Working 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.
All Activities
-
-
Improving your 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.
-
Building an intent hierarchy
The intent hierarchy is the core of the boost platform. It is here that the scope, what your virtual agent is supposed to know, is organized. This course covers how to build and navigate your own intent hierarchy.
-
Create and design basic content
A virtual agent needs to be able to respond to an end user with well-designed and informative content. This course takes you through the most basic and simple tools for creating great responses.
-
Onboarding for AI Trainers
Are you an aspiring AI Trainer? This is the perfect onboarding for you to take as you build your first virtual agent. Learn all the basic tools to train a custom model, create responses, and get a feel for how...
-
Train a custom NLU model
For the virtual agent to understand end users it needs some kind of model, and the boost platform allows you to train your own custom NLU model. This course takes you through that process, including training data and test data.
-
-
Introduction 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.
-
-
Conversation design for voice
We learn the basics of designing content for voicebots. We look at how the voice channel differs from chat and which features you can use to enhance your voice flows.
-
Building trust through security & data protection
Data security is essential for protecting sensitive information and maintaining customer trust. Boost.ai helps businesses build trust by offering tools for data protection and compliance. This lesson covers Boost.ai’s security measures, emphasizing cloud hosting as a secure solution and how...
-
Why support multiple languages?
If you are interested in finding out how multiple languages work, why and when it should be implemented, and how to get started. Then this is the course for you.
-
How boost.ai leverages generative AI
Get an overview of how boost.ai build and implement high performing virtual assistants by leveraging Generative AI within our custom platform.
-
Security & privacy features in the boost platform
Boost.ai is an organisation that takes security and privacy very seriously, and the platform has several features that will help you manage you and your end user's date securely and responsibly. We can not give advice on how to configure...
-
What parts make up a virtual agent?
Are you new to boost.ai's platform, or curious what it is? In this course we explain how our platform is set up, in broad lines, to help you understand how we help you deliver great virtual agents.
-
Increase your traffic
In this course, we cover methods to increase your traffic based on real data from live projects. You'll learn how to categorize initiatives to increase traffic, and how to find ones that fit your virtual agent's project.
-
Automate more interactions
The automation rate tracks how many interactions we can resolve without involving a human. It is one of the most central Key Performance Indicators (KPIs) for virtual agent projects, because automated interactions save time, money and resources. This course covers...
-
Working with intent overview
In this course, we introduce the intent overview tool and explain why it's such an important tool for running an efficient virtual agent project. We show what you can do with it, and share examples of how to use it...
-
Teaching our VA to understand & respond to users
In its simplest form, a virtual agent needs to understand what users are saying and respond appropriately. In this activity, we are going to dive into how we build understanding and create responses in the boost.ai platform.
-
The boost.ai platform
Get a quick overview of what virtual agents are, the parts that they are made of and how they work within the boost.ai platform.
-
Building virtual agents with boost.ai
Building virtual agents might sound like a big task, but it's not that bad so long as we approach it systematically. This course is all about giving you an overview of how it's done.
-
Understanding the boost.ai platform
If you're new to boost.ai and need a broad overview of our product and how it works, then this is your starting point. Even if you don't have access to the boost.ai platform yet, this is a perfect introduction to...
-
Building flexible responses with generative action
Generative action allows us to create dynamic and flexible responses that cover multiple scenarios and use cases. This course gives an introduction to how to write instructions, upload knowledge, design action and API hooks, and set up guardrails, making sure...
-
Giving the best response: Generative or predefined?
Let's explore the building blocks of conversation design: generative and predefined responses.
