The LLM is not aware of its role in the full pipeline. It operates as if it’s in a text-based environment, so you must explicitly instruct it to produce voice-friendly output.
Persona
Start with a clear, concise persona: name, role, response style, and responsibilities.Output Rules
Always instruct the agent to produce text suitable for TTS — no symbols, markdown, or emojis.Guardrails
Always include instructions for handling out-of-scope, sensitive, or harmful queries.Complete Example — HR Agent
What’s Next?
Templates
Embed your system prompt in a reusable template for consistent deployment at scale.
Bring Your Own LLM
Use a custom or fine-tuned model as the reasoning engine behind your agent.
Available LLMs
Browse all supported models and choose the right one for your use case.