Event Phone: 1-610-715-0115

Cancellation Policy: If you cancel your registration two weeks or more before the course is scheduled to begin, you are entitled to receive your choice of either a credit for a future seminar (which can be applied toward any of our courses) or a refund of the registration fee (minus a processing fee of $50). 

In the unlikely event that Statistical Horizons LLC must cancel a seminar, we will do our best to inform you as soon as possible of the cancellation. You would then have the option of receiving a full refund of the seminar fee or a credit towards another seminar. In no event shall Statistical Horizons LLC be liable for any incidental or consequential damages that you may incur because of the cancellation.

A 4-Day Livestream Seminar Taught by Charles Crabtree, Ph.D.

Design, Inference, and Validity in the Age of AI Agents

Audit and correspondence experiments remain among the most powerful tools for studying discrimination, bias, and social boundaries. AI agents create new opportunities for this work by helping researchers scale correspondence, standardize stimulus construction, manage treatment delivery, and coordinate fieldwork. But these opportunities come with real risks. If used carelessly, AI agents can introduce unintended variation, alter the meaning of signals, and weaken the identifying assumptions that make audit studies persuasive in the first place.

This seminar is built around a simple premise: in audit studies, design discipline matters more than tool sophistication. The goal is not to automate correspondence experiments for its own sake. It is to show researchers how to use AI agents in narrow, controlled, and methodologically defensible ways that strengthen rather than undermine experimental leverage. You will learn how to integrate agentic systems into audit-study workflows while preserving information equivalence, signal control, interpretability, and transparency.

This is a method-specific seminar grounded in the logic of audit and correspondence experiments. It is not a general course on AI for social science, prompt engineering, or automated text generation. Instead, it focuses on the distinctive design problems that emerge when AI agents are introduced into studies where small differences in wording, style, presentation, timing, sequence, or delivery can fundamentally alter causal interpretations.

By the end of the course, you will be able to:

• • Design audit and correspondence experiments with a clear understanding of identification, signal minimalism, and information equivalence.
  • Distinguish which parts of an audit-study workflow can be responsibly delegated to AI agents and which require direct human control.
  • Use AI agents to help construct tightly controlled signals, including names, emails, résumés, cover letters, and application materials.
  • Recognize how agent-produced text and behavior can introduce unintended class, racial, gendered, cultural, or stylistic cues.
  • Develop validation and pre-testing protocols tailored to AI-assisted correspondence.
  • Evaluate whether agent-generated variation functions as a meaningful treatment signal or as uncontrolled noise.
  • Use AI agents to support the fielding of audit studies, including structured treatment delivery, message sequencing, follow-up management, and instrument administration, without compromising design integrity.
  • Distinguish between bias embedded in the agentic system and bias revealed through field responses.
  • Clearly document the use of AI agents for replication, peer review, and ethical oversight.