
In a previous episode, we looked at structured outputs where we could get a language model to respond in a shape that our application understands.

Ask it about the data in your database without providing it in the context and it will happily make something up.

Instead of our application asking the model for information, we're going to let the model ask our application.

Read the full transcript.
Create an account to read the whole episode, search across every transcript, and follow the shows you care about.