AmplifyAI

AmplifyAI is Mercer’s multimodel generative AI access platform.

How to Access and Sign In

Go to: mercer.cr8.io
Sign in with your Mercer University credentials. This will engage multi-factor authentication, and you will need to authenticate your login.

How to Use AmplifyAI

Amplify AI provides functionality to customize your interactions with large language models. The left-hand sidebar includes the following features:

Assistants: Assistants are pre-configured AI experts designed for specific tasks. These are created by you to assist with specific needs, such as repetitive tasks, research workflows, writing guides, etc.
Prompt Templates: These are pre-written starting points for your conversations that you write and save as a template.
Custom Instructions: Similar to “Gems” in Gemini or custom GPTs in ChatGPT, you might find an option to add “Custom Instructions.” This allows you to provide overarching guidelines or persona details that the AI should always adhere to in your chats, making its responses more consistent with your preferences.

Effective prompts include these components:

Instruction – the specific task, question, or instruction you want the model to perform for you.

Context – information, history, background, or other additional details that can steer the model to provide you with the best response.

Output Indicator – the type or format of the output (respond in a numbered list, assemble the data in a table, etc).

Role or Perspective – assigning a role to the prompt can direct the model to access different knowledge patterns and response styles. (Example: “Act as an economics professor and explain the reasons for the stock market behavior in 2008.”)

Constraints and Boundaries – if appropriate, specify any conditions that you’d like to use to constrain the model. (Example: Provide a summary of the article but exclude all bibliographic information.)

Known Limitations

All AI models have limitations. Please keep the following in mind when using AmplifyAI:

Developed by Higher Ed: Amplify’s development is led by Vanderbilt University. As a product developed within higher education, you may occasionally encounter discover functionality that lag behind commercial solutions.
No Conversational Memory Between Chats: Amplify AI models do not “remember” information from one chat conversation to another. If you tell it your name in one chat, and then open a new chat (even with the same model), you’ll need to re-introduce yourself or any prior context. Each new chat begins with a fresh memory slate.
No Web Search Capabilities: Because our hosted solution is secure and does not access the Internet, all knowledge comes from the model. For this reason, models in Amplify will not return live web search results or retrieve real-time information. Only files you directly upload and its own training knowledge base are used to answer questions.
File Type Support: Some file types may not be fully supported for analysis or processing within Amplify. Most PDFs, CSV, and DOCX files are expected to work with Amplify; however, exceptions may exist. If your file fails to upload or be recognized, you may try saving it in a different format (e.g., converting a complex PDF to a plain text file or a different PDF version).