Sister Chapter Event – AI in L&D: Advanced with FL Suncoast Chapter

AI in L&D - Advanced

with FL Suncoast Chapter

From Prompting to Prototyping: Designing AI-Powered Customer Practice and Coaching Systems

Session #2 (Beginners) Details

This advanced session is designed for learning and development professionals who want a practical, design-first understanding of how AI-powered practice and coaching experiences can be built and evolved in real learning environments.

Participants will see a live demonstration of a fully working AI-powered customer simulator that allows learners to practice realistic customer conversations and receive immediate, structured coaching feedback. The session shows how AI can be intentionally designed to act both as a realistic customer and as a consistent coach, creating safe, repeatable practice that builds confidence and skill.

The presenter will then walk through how the simulator was first designed as a GPT-based solution and explain why and how it later evolved into a more integrated Realtime API implementation. Rather than focusing on code, the session emphasizes the learning design decisions behind each version, including role definition, guardrails, scenario design, evaluation logic, and system constraints.

Participants will leave with a clear mental model for prototyping, iterating, and evaluating AI-powered customer practice systems, and for choosing the right level of technical complexity based on learner needs, workflow, scale, and cost.

Objectives

By the end of this advanced session, participants will be able to:

• Describe how an AI-powered customer practice and coaching simulator works end-to-end, from learner interaction through coaching feedback.
• Identify key design elements of a production-ready GPT-based simulator, including role definition, guardrails, scenario structure, phase logic, and evaluation criteria.
• Explain how the same learning design can be extended into a Realtime API solution and what additional capabilities that enables.
• Determine when a GPT-based approach is sufficient versus when a more custom Realtime API solution is appropriate.
• Apply an inquiry-driven approach to prototyping and iterating AI-powered practice experiences.

What You’ll Walk Away With

• A clear picture of how a production-ready AI-powered practice simulator is structured from learner experience through coaching feedback.
• A concrete example of how a GPT-based simulator can be designed using clear instructions, guardrails, and evaluation logic.
• A high-level understanding of how that same design can be extended into a Realtime API solution, including the major front end and back end components.
• A reusable set of inquiry prompts and example chat logs that show how to move from ideas to draft implementations, test them, and improve them iteratively.
• Practical guidance for choosing between a GPT-based approach and a Realtime API solution based on workflow, integration needs, scale, and cost considerations.

Note: While attending ATD Suncoast events, please be aware that photography, audio, and/or video recording may occur. Your attendance serves as your implied consent for ATD Florida Suncoast Chapter, Inc. to use your image in marketing and social media materials.