The Model T, also known as the "Tin Lizzie," was designed by Henry Ford and his team at Ford Motor Company. It was introduced in 1908 and is considered one of the most influential cars in automotive history, as it made automobiles affordable for the average consumer through innovative manufacturing techniques like assembly line production.

Our ChatBot was also using the 3.5 Model, but we got these results:

USER: Who designed the Model T?
AI : The Model T was designed by Joseph A. Galamb (main engineer), Eugene Farkas, and Childe Harold Wills.

The reason the results are different is because the Prompt we sent to the LLM contained relevant information from our dataset. To see exactly what was passed to the prompt you can click the View Trace Link under the AI node after you run a test.

With BotDojo, you can see all of the Inputs and Output from all the Nodes. This helps you understand what is going on under the hood. Now that we have a working ChatBot, how do we know it’s answering things correctly? Next, we will learn how to set up Evaluations to monitor the performance of our ChatBot.