Classify calls by outcome and intent

​

What is call classification?

Call classification sorts each call by its outcome and the caller’s intent. Tuner doesn’t know what a successful call looks like for your use case until you define it. Once you do, you can track your success rate, find the calls that failed, and see what callers ask for.

​

Call outcome

A call outcome is the result of a call from your business perspective. It answers the question: did this call achieve its goal? Each outcome has an Outcome Type of Success or Failure. What counts as each depends on your use case:

• For a sales agent, a successful outcome might be “Demo Scheduled” or “Purchase Completed”.
• For a support agent, it might be “Issue Resolved” or “Ticket Created”.
• For a booking agent, it might be “Appointment Confirmed”.

​

Call intent

A call intent is the reason the caller called. It answers the question: what did the caller want to accomplish? Tracking intents shows you what callers ask for most, which requests your agent struggles with, and the success rate per request type. For example, a restaurant booking agent might see intents like “Make Reservation”, “Cancel Reservation”, “Modify Reservation” or “Ask About Hours”.

​

Data extraction

The Data Extraction section on the same tab pulls structured values out of each call; see Data extraction.

​

Set up call classification

​

Best practices

• Start with the library: add library outcomes for common call endings first, then create custom outcomes for results specific to your business.
• Be specific: the more specific your prompt definitions, the more accurate the classification.
• Start small: begin with a few key outcomes and add more as you gather data.
• Use Stop Analysis for dead-end calls: turn it on for outcomes where further evaluation adds nothing, such as wrong numbers, spam or disconnected calls.
• Review regularly: check classified calls to make sure your definitions are still accurate.

​

Example: inbound lead qualification agent

This example sets up call classification for an inbound lead qualification agent. The agent handles incoming calls from potential customers, qualifies them against set criteria, and routes qualified leads to the sales team.

​

Call outcomes

List every way a call can end. Generic endings may already be in the outcome library; the qualification results are custom outcomes.

​

Call intents

​

Sample prompt definitions

Clear prompt definitions improve classification accuracy. For example: For “Qualified Lead - Meeting Booked”:

Classify as this outcome when ALL of the following are true:

1. The caller confirmed they are a decision maker or can influence the purchasing decision
2. The caller’s company meets our target criteria (mentioned company size, industry, or use case that fits)
3. A specific meeting date and time was confirmed during the call
4. The agent confirmed the meeting details (date, time, attendees) before ending the call

For “Not Qualified - Wrong Fit”:

Classify as this outcome when the caller does not meet qualification criteria. Look for indicators such as:

• Company size too small (e.g., “just me” or “small team of 2-3”)
• Industry we don’t serve (e.g., mentioned being in an unsupported vertical)
• Budget significantly below our minimum (e.g., “looking for something free” or mentioned budget under $X)
• Use case we don’t support (e.g., looking for features we don’t offer)

​

Read the results

With this setup, each call shows its outcome and intent, so you can see how many calls end in each outcome and what callers ask for most. For example, if many callers with the “Get Pricing Information” intent end as “User Hung Up Early”, your agent may be taking too long to give pricing.

​

Limits

Limits enforced by the dashboard forms:

​

Next steps