Optimize Agent
Data Flywheel
In the last section we created test sets of varying sizes, ready to evaluate our agent. So, it’s finally time to start our data flywheel spinning! 🔁
In pseudo-code, the general process for optimizing an LLM agent is quite straightforward:
Firstly,
let’s activate the MarkingAssistant
project.
Let’s also set a new context Evals
,
where we’ll store all of our evaluation runs.
Great, we can now dive into the first step of the flywheel! 🤿