Voice debug monitor¶

Live debugging

Use the Voice Debug Monitor when you need evidence from a real call: what the caller said, what the agent heard, what context was sent, and when tools ran.

Debug the call path before rewriting prompts or changing multiple settings.

Use the Voice Debug Monitor when you need to see what happened during a live or test call while it is still unfolding. This is the fastest way to understand why the callback assistant asked the wrong question, missed a caller detail, or triggered a tool too early.

Where to find it¶

You can reach it in two places:

from the agent editor when the Debug step is available
from the agent actions menu on an existing voice agent

The page title in the product is Voice Debug Monitor.

What the monitor is for¶

Use it to inspect:

what the speech-to-text system actually heard
what the assistant said back
whether the backend debug stream is active
when tools executed
whether knowledge base content or conversation history was injected

For the callback assistant, this is the best place to verify that the agent collects the name, company, reason, and callback number in the right order.

Before you start¶

The monitor is most useful when:

the agent is already assigned to a phone number
you are placing a real or controlled test call
Debug enabled is turned on for the voice agent

If the page loads but nothing useful appears, check whether the Debug enabled switch is on and whether the backend state shows Backend Debug On.

What you will see¶

The debug page is organized around live call activity.

Status badges¶

At the top of the page you will see:

connection status
Backend Debug On or Backend Debug Off
the Debug enabled switch
the Clear timeline button

The Why updates can pause hint is expected. The stream may update slightly behind real time, but finalized speech, tool executions, and knowledge hits should still be reliable.

Caller Speech¶

This panel shows:

the current partial transcript
finalized utterances
silence gaps between utterances

Use this first when the callback assistant captures the wrong caller name, company, or phone number. If the speech transcript is wrong here, the problem is usually in recognition language, phrase list, or silence timing, not in the prompt.

Assistant Response¶

This panel reconstructs the assistant response from streaming chunks.

Use it to check:

whether the assistant stayed on script
whether it asked only one question at a time
whether it repeated itself
whether it responded too early or too late

For the callback assistant, a healthy sequence looks like:

greeting
caller name
company name
reason for the call
callback number confirmation
tool execution
clean closing line

What to check for the callback assistant¶

During a test call, watch for these specific signals:

The assistant skipped a question¶

If the assistant jumps from greeting directly to ending the call or triggering a tool, check:

the system prompt conversation flow
the Email Tool or API tool execution description
whether the conversation history is being included

The assistant forgot something the caller already said¶

Check both:

Conversation history limit is set in Technical
{conversation_history} is still present in the prompt

If either is missing, the assistant will sound stateless even when the rest of the flow is correct.

The assistant triggered a tool too early¶

This is one of the highest-value debug checks. If the Email Tool or API tool runs before all callback details are complete, the execution description is too loose or the prompt does not clearly gate the action.

For the callback assistant, the tool should not run until:

caller name is known
company name is known
reason for the call is known
callback number is confirmed

The company name or caller name is wrong¶

If the monitor shows the wrong transcription, improve:

recognition language selection
phrase list entries
silence timing if the model is clipping words

The assistant sounds repetitive¶

If the responses repeat or loop:

tighten the conversation flow in the prompt
keep one question per turn
reduce temperature if answers are drifting

Recommended debugging workflow¶

Use this order every time:

place a test call
watch Caller Speech
watch Assistant Response
confirm tool execution timing
make one change only
place the same test call again

Do not change speech settings, prompt logic, and tool execution rules all at once. You will not know which change fixed the issue.

Common callback-assistant checks¶

Name captured incorrectly¶

Start with Caller Speech and phrase list updates.

Callback number not confirmed¶

Check the prompt flow. The assistant should explicitly ask whether {caller_phone_number} is the correct callback number.

Email never sends¶

Check the tool execution description and the debug stream for the moment when the tool should have fired.

Email sends with missing fields¶

The tool fired too early. Tighten the trigger logic before changing the email template.

Read this next¶

Common Issues if the assistant behavior is still unstable
Agent Options for the prompt and technical settings behind the debug stream
Call History to review the finished result after the call ends