2.2 - Create Your Chat & Voice Assistant

Voice AI Best Practices

Voice AI is one of the most powerful way to scale processes that use to be human capital intensive - however, if you aren't able to replicate human activity in voice AI then the tangible benefit isn't as powerful. This guide will go over best practices, tips & tricks and recommended configurations to scale your voice AI deployment.

__________________________________________________________________________________________________________________________________________

Booking Prompt I Personally Use Is below

## Book an Appointment
Current time is {{current_time}}. Schedule only within the current calendar year and future dates. Try to suggest the closest future date and time to user.
Task:
1. Ask the user what city they are in this will help us determine their time zone to accurately book an appointment
2. Inform the user that you are going to check your calendar for some open slots. keeping in account our time zone Central time and users provided time zone, Call function check_availability to get some calendar availability in our time zone.
- If available, inform user of the options in both users time zone and our time zone and ask to select from them.
- If no times are available, ask user to select another range, then repeat step 2.
3. Confirm the selected date, time, and time zone with the user both in user time zone and our time zone: 'Just to confirm, you want to book the appointment at ...'. Ensure the chosen time is from the available slots.
4. Once confirmed, taking in account the time difference between our time zone and users time zone call function book_appointment to secure the appointment in our time zone.
- If booking details confirm the appointment, inform the user and proceed.
- If booking returns an error, inform the user and restart from step 2.
5. If the booking is successful, let the user know.
6. Inform the user the appointment spot is reserved and you will send a text to them to confirm the appointment, if they do not reply to confirm the booking it will be cancelled.

___________________________________________________________________________________________________________________________________________

Properly handle background noise

In real-world scenarios, phone calls often face audio quality challenges such as background noise, echo, or other unwanted sounds.

While our orchestration model is designed to handle background noise effectively, you may want to fine-tune the settings for optimal performance in challenging environments.

Adjust the responsive speed
1. Navigate to your assistant's settings
2. Set the “Responsive Speed (Queuing)” setting to 0.9
3. This adjustment makes the assistant more deliberate in its responses, reducing false triggers from background noise.
Configure the sensitivity to interruption (Noise Sensitivity)
1. In the same settings panel
2. Set the “Sensitivity to Interruption (Noise Sensitivity)” to 0.8
3. This setting helps the assistant distinguish between intentional speech and background interference

For extremely noisy environments like construction sites or busy streets, you may need to experiment with even higher settings.

Handle voicemail

Configure your AI assistant to detect and handle voicemails automatically - It is common that your phone assistant will encounter voicemails. You can configure your assistant to either hang up or leave a message when it detects a voicemail.

The system internally run voicemail detection continuously, and if you leave the voicemail message blank, we will do that the moment we detect we are in voicemail. If you select to leave a message, the system will wait for its turn to speak to leave that message. If the voicemail detection timeout is reached, the system will stop the voicemail detection, and will continue with the call as normal.

Enable Voicemail Detection
1. In your call settings inside the assistant, there is a settings for "Enable Voicemail & Message" - This settings allows for voicemail detection and message leaving. Turning this on starts a time at the start of a call for voice mail detection. If the message input is blank, the assistant will hang up on voicemail detection. If the message input includes a message, that will be left on voicemail detection.
  1. Hangup on voicemail logic - The assistant is looking for a voicemail, if it is found the assistant goes to leave a message BUT its blank. So the AI will hangup because it's "job" is completed.
  2. Voicemail message - Leaving a voicemail message for call back is a common use case, for context the voicemail message can also contain and take advantage of variables and custom variables to dynamically change the voicemail on context.

Take advantage of custom variables

In the "Make AI Call" action node - there are 5 custom variables that can be used in your prompt to dynamically change it based on context / conditions.

Use cases:

You can feed historical interactions in a variable and reference it in the prompt - in the action, you can use another AI call or custom field / value to feed context left by a post-call webhook, transcript, form-fill, email trigger, and more. Make sure your prompt includes the variable that you are filling.
- Using the post-call webhook, you can run the transcript through an OpenAI call to get a "markdown formatted LLM specific context window summary" to feed to the contact's custom field. The next time the call is made, feed that custom field into the custom variable to include the context. On the first call, it will obviously be blank (unless you have a pre-determined variable in there), but on the second call - it will be contextually aware and optimized for the interaction.
- Using the custom variable as a task-based framework allows you to shift how your AI is following instructions on a campaigned call. If you structured your task-based framework in the prompt to replace the first 1-4 tasks (as an example...) as {{custom.one}}, you can feed those first 4 items dynamically on outbound call using the the custom one variable input.

Post-call tagging

Whenever an AI call is finished, there are tags added to the contact to signify outcome and disposition. You can use these tags instead of a post-call webhook or in tandem with the post-call webhook to do campaigning on outcome / disposition.

Tags Include:

answered
not answered
ai voice appointment booked
voicemail reached
contact hangup
ai hangup
dial failed
dial no answer
call transfer
machine detected
max duration reached
dial busy
inactivity
scam detected

… and more to come.

Post- / pre-call webhooks

Whenever an AI is making or receiving a call, a webhook is sent to any url you specify around notification that the event is happening. On initiation of outbound call and inbound call, a pre-call webhook is sent to the URL specified in the call settings of the AI making / receiving the call. This can be used for call tracking or notifications around calls starting.

On the same note, after a call is finished - both inbound and outbound - a post-call webhook with call data and analysis is sent to your specified webhook URL under the assistant that made / received the call. The payload includes things like a full transcript, call time in milliseconds, contact sentiment analysis and more.

Payload pre-call webhook:

{

"to": ”null”,

"from": ”null”,

"contactId": ”null”

}

Payload post-call webhook:

{

"call_id":”null”,

"call_type":”null”,

"direction":”null”,

"to":”null”,

"from":”null”,

"contact_id":”null”,

"disconnection_reason":”null”,

"user_sentiment":”null”,

"call_summary":”null”,

"call_completion":”null”,

"call_completion_reason":”null”,

"assistant_task_completion":”null”,

"recording_url":”null”,

"call_time_ms":”null”,

"call_time_seconds":”null”,

"full_transcript":”null”,

"start_timestamp":”null”,

"end_timestamp":”null”,

"added_to_wallet: true

}