This learning plan is designed to be taken with the basic AI Trainer onboarding. It contains additional course material specifically for using intent-based routing and training an NLU model. This material is only required for AI Trainers working on intent projects, and for projects relying on the orchestrator, it won't be needed.
Onboarding add-on for Intent based routing
Intents
The first step when learning how to set up intent based routing is the intent hierarchy itself.
Training an NLU model
Everything you need to build an AI agent and train a custom NLU model. The first course is also part of the basic onboarding. The second course explores language processing, a core aspect of the NLU model.
-
Train a prediction model
Learn how to train a custom NLU model in boost.ai — from preparing training data to evaluating performance.
-
Intro to language processing
The language processing algorithm is a central part of how our custom NLU model understands languages. In this course, we will see how big of an impact this algorithm can have on model performance and how it works.
Improve the NLU model
The NLU model won't be perfect when we train it the first time, sp we will have to work methodically to improve it. These courses will teach you everything you need to create an accurate model.
-
Improve the model with clean-up reports
The clean-up reports are built-in reports that tell you where to improve your trained NLU model. In this course, we will go through some of the more important reports and give you an idea of where to start.
-
Improve the model with test results
Test results are the ultimate tool for benchmarking and improving a custom-trained NLU model. This course introduces the various kinds of issues we can find here and how to resolve them, improving prediction accuracy.