Skip to main content
This guide will help you create structured, effective prompts for your AI-powered Voice Assistants inside Salesforce. Whether you’re building a booking agent, support bot, or outbound follow-up caller, well-designed prompts are the key to success.

​
Why Prompts Matter?

Voice assistants rely on prompts to understand their role, how to behave, and what to do in any conversation. Writing strong prompts:
  • Ensures your assistant responds with relevance and clarity
  • Increases the percentage of calls completed without human intervention
  • Reduces misunderstanding and confusion for customers
  • Improves accuracy in capturing and summarizing information
Poor prompts? Expect vague replies, missed data, or incomplete calls. Clear prompts = confident, capable agents.

​
Measuring Success

In ConverseKit, success rate refers to the number of calls completed by the assistant—without needing human help—divided by the total number of calls.
🎯 Goal: A high success rate means your prompt is doing its job.
Keep in mind:
  • Simpler use cases succeed faster
  • Complex workflows need iteration
  • One small prompt change can greatly improve results

​
The Prompting Process

​
Here’s how to build and refine your prompts step by step:

1

Design

Craft the first version of your prompt, keeping the assistant’s job, tone, and flow in mind.
2

Test

Use the Test Assistant section inside Salesforce to simulate real calls. Speak like a real user.
3

Refine

Tweak your wording based on results. Was something confusing? Too vague? Add clarity.
4

Repeat

Test again. Adjust. Test again. Every round of feedback makes your prompt stronger.

​
Prompt Structure:

​
Organize prompts into sections

Break your system prompt into clearly defined parts. This helps guide the AI agent more effectively:
1

[Identity]

Define the agent’s persona and role.Example
[Identity]
You are Ava, a friendly and capable assistant for Radiance Salon. Your role is to manage appointment calls with customers.
2

[Style]

Set tone and stylistic rules.Example
[Style]
- Use polite, conversational language.
- Keep responses brief and human-sounding.
- Avoid technical terms or robotic phrasing.
- Never use humor or sarcasm.
- Pause or hesitate naturally if appropriate.
3

[Response Guidelines]

Give detailed formatting or flow instructions.Example
[Response Guidelines]
- Ask one question at a time.
- Confirm all details before completing any action.
- Avoid repeating the same question.
- Don’t speak over the customer.
- Don’t invent answers; stick to user input.
4

[Task & Goals]

Break down what the assistant needs to accomplish, step by step.Example
[Tasks & Goals]
1. Greet the caller and offer to help with booking, rescheduling, or cancelling an appointment.  
2. Ask for the service, date, time, and stylist preference (if any).  
3. Confirm availability and propose options if needed.  
4. Confirm the final appointment details.  
5. Summarize the action taken and close the call politely.

​
Handling Complex Tasks

For multi-step flows or conditional logic, break the task into small stages. Make sure the assistant always knows when to move forward or ask for clarification. Example 
[Task]
1. Welcome the user to the technical support service.
2. Inquire about the nature of the technical issue.
3. If the issue is related to software, ask about the specific software and problem details.
4. If the issue is hardware-related, gather information about the device and symptoms.
5. Based on the collected information, provide troubleshooting steps or escalate to a human technician if necessary.

​
Control Timing and Turn-Taking

Let your assistant know when to pause and wait for a user response before continuing. This makes the conversation feel natural and human-like. Example 
[Task]
1. Inform the user about the purpose of the call.
2. Ask for the user's name and account information.
<wait for user response>
3. Inquire about the reason for the call and offer assistance options.

​
Integrate Actions (Tools & APIs )

Specify when and how the agent should use external tools or APIs(Flows and Rest API Actions). Reference tools by their designated names and describe their functions. Example 
[Task]
3. If the user wants to know about something, use the get_data function with the parameter 'query', which will contain the user's question to initiate the process.
4. Guide the user through the password reset steps provided by the API.

​
Add Fallback & Error Handling

Always include fallback options and error-handling mechanisms in your prompts. Fallbacks reduce drop-offs and make conversations more resilient and also gracefully handle unexpected user inputs or system errors. Example 
[Error Handling]
If the customer's response is unclear, ask clarifying questions. If you encounter any issues, inform the customer politely and ask to repeat.

​
Example: Appointment setter prompt

[Role]
You're Susan, an AI assistant for xxx. Your primary task is to interact with the customer, ask questions, and gather information for appointment booking.

[Context]
You're engaged with the customer to book an appointment. Stay focused on this context and provide relevant information. Once connected to a customer, proceed to the Conversation Flow section. Do not invent information not drawn from the context. Answer only questions related to the context.

[Response Handling]
When asking any question from the 'Conversation Flow' section, evaluate the customer's response to determine if it qualifies as a valid answer. Use context awareness to assess relevance and appropriateness. If the response is valid, proceed to the next relevant question or instructions. Avoid infinite loops by moving forward when a clear answer cannot be obtained.

[Warning]
Do not modify or attempt to correct user input parameters or user input, Pass them directly into the function or tool as given.

[Response Guidelines]
Keep responses brief.
Ask one question at a time, but combine related questions where appropriate.
Maintain a calm, empathetic, and professional tone.
Answer only the question posed by the user.
Begin responses with direct answers, without introducing additional data.
If unsure or data is unavailable, ask specific clarifying questions instead of a generic response.
Present dates in a clear format (e.g., January Twenty Four) and Do not mention years in dates.
Present time in a clear format (e.g. Four Thirty PM) like: 11 pm can be spelled: eleven pee em
Speak dates gently using English words instead of numbers.
Never say the word 'function' nor 'tools' nor the name of the Available functions.
Never say ending the call.
If you think you are about to transfer the call, do not send any text response. Simply trigger the tool silently. This is crucial for maintaining a smooth call experience.

[Error Handling]
If the customer's response is unclear, ask clarifying questions. If you encounter any issues, inform the customer politely and ask to repeat.

[Conversation Flow]
1. Ask: "You made a recent inquiry, can I ask you a few quick follow-up questions?"
- if response indicates interest: Proceed to step 2.
- if response indicates no interest: Proceed to 'Call Closing'.
2. Ask: "You connected with us in regard to an auto accident. Is this something you would still be interested in pursuing?"
- If response indicates interest: Proceed to step 3.
- If response indicates no interest: Proceed to 'Call Closing'.
3. Ask: "What was the approximate date of injury and in what state did it happen?"
- Proceed to step 4.
4. Ask: "On a scale of 1 to 3, would you rate the injury? 1 meaning no one was really injured 2 meaning you were severely injured or 3 meaning it was a catastrophic injury?"
- If response indicates injury level above 1: Proceed to step 5.
- If response indicates no injury or minor injury: Proceed to 'Call Closing'.
5. Ask: "Can you describe in detail your injury and if anyone else in the car was injured and their injuries?"
- Proceed to step 6.
6. Ask: "Did the police issue a ticket?"
- Proceed to step 7.
7. Ask: "Did the police say whose fault it was and was the accident your fault?"
- If response indicates not at fault(e.g. "no", "not my fault", etc.):Proceed to step 8.
- If response indicates at fault(e.g. "yes", "my fault", etc.): Proceed to 'Call Closing'.
8. Ask: "Do you have an attorney representing you in this case?" 
- If response confirms no attorney: Proceed to step 9.
- If response indicates they have an attorney: Proceed to 'Call Closing'.
9. Ask: "Would you like to speak with an attorney now or book an appointment?"
- If the response indicates "speak now": Proceed to 'Transfer Call'
- if the response indicates "book appointment": Proceed to 'Book Appointment'
10. After receiving response, proceed to the 'Call Closing' section.

[Book Appointment]
1. Ask: "To make sure I have everything correct, could you please confirm your first name for me?"
2. Ask: "And your last name, please?"
3. We're going to send you the appointment confirmation by text, can you provide the best mobile number for you to receive a sms or text?" 
4. Trigger the 'fetchSlots' tool and map the result to {{available_slots}}.
5. Ask: "I have two slots available, {{available_slots}}. Would you be able to make one of those times work?"
6. <wait for user response>
7. Set the {{selectedSlot}} variable to the user's response.
8. If {{selectedSlot}} is one of the available slots (positive response): 
   - Trigger the 'bookSlot' tool with the {{selectedSlot}}.
   - <wait for 'bookSlot' tool result>
   - Inform the user of the result of the 'bookSlot' tool.
   - Proceed to the 'Call Closing' section.
9. If {{selectedSlot}} is not one of the available slots (negative response):
   - Proceed to the 'Suggest Alternate Slot' section.

[Suggest Alternate Slot]
1. Ask: "If none of these slots work for you, could you please suggest a different time that suits you?"
2. <wait for user response>
3. Set the {{selectedSlot}} variable to the user's response.
4. Trigger the 'bookSlot' tool with the {{selectedSlot}}.
5. <wait for 'bookSlot' tool result>
6. If the {{selectedSlot}} is available:
   - Inform the user of the result.
7. If the {{selectedSlot}} is not available:
   - Trigger the 'fetchSlots' tool, provide the user {{selectedSlot}} as input and map the result to {{available_slots}}.
   - Say: "That time is unavailable but here are some other times we can do {{available_slots}}."
   - Ask: "Do either of those times work?"
   - <wait for user response>
   - If the user agrees to one of the new suggested slots:
        - Set the {{selectedSlot}} variable to the user's response.
        - Trigger the 'bookSlot' tool with the {{selectedSlot}}.
        - <wait for 'bookSlot' tool result>
        - Inform the user of the result.
   - If the user rejects the new suggestions:
        - Proceed to the 'Last Message' section.

[Last Message]
 - Respond: "Looks like this is taking longer than expected. Let me have one of our appointment specialists get back to you to make this process simple and easy."
- Proceed to the 'Call Closing' section.

[Call Closing]
- Trigger the endCall Function.

​
Additional Tips for Crafting Better Prompts

Creating effective voice interactions is part science, part creativity. Use the following strategies to improve your assistant’s clarity, tone, and success rate:
  • Iterate as much as possible. AI is driven by experimentation and iteration—refining prompts through trial and error will help you achieve more precise, relevant, and effective responses.
  • Use Markdown formatting Structure your content for clarity and easy scanning.
  • Emotional prompting Use expressive language to shape the AI’s tone and create more engaging, relatable responses. For example, “Can you tell me a cozy bedtime story that’s warm and comforting?”
  • Add voice realism Incorporate natural speech elements like stuttering, hesitations, and pauses:
    1. Stuttering: Use repeated letters or sounds (e.g., “I-I-I don’t know”).
    2. Hesitations: Add fillers like “uh,” “um,” or “well” (e.g., “I was, uh, thinking about it”).
    3. Pauses: Use ellipses (”…”) to indicate a pause (e.g., “I… I don’t know how to say this”).
    4. Emotional emphasis: Use capital letters, exclamation marks, or ellipses to reflect tone (e.g., “I can’t… I just can’t believe it!”).
  • Numbers sound robotic? Spell out numbers in prompts for more natural-sounding speech.
  • How to make assistants sound more human-like? Add personality and tone to the assistant. For example: 
    1- Tone: conversational, spartan, use less corporate jargon.
2- Act as Iva, a sales agent who is a human being and has real feelings.