FAQs

​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 was 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.​ 

​Agents in Clarity use Artificial Intelligence to simulate human-like conversations. You can ask it questions or give it commands, and it responds conversationally. At the heart of an agent is a large language model, like GPT, Gemini, 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 the responses for accuracy. Some agents integrate tools like code interpreters and can support a variety of advanced tasks, from analyzing and summarizing documents to assisting with coding projects. 

​The agents on the Clarity platform is housed within Yale’s secure infrastructure. 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 agents in Clarity, must do so in a responsible and appropriate manner.  You are responsible for ensuring that your use of the agents 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 agents in Clarity, you must also remain mindful of and comply with any third-party requirements and restrictions applicable to the information that you upload to any conversation.

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 agents in Clarity. You are responsible for any content that you produce, publish or otherwise use that includes content generated by the agents.

Agents in Clarity are 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 any agent in Clarity. Any misuse of an agent, such as using the agent 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 agent may result in restricted or prohibited access.

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

All users must use agents in Clarity ethically and responsibly, keeping in mind the collaborative and supportive purpose they serve.

Access to create Custom Agents will be granted upon approval of submitted use cases. Detailed information can be found on the Custom Agents Overview page.

Instructions for creating or managing Custom Agents upon use case approval are provided on the Create/Manage Your Agent page.

Pending use case approval, users can create up to 5 Custom Agents for a use case in Clarity. If you are looking to create agents for a different use case, an additional use case request needs to be submitted.

No, you cannot switch models for your Custom Agents. Create a new agent to use a different model. 

You can select from several different models when creating your Custom Agent. To learn more about how the models differ, please refer to the Agents page.

There is no limit to the number of users you can grant access to your agent, however they must be added individually. If your use case requires a large number of users to have access, you can reach out to ai.platforms@yale.edu for assistance.

Refreshing the Manage Agents page should cause your saved changes to be reflected. 

Review your custom agent’s system prompt as you may need to adjust it to better guide your agent’s behavior. Also, check any documents that you might have uploaded as the agent’s knowledge source that might affect the responses. You can also ask questions our Teams based in the Community of Practice or visit our monthly Office Hour on the first Wednesday of every month, between 10 and 11. 

While some models allow for adjusting temperature, you cannot modify the temperature for your agent in self-service. 

ePHI is approved for Custom Agents or API access in Clarity if the use case has been approved. In addition, there are Health agents available for YSM community use. For more information, refer to the Health Sciences AI Toolkit and the Clarity Platform Security guidelines for approved data types.

Yes, you can get a shareable agent link which is a special URL that takes you directly to a specific agent in Clarity and instantly starts a new conversation with it. It is intended to make it quick and easy to share a specific agent with colleagues, so that the users can navigate directly to the agent without any additional steps and having to select the agent from the dropdown. Please refer to our documentation on how to get a shareable link to an agent.  

API keys for Clarity are granted in relation to Custom Agents and distributed through Azure Key Vault whereas Portkey allows you to generate API keys on your own which aren’t tied to a Clarity Custom Agent. To obtain API access through either option, you must go through a use case review process. Review the Clarity API and Portkey webpage for more information. 

API keys expire after 90 days. If your Clarity API key expires, the AI Platform Services team will issue a new one; for Portkey, you can generate a new API key yourself.

API costs are charged monthly based on consumption. Please refer to the API Pricing page for more information.

Users can create up to 5 Custom Agents in Clarity.

After you have created your Custom Agent in Clarity you reach out to the ai.platforms@yale.edu to get an agent access token. The key will be shared with you through Azure Key Vault. 

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.  

​There are two ways to attach a file:  

1. ​Drag and drop your file into the chat interface.

Or:

2. Select the add (+) icon in the chat input box.
3. Select the “Upload Files” option. 
4. ​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. 
5. ​Upload the file: After selecting the file, the file(s) will be uploaded to the conversation.  A progress indicator will appear, indicating that the file is being uploaded.

Once the file is uploaded, you can interact with the Agent to analyze, summarize, or process information from the document. 

You can maximum upload 1,000 files to a Custom Agent’s knowledge store and you can upload up to 10 files simultaneously in a prompt. 

​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. In addition, the size of the extracted text (not the size of the original file) cannot exceed 10,000,000 characters.

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. Please refer to our documentation on how to search, group, tag, and delete your conversation to easily manage your conversations.

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

Agents in Clarity use general-purpose models that have not been trained on Yale specific data. As such, agents in Clarity may make mistakes in its responses. While agents are very good at generating content, the content they generate may be inaccurate, misleading, or entirely fabricated; this is oftentimes referred to as “hallucinations”. This is one of the limitations of AI 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.  

Additionally, agents might not always have the information you need, especially if it’s very domain-specific or beyond their knowledge cut-off date. Our agents 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 Platform has several agents available. Please refer to the Clarity Agents Page which outlines each of the agents and their differences.

The 🌱 emoji indicates an agent which uses a more environmentally friendly model.

The featured agents on the Clarity platform know the current date. 

• To ensure the fastest response, please use the channel that matches your request:
  • Clarity bugs and issues
  • General Clarity requests and/or questions
  • Portkey bugs and issues
  • Health chatbots/agent access
• For any other technical support related to the Clarity platform please reach out to the ITS helpdesk.

The Clarity Agent Portal is available in four Yale-branded themes. Please refer to our documentation on how to select a theme.

All Featured Agents can generate images from a text or voice prompt utilizing the Gemini 3.1 Flash Image model. Generating an image works just like asking any other question you may ask the agent – type or speak your prompt, and the agent will generate an image based on your request. 

1. Start a conversation with any featured Clarity agent. 
2. Describe the image you want in plain language.  
3. Send your message. 
4. The agent will let you know it’s working on your image. Your image will appear directly in the conversation thread shortly after. 
5. To save the image to your device:  
6. Desktop: Right-click the image and select Save image as…, then choose a location on your device. 

Refer to our documentation for more information and tips on how to generate images in Clarity.

Image generation in Clarity creates new images from text descriptions. A few things are outside its current scope: 

• Content guardrails: Content safety filters are applied to all image requests. Prompts that request harmful, explicit, or policy-violating content will not be fulfilled, and you’ll receive a message explaining why. 
• Video or animation: Only static images are supported. 

Voice mode lets you have a spoken conversation with agents in Clarity. You speak naturally, the agent listens and responds aloud, and the conversation flows back and forth just like a real dialogue.  

Voice is available on all Featured Agents and it can be enabled for your Custom Agents. If the voice button isn’t visible in the conversation input area, the agent you’re using doesn’t have it turned on. 

Please refer to our documentation for more information on how to start and end your voice conversation.

When you use voice mode, your spoken words are transmitted securely to process your request and generate a response. 

• Audio is not stored: Voice recordings are not saved after your session ends. 
• Your audio is not accessible to others: Your voice audio is not made available for others to listen to.
• The microphone is never on without your action: Voice mode only activates when you explicitly tap the wave button and deactivates when you end the session.

1. Select the add (+) icon in the chat input box
2. Select the “Connect to OneDrive” option 
3. A confirmation message will display when the connection has been established.
4. ​Select the “Upload file from OneDrive” when clicking on the add (+) icon: 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. 
5. ​Upload the file: After selecting the file, the file(s) will be uploaded to the conversation.  A progress indicator will display, indicating that the file is being uploaded.

Your profile picture appears in Clarity because it is linked to your Yale-affiliated Microsoft account. When you connect your OneDrive or use the same account details to log into Clarity, the associated profile information, including your profile picture, gets integrated. 

There are two ways that you can disconnect from your OneDrive in Clarity.  

You can make a soft disconnect by: 

1. Select the add (+) icon in the chat input box
2. Select the “Disconnect OneDrive” option 
3. A confirmation message will display when your account is disconnected from OneDrive.

The soft disconnection from your OneDrive account does not revoke your access grant via Microsoft. Please follow the following steps, if you want to revoke the access grant via Microsoft too: 

1. Navigate to Microsoft’s website(Link is external). 
2. Find the app named FoundationaLLM-Core-Portal and select the three dots next to the app and choose “Manage your application”. Do NOT select the option to “Remove” the app. 
3. On the FoundationaLLM-Core-Portal page you have the option to select “Revoke Consent”. 
4. When you go back into Clarity and select a file from OneDrive, a pop-up window will ask you to grant Clarity the necessary permissions to access your OneDrive files.  To connect to your OneDrive again, simply accept these permissions.

There is a hard limit of 512MB per file and you can upload up to 10 files simultaneously. All common file types are supported, including text files, spreadsheets, presentations, and documents. Please refer to the FAQ that outlines the supported file types.