Goodnotes' primary AI tool, Compare to Model Answer, can analyze and group student responses based on their similarity to a predefined correct solution. This tool is used in Smart Clusters, significantly enhancing your grading efficiency, allowing you to focus more on student development.
Other features such as Spellcheck and Math Conversion may be used by your Students in Goodnotes.
Why do I not have access to all Goodnotes AI features?
Most of our AI features, namely Spellcheck, Word Complete, Math recognition, Interactive Exam Practice, and AI Math Assistance, are available in all markets. However, a few AI features are only available in certain regions or languages. For example, AI typing features aren’t available in the following regions at the moment:
- Afghanistan
- Belarus
- China
- Iran
- North Korea
- Russia
- Syria
- Ukraine
- Venezuela
Which LLM does Goodnotes Education use for Compare to Model Answer?
Goodnotes is using OpenAI's GPT4o model to analyse and group student answers. In order to use this feature, student's answers are anonymously sent to OpenAIs servers. Note that the feature is optional and Goodnotes will only send the student responses to OpenAI's server when the user is using Compare to Model Answer.
Is personal data (handwriting/notebook content) used to train AI features?
Goodnotes assures users that it does not access or collect data from their notebooks to train its AI features. However, users of Goodnotes can voluntarily submit their data through ‘Feature Feedback’ under section 3.7.1. Goodnotes may use this information to improve its services, but only if it is submitted voluntarily.
As our Compare to Model Answer feature uses Generative AI to analyse and group student answers, it may occasionally provide incorrect results. Certain student answers may not be properly recognised and analysed by the model. Teachers should also verify the results of Compare to Model Answer and make necessary adjustments.
Does Goodnotes use document data to train AI models?
We use document data in order to provide and optimize our AI features. Raw documents stored by Goodnotes are stripped of any personal data before being used for training.
What data does Goodnotes collect from your institution’s use of AI features?
We collect anonymized statistical data to track the use of our AI features. We also collect Human Override Data (aka AI mistakes) and any "change" made by a teacher to override any decision made by AI. This helps us improve the accuracy and identify mistakes in the AI model.
How has Goodnotes designed Smart Clusters in line with responsible AI?
Smart Clusters have been trained on a diverse and representative data set. For example, its handwriting recognition component encompasses a wide range of handwriting styles and languages. Smart Clusters’ ability to comprehend language is powered by Open AI’s GPT-4 model, which is trained on a large sample of 1 petabyte of data. Moreover, whenever using Smart Clusters, teachers are reminded that AI is capable of making mistakes and they should verify its output.