platoseedplatoseed
Simulate your customers with AI agents
Expected Parrot helps companies simulate their customers with AI agents to explore pricing, product, marketing, communications and other scenarios at scale. Our open-source library and no-code web app let you design custom agent personas and conduct interviews and surveys with them using LLMs of your choice to generate results and reports. Everything is cached and reproducible, and you can send the same surveys to human respondents to validate results in the same interface.
Prior to building E[P] I was as founding member of Uber's Legal Data team and spent 7 years managing cross-functional data reporting. Before joining Uber I was a tax and investment funds attorney at Ropes & Gray LLP and served as an Assistant Attorney General in Massachusetts prosecuting environmental and white collar crimes. Before law school I managed simulations contracts for Northrop Grumman. Harvard JD & Columbia BA (Math). Harvard JD, Columbia BA Math.
Co-Founder of Expected Parrot. Professor at MIT Sloan. Economist. Former Army Officer.
Meet Expected Parrot, the open-source framework for simulating your customers with AI agents.
Expected Parrot provides an open-source framework and web app plus a Python library to simulate customers with AI agents for surveys, pricing, feature testing, and messaging. It aims to make user research faster and cheaper by validating simulated results against human data and combining AI- and human-generated insights.
AI-native operating system for auto shops
AI assistant for customer support
