Skip to main content

​
Designing Prompts for AI Voice Agents

The effectiveness of your AI voice agents largely relies on the quality of the prompts you design. A well-crafted prompt guides the language model (LLM) to interact in a relevant, natural manner and aligns with your business objectives. This page details the fundamental principles and best practices for creating high-performance prompts for Volubile phone agents.

​
The Foundations of Prompt Writing

A prompt is the initial instruction you provide to the LLM. It defines the context, the task to be accomplished, the tone to adopt, and the constraints to respect.

​
Clarity and Precision

The LLM interprets your instructions literally. Therefore, be as clear and precise as possible.

Avoid Ambiguities

Vague terms can lead to unexpected and inconsistent responses.

Define Jargon

If your field uses specific vocabulary, clarify it in the prompt.

Specify Format

Be explicit about the expected output format if necessary.

​
Provide Context

The more relevant context the LLM has, the better it can tailor its response to the specific situation.
Describe not only the agent’s function but also their “personality” to achieve the desired tone.

​
Use Examples (Few-Shot Prompting)

Providing concrete examples of questions and expected answers can significantly enhance the model’s performance, especially for complex tasks or specific formats.
Include varied examples, including difficult situations or special cases, to prepare the agent for all possible scenarios.

​
Define Constraints

Clearly indicate what the agent should not do or say to avoid undesirable behaviors.
  • Response Length: “Limit your responses to 2 or 3 concise sentences to maintain a natural conversational pace over the phone.”
  • Style: “Adopt a professional and empathetic tone. Avoid technical jargon unless the user seems comfortable with those terms.”
  • Structure: “Structure your explanations in clear, numbered steps when giving instructions.”
  • Confidential Information: “Never ask for the user’s full password. Do not disclose any personal information about other customers.”
  • Service Limitations: “Do not make promises that the company cannot keep. If you don’t know the answer, offer to transfer the call to a specialist.”
  • Sensitive Topics: “Avoid discussions on political, religious, or controversial issues, even if the user brings them up.”
  • Nature of the Agent: “Specify that you are an AI assistant if asked.”
  • Legal Disclaimers: “For calls regarding contracts, always specify that ‘This call is recorded for training and quality control purposes.’”

​
Optimizing Prompts

Creating prompts is an iterative process. Continuously test and refine your prompts to achieve the best results.

​
Iteration and Testing

1

Start Simple

Begin with a basic prompt that covers essential functionalities.
2

Test with Varied Scenarios

Pose simple, complex, unexpected, or poorly formulated questions to the agent to assess its robustness.
3

Analyze Responses

Identify weaknesses and note cases where the agent deviates from the desired behavior.
4

Adjust and Strengthen

Modify the prompt by enhancing problematic instructions. Using superlatives like “it is very important that” can help reinforce certain constraints.
5

Repeat the Process

Continue testing and refining until satisfactory performance is achieved across all scenarios.

​
Structuring the Prompt

Use delimiters (such as ###) to clearly structure the different sections of your prompt (context, instructions, examples, constraints). This helps the LLM better understand the request.

​
Watch the Length

While context is important, an excessively long prompt can introduce noise and dilute key instructions. Focus on relevant information for the task at hand.