Clarity Platform FAQs

Overview

​The Clarity platform is part of Yale’s AI initiative to offer the Yale community secure and equitable access to AI. The first tool to launch on the Clarity platform is a secure, conversational chatbot with innovative capabilities. It is available to all students, faculty, and staff.

​The Clarity platform will evolve to support additional use cases such as the creation of custom AI agents and direct access to AI models, enabling developers to incorporate these tools into applications used for research, teaching, and other use cases.​ 

​An AI chatbot is a tool designed to simulate human-like conversations. You can think of it as a virtual assistant that you interact with. You can ask it questions or give it commands, and it responds conversationally. At the heart of an AI chatbot is a large language model, like GPT-4o, Llama, Claude, or others. These models excel at producing responses to natural language prompts. While these responses can sound authoritative and convincing, they can contain mistakes and falsehoods. You should check AI chatbot responses for accuracy. Some AI chatbots integrate tools like code interpreters and can support a variety of advanced tasks, from analyzing and summarizing documents to assisting with coding projects. 

​The AI chatbot on the Clarity platform is like Microsoft Copilot with Data Protection or OpenAI’s ChatGPT but housed within Yale’s secure infrastructure to allow use with sensitive/confidential/proprietary data. Users are expected to observe relevant security standards when handling data provided to or created by Clarity.

Yale University operates under a shared responsibility model, which means that each individual using University-provided technology, including the Clarity AI chatbot, must do so in a responsible and appropriate manner.  You are responsible for ensuring that your use of the Clarity AI chatbot complies with all University policies that may be applicable to you, such as the University policies on academic integrity, the Yale University Policy Against Discrimination and Harassment and the Yale University Sexual Misconduct Policies. When using the Clarity AI Chatbot, you must also remain mindful of and comply with any third-party requirements and restrictions applicable to the information that you upload to the Clarity AI chatbot.

Please be aware that AI-generated content may sometimes be inaccurate, misleading or entirely fabricated (sometimes called “hallucinations”) or may contain information protected by third-party intellectual property or other rights. As such, you must carefully evaluate the content generated by the Clarity AI chatbot. You are responsible for any content that you produce, publish or otherwise use that includes content generated by the Clarity AI chatbot.

The Clarity AI chatbot is designed to assist your University work and daily tasks, including research, and teaching and learning. Policy 1607 (Information Technology Appropriate Use Policy), which provides guidelines for the appropriate use of University IT Systems, applies to your use of the Clarity AI chatbot. Any misuse of the Clarity AI chatbot, such as using the Clarity AI chatbot to engage in activities that are illegal, infringe on the rights of others or otherwise violate applicable University policy, or conducting unauthorized security tests of the Clarity AI chatbot, may result in restricted or prohibited access.

In addition, jailbreaking the Clarity AI chatbot by modifying or manipulating the Clarity AI chatbot to bypass built-in safeguards is prohibited. If the Clarity AI chatbot does not support your desired action, you are encouraged to contact us or suggest a new feature instead of attempting to alter the Clarity AI chatbot’s functionality.

All users must use the Clarity AI chatbot ethically and responsibly, keeping in mind the collaborative and supportive purpose it serves.

​Access, Features and Limitations

The AI chatbot can be accessed on the Clarity platform. You will need to log in with your Yale email. 

The like and dislike buttons allow you to mark responses you find helpful or not, but the information otherwise is not shared with anyone at Yale. The buttons do not impact the responses from the chatbot. In the future we may extend the functionality of these buttons to aggregate feedback to improve the performance of the chatbot, after confirming with the user that they agree to share the feedback.

A token count is displayed for your prompt and for the generated response. Instead of words or characters, tokens are a measurement tool used to assess the length of chat inputs and outputs, defining the amount of work the agent must perform. Usually, it is not something you as a user should be worried about.

The AI chatbot on the Clarity platform doesn’t have the capability to browse the internet to provide up-to-date information and is relying on its training data when generating responses. The training data is current as of October 2023.

​For searching within the file, the following file types are supported: 

  • Text Files: .doc, .docx, .pdf, .pptx, .txt, .md, .tex
  • Data Files: .json
  • Code Files: .c, .cpp, .cs, .css, .html, .java, .js, .php, .py, .rb, .sh, .ts

​For interpreting the file using code, the following file types are supported: 

  • Text Files: .doc, .docx, .pdf, .pptx, .txt, .md, .tex
  • Data Files: .csv, .xlsx, .json, .xml
  • Code Files: .c, .cpp, .cs, .css, .html, .java, .js, .php, .py, .rb, .sh, .ts
  • Image Files: .gif, .jpeg, .jpg, .png
  • Compressed/Archive Files: .tar, .zip

​Over 100 languages are supported. However, please be aware that while the AI chatbot can understand and generate text in these languages, the quality of the responses may vary based on the language’s complexity and the context of the request.

Training and General Instructional Questions

Training material, including key terms and training videos on AI, can be found on the Learn About AI page.   

​Training material specific to the Clarity platform can be found on the Clarity Platform page.

​To upload a file during your conversation, you can use the “Attach File” button located at the bottom of the chat interface and next to the message box.  

​Here’s a step-by-step guide: 

  1. ​Select the paperclip button: Look for the paperclip icon labeled “Attach File” in the chat interface. 
  2. ​Select your file: A file explorer window will open, allowing you to select one or multiple files from your computer. Navigate to the file you want to upload and select it. 
  3. ​Upload the file: After selecting the file, confirm the upload by selecting the upload button. A progress indicator will display, indicating that the file is being uploaded and a success message will display when the file has been successfully uploaded. 

Once the file is uploaded, you can interact with the AI chatbot to get analyses, summaries or to process information from the document. 

Currently, there is a limit of 10 files that can be uploaded per chat session.

​The file size limit is 512MB for any type of file. An error message will show up on your chat session if the file limit has been exceeded. 

​There is no limit to how many chat sessions a user can have. If you don’t want to keep a chat, you have the option to delete it from the chat history. 

​To have multiple chat sessions at once, click on the “+” in the upper left corner of your chat window to start additional chat sessions. 

The AI chatbot on the Clarity platform is a general-purpose AI chatbot and it has not been trained on Yale specific data. AI chatbots, including the AI chatbot on the Clarity platform, may make mistakes in its responses. AI chatbots are very good at generating content, which is one of the reasons they are very popular, but that content can be inaccurate, misleading, or entirely fabricated, sometimes called “hallucinations”. This is one of the limitations of AI chatbots and it highlights why it is important to always fact-check the responses you receive. Remember that you are responsible for any content you produce or publish, including AI-generated material.  

Also, it’s important to understand the limitations of AI chatbots. They might not always have the information you need, especially if it’s very domain-specific or beyond their knowledge cut-off date.  AI chatbots are powered by large language models that may reflect biases in their training data. Consequently, the responses they produce reflect their inherent bias and the quality of their programming and training data.   

​The Clarity AI chatbot is driven by the GPT-4o multi-modal model. In the future the Clarity platform will make many other models available for use in custom applications. 

Security Questions

Yes, your questions and responses from the AI chatbot on the Clarity platform are securely stored within Yale’s IT infrastructure.

​Your conversations with the AI chatbot on the Clarity platform will be accessible to you, IT Systems Administrators, and Microsoft. As with any IT system, the data you enter can be accessed by IT Systems Administrators; however, this would only be done in accordance with Policy 1607.2 (Conditions for University Access).  Also, since abuse monitoring is enabled, your conversations will be accessible to Microsoft.

No, the Clarity platform utilizes a security architecture that applies role-based access control to the information you enter into the chatbot. Every attempt to access data first verifies that the user who created the data is the one attempting to use it.

​The Clarity platform is approved for high-risk data. Please refer to Yale’s Data Risk Classification Guideline.