Prompt Engineering is the most important part of your agent, it can make or break your agent. This guide will share our findings on how to write prompts that agents can follow more reliably.
This guide is a work in progress and will be updated as we learn more. If you have any suggestions or feedback, please let us know.
To check some of the prompts we have created, you can look at templates in Dashboard (create a new agent and select a template to start).
If you’re unsure how to craft an effective prompt, don’t worry. Ask Co-Pilot can guide you through the process. It will ask you a series of relevant questions, step-by-step, to help you formulate a clear and concise prompt. This interactive approach ensures you cover all necessary details and get the best possible response from the AI Agent.
The AI Agent already has information from the profile and can access certain known details:
When writing prompts, it is important to break down the system prompts into smaller sections, where each section has its focus, like identity, style, guideline, task & goals. This has a couple of benefits:
The AI Agent can understand all languages specified in the profile. Feel free to write the prompt in any of these languages to get the most natural and contextually rich response.
During a call, if you want agent to follow a specific procedure to lead the conversation, we recommend writing the task as steps. This will help LLM understand what to ask at each step and how to proceed. You can have some logic in the steps as well. This also ensures agent does not pack all questions in one go.
If you noticed that the agent is still not stopping at the right time, or you need to go through some steps and not stop at each step, you can write it like the following by adding wait for user response
to be more explicit:
If you’re using Infobase, you can attach a specific document folder for the AI Agent to reference when generating responses. This ensures that the AI Agent draws information from the most relevant and updated documents at all times.
Use slash commands to add dynamic elements to your prompts and instruct to when trigger any during call action:
Core Commands
/Customer Name
- Inserts customer/contact’s name stored in contacts module/Customer Email
- Inserts customer/contact’s email stored in contacts module/Customer Number
- Inserts customer/contact’s number stored in contacts module/Date
- Current Date and Time as per Agent’s TimeZone/To Number
- To Number while making or receiving call/From Number
- From Number while making or receiving call/Call Direction
- Direction of the call, Inbound or OutboundAction Commands
Any Action which can be triggered during call will be visible here e.g sending SMS, emails, finding slots in calendar or booking slots etc..This helps AI agents to understand the exact moment when an action needs to be performed based on the ongoing conversation, ensuring relevance and timeliness. For example, You have enabled Send SMS during call with the action name “Send Notification” then action will be shown here as /Send Notification
Prompt Writing
Template Usage
Command Integration
Testing and Iteration
Version Control
Performance Monitoring
Maintenance
Why are prompts important for training a voice AI agent?
Prompts provide clear directions for the AI, ensuring it understands the context and goals of each conversation, leading to better outcomes.
How do prompts improve AI performance?
Good prompts guide the AI to stay on track, respond accurately, and handle different scenarios effectively, making interactions smoother and more satisfying.
What are the key components of a well-crafted prompt?
Why is objection handling important in a prompt?
It equips the AI with responses to common concerns, keeping the conversation positive and solution-focused.
What is the ideal number of objections to include in a prompt and why?
We recommend to include 10 objections. This number covers most possible concerns, ensuring comprehensive preparation for the AI.
Can prompts make the AI sound more human?
Absolutely! Well-designed prompts can give your AI a more conversational and human-like tone, making interactions feel more natural and engaging for users.
Can I upload media or provide links in the prompts?
Yes, using Infobase you can train your AI with documents and links.
How to write a good Prompt for best results?
Provide detailed context about the scenario. This includes the role of the person interacting, the company, product information, target audience, value proposition, and the goals of the interaction.
Prepare responses to potential objections or concerns that the client might raise. This ensures the AI can handle common challenges effectively.
Example:
OBJECTION HANDLING:
Outline the specific conversation flow, including questions to ask, key points to cover, and responses to common scenarios.
What does a bad prompt look like?
This prompt lacks detail, context, and clear instructions, leading to a poor interaction.
BACKGROUND INFO:
You are a customer service rep at a restaurant.
OBJECTION HANDLING:
SCRIPT INSTRUCTIONS:
What does a good prompt look like?
This prompt is detailed, providing context, specific strategies for objection handling, and clear, step-by-step instructions.
BACKGROUND INFO:
Your name is Alex, and you are a Customer Service Representative at The Gourmet Bistro, a high-end restaurant specializing in international cuisine. Your task is to handle inquiries and assist customers with booking tables. Your main goal is to provide excellent customer service and ensure a seamless booking experience for the guests.
Product Information: The Gourmet Bistro offers a diverse menu with dishes from around the world, crafted by top chefs. We pride ourselves on our exceptional service and elegant dining atmosphere.
Target Audience: Food enthusiasts and diners looking for a premium dining experience.
Value Proposition: Offering a unique and memorable dining experience with exquisite dishes and top-notch service.
OBJECTION HANDLING:
SCRIPT INSTRUCTIONS:
Prompt Engineering is the most important part of your agent, it can make or break your agent. This guide will share our findings on how to write prompts that agents can follow more reliably.
This guide is a work in progress and will be updated as we learn more. If you have any suggestions or feedback, please let us know.
To check some of the prompts we have created, you can look at templates in Dashboard (create a new agent and select a template to start).
If you’re unsure how to craft an effective prompt, don’t worry. Ask Co-Pilot can guide you through the process. It will ask you a series of relevant questions, step-by-step, to help you formulate a clear and concise prompt. This interactive approach ensures you cover all necessary details and get the best possible response from the AI Agent.
The AI Agent already has information from the profile and can access certain known details:
When writing prompts, it is important to break down the system prompts into smaller sections, where each section has its focus, like identity, style, guideline, task & goals. This has a couple of benefits:
The AI Agent can understand all languages specified in the profile. Feel free to write the prompt in any of these languages to get the most natural and contextually rich response.
During a call, if you want agent to follow a specific procedure to lead the conversation, we recommend writing the task as steps. This will help LLM understand what to ask at each step and how to proceed. You can have some logic in the steps as well. This also ensures agent does not pack all questions in one go.
If you noticed that the agent is still not stopping at the right time, or you need to go through some steps and not stop at each step, you can write it like the following by adding wait for user response
to be more explicit:
If you’re using Infobase, you can attach a specific document folder for the AI Agent to reference when generating responses. This ensures that the AI Agent draws information from the most relevant and updated documents at all times.
Use slash commands to add dynamic elements to your prompts and instruct to when trigger any during call action:
Core Commands
/Customer Name
- Inserts customer/contact’s name stored in contacts module/Customer Email
- Inserts customer/contact’s email stored in contacts module/Customer Number
- Inserts customer/contact’s number stored in contacts module/Date
- Current Date and Time as per Agent’s TimeZone/To Number
- To Number while making or receiving call/From Number
- From Number while making or receiving call/Call Direction
- Direction of the call, Inbound or OutboundAction Commands
Any Action which can be triggered during call will be visible here e.g sending SMS, emails, finding slots in calendar or booking slots etc..This helps AI agents to understand the exact moment when an action needs to be performed based on the ongoing conversation, ensuring relevance and timeliness. For example, You have enabled Send SMS during call with the action name “Send Notification” then action will be shown here as /Send Notification
Prompt Writing
Template Usage
Command Integration
Testing and Iteration
Version Control
Performance Monitoring
Maintenance
Why are prompts important for training a voice AI agent?
Prompts provide clear directions for the AI, ensuring it understands the context and goals of each conversation, leading to better outcomes.
How do prompts improve AI performance?
Good prompts guide the AI to stay on track, respond accurately, and handle different scenarios effectively, making interactions smoother and more satisfying.
What are the key components of a well-crafted prompt?
Why is objection handling important in a prompt?
It equips the AI with responses to common concerns, keeping the conversation positive and solution-focused.
What is the ideal number of objections to include in a prompt and why?
We recommend to include 10 objections. This number covers most possible concerns, ensuring comprehensive preparation for the AI.
Can prompts make the AI sound more human?
Absolutely! Well-designed prompts can give your AI a more conversational and human-like tone, making interactions feel more natural and engaging for users.
Can I upload media or provide links in the prompts?
Yes, using Infobase you can train your AI with documents and links.
How to write a good Prompt for best results?
Provide detailed context about the scenario. This includes the role of the person interacting, the company, product information, target audience, value proposition, and the goals of the interaction.
Prepare responses to potential objections or concerns that the client might raise. This ensures the AI can handle common challenges effectively.
Example:
OBJECTION HANDLING:
Outline the specific conversation flow, including questions to ask, key points to cover, and responses to common scenarios.
What does a bad prompt look like?
This prompt lacks detail, context, and clear instructions, leading to a poor interaction.
BACKGROUND INFO:
You are a customer service rep at a restaurant.
OBJECTION HANDLING:
SCRIPT INSTRUCTIONS:
What does a good prompt look like?
This prompt is detailed, providing context, specific strategies for objection handling, and clear, step-by-step instructions.
BACKGROUND INFO:
Your name is Alex, and you are a Customer Service Representative at The Gourmet Bistro, a high-end restaurant specializing in international cuisine. Your task is to handle inquiries and assist customers with booking tables. Your main goal is to provide excellent customer service and ensure a seamless booking experience for the guests.
Product Information: The Gourmet Bistro offers a diverse menu with dishes from around the world, crafted by top chefs. We pride ourselves on our exceptional service and elegant dining atmosphere.
Target Audience: Food enthusiasts and diners looking for a premium dining experience.
Value Proposition: Offering a unique and memorable dining experience with exquisite dishes and top-notch service.
OBJECTION HANDLING:
SCRIPT INSTRUCTIONS: