Privacy and Security
Like Copilot, Teams, and other Rollins supported systems, data that is entered into Amplify GenAI is kept within the Rollins system. Companies that own and operate the models that Amplify GenAI provides access to are not collecting, or using any of the information, prompts, conversations, or artifacts to train or advance their own AI. Your conversation history when saved locally is stored in your device’s browser, and when stored in the cloud simply makes it accessible between devices, but does not share it institutionally or externally. The only time that your chat history or conversations, assistants, artifacts, etc. are shared, is when you choose to share them individually.
Even with data protection within the Rollins system, sensitive or personally identifiable information, and other data that may be protected under laws and regulations like FERPA, HIPPA and more, should not be uploaded to Amplify GenAI through document upload, or prompting.
Model Choice
Amplify GenAI gives you access to multiple models within one, secure location. Models can be utilized between conversations and should keep their internal chat memory – or contextual window. Choosing a model, or swapping models to continue working through your project and conversational needs can ensure that your model always aligns its expertise with your project, idea, or conversational needs. Testing each model with various prompts helps identify their strengths and weaknesses.
Note: Currently, there is no way for any of the models within Amplify – regardless of their abilities outside the Amplify interface – to web search and find sources to cite the outputs you receive. The models will only be able to pull information up to the date that they were last trained, and all outputs should be verified independently for accuracy.
(Vanderbilt Documentation)
Available Models include:
- GPT-3.5
- GPT-4 Turbo
- Claude 3 Sonnet
- Claude 3 Haiku
- Mistral 7B Instruct
- Mixtral 8x7B Instruct
- Mistral Large
Assistants, Helpers and Templates
Custom Instructions in Amplify are basically a set of rules at the start of a conversation designed to prime the AI tool to get a more focused and desired response. These instructions can include details about desired tone, style, or content, allowing you to customize the language model's responses to better suit their individual requirements. Examples of custom instructions could be ones focused on turning data into a visualization or taking detailed text and reformatting it into a PowerPoint presentation.
Prompt Templates are designed to streamline the process of using the same prompt or sharing a prompt with slight differences. A prompt template is a prompt with placeholders. You can select a prompt template, fill in the placeholders and run the prompt with the model of your choice. This is a great tool if you create a detailed prompt that you plan to use to complete a similar task more than once that may be focused on different content.
Amplify Helpers are prompt templates and custom instructions that the Amplify development team deems “helpful” to Amplify users.
Assistants are Conversation “overlays” that can be used to add data sources automatically to a pool of resources for the model to interact with. They can automate repetitive tasks, generate specifically formatted content like articles summaries or code, and assist with research analysis and decision-making.
Brief Overview
Additional Information