How can Iris help me with my work?

Iris is designed to help non-expert programmers who understand what kinds of analyses they need to run (for example, creating a logistic regression model, or computing a Mann-Whitney U test) but not how to write the code to accomplish these goals. Iris also allows expert programmers to accomplish data science tasks more quickly.

Iris supports a broad set of functionality available in popular Python scientific libraries such as scipy and scikit-learn, and we intend to open source the system upon release.

How is Iris different from today's conversational agents?

Iris allows you to combine commands together in a way that is not possible for today's agents. For example, you can log-transform a piece of data before applying a t-test through a nested conversation with Iris, or use the result returned by a previous conversation with Iris in a new conversation ("take the variance of that"). By treating commands as building blocks that you can weave together through conversation, Iris allows you to accomplish far more complex tasks.

Who is working on Iris?

Iris is a research system under development by the Human-Computer Interaction (HCI) group at Stanford University. We are collaborating with others in the Bioinformatics and Communications departments at Stanford.