Description

To put Cornell at the forefront of Artificial Intelligence innovation, as well as provide tools that allow faculty and staff to realize time and effort savings, Cornell needs AI tools that allow its constituents the opportunity to manipulate protected data (as defined by University policy and applicable federal and state laws).

CIT is developing a chatbot tool that allows Cornell to use AI in a Cornell-owned environment. The goals of this project include providing an AI tool that can be used with moderate risk data.

SandboxAI is currently available to those with a demonstrated need for this secure environment. During this initial exploratory phase, CIT plans to continue developing SandboxAI. 

Access SandboxAI

Sandbox AI is not yet generally available. However, if you have an institutional problem that requires data-protected AI to help solve, please submit a request to access this tool.

About the AI Models

GPT-4o (Azure OpenAI)

GPT-4o is OpenAI’s flagship multimodal model that integrates text, vision, and audio capabilities, available through Microsoft Azure’s OpenAI Service. Read more about GPT-4o directly from Microsoft.

Data Analyzer (Azure OpenAI Assistants)

The “Data Analyzer” model, also known as “Code Interpreter,” extends the capabilities of GPT-4o by enabling the execution of Python code within the assistant. With this feature you can conduct advanced data analysis and data visualization, as well as solve complex code and math problems. Technical details are available from Microsoft Learn.

Claude 3.5 Sonnet

Anthropic's Claude 3.5 Sonnet is an advanced AI model that excels in reasoning, coding, and visual tasks, surpassing previous versions and competitors. It offers enhanced speed and cost-effectiveness, making it suitable for complex applications like customer support and multi-step workflows. More info directly from Anthropic.

Support for SandboxAI

SandboxAI has a support team separate from the IT Service desk. For help fill out this form.