CZI: Building AI You Can Trust: Evaluating LLM Outputs for Learning

AI in education is booming, but how do we ensure that LLM-generated content actually supports learning? In this fast-paced, 10-minute demo, we’ll showcase AI evaluation tools for developers that automatically score text based on learning science. Built in collaboration with pedagogical experts from Student Achievement Partners, the Achievement Network, and Gradient Learning, these tools give developers greater visibility and control over AI-generated content. Join us to see how evaluators can help you build AI-powered edtech with confidence—and ensure your technology supports learning.