System Prompt Design for Voice Agents

AUG 19, 202608:30 - 09:00 AM (PT)30 MINS

Watch the recording

In this session, we'll explore how system prompt design shapes real-time voice AI behavior, from pacing and hesitation handling to confirmations, interruptions, tool calling, and recovery. Using a live Vapi demo, we'll compare approaches to system prompt design across the same use case to understand the implications of small changes. We will also discuss how model selection affects how your voice agent interprets and uses your system prompt. Attendees will leave with a practical framework for designing voice agents that can listen naturally, use tools reliably, and feel more patient, capable, and human in conversation.

About the speaker

Amanda Martin:

Amanda leads DevRel at Vapi, where she helps developers build great Voice AI agents. She brings over 10 years of experience, starting as a developer before moving into developer relations. A creative problem solver, she's currently focused on agent experience and how it shapes both the developers building agents and the agents themselves. When she's not deep in agent sessions, you can find her exploring SF, playing with her dogs, cycling, reading, or trying a new recipe.

More Sessions

KEYNOTE

Beyond Benchmarks: Evaluating Agents Against What They are Actually Supposed to Do

SESSION

Why RL Environments are all you need for building agents

PANEL

QE at Enterprise Scale - What Will a QE Org Look Like in 2027?

Join the builders, testers, and innovators shaping the next generation of web experiences.
Testμ Conf 2026 is where they meet.