In your company settings page, click Trackers. This will open the Smart Trackers tab by default.

If this is the first time that anyone in your company has used the feature, you’ll need to unlock it first.
Unlocking smart trackers enables us to prepare your calls so that they can be used to build the tracker’s AI model. This process takes up to 2 days. When the processing is done, you’ll be notified by email and can start building your first smart tracker.
How many calls do you need to get started?
Smart trackers are built using an AI model, and this model needs at least 500 calls for training. Best results are achieved with at least 1500 calls. If you have less than 1500 calls, track a concept that is fairly common in your calls. This enables us to provide the model with many examples of sentences from your calls that positively match the concept, and this is important for building a strong smart tracker.
Tip
Your org or workspace doesn’t have 500 calls yet? Or maybe it does, but the concept you want to track isn’t that common. In such cases, you may want to build a keyword tracker, which surfaces words and phrases in your calls. For more, see this.
-
Click + CREATE TRACKER.
-
Think of a concept you want to track.
-
Set up the tracker by giving it a name and description that reflect this concept. These should be meaningful enough so that people at your company who see the tracker understand what it’s tracking.
-
Filter the types of calls you want this tracker to be trained on. For example, outbound calls, external calls, calls in a certain stage of the deal. These filters help focus the tracker, so it produces more accurate results. They also determine which calls the tracker can work on after it’s activated.
-
Give at least 5 examples of real sentences from your calls that fit this concept. Using these sentences, we'll create a set of sentences that match (or don't match) your concept.
-
Tag the sentences to train the AI model to identify which types of sentences match your concept, and which ones don’t. Basic training for the model requires 4 rounds of tagging. Each round contains 25 sentences.
-
After 4 rounds of tagging, review the tracker to see if it’s producing accurate results.
-
Results look good? Activate the tracker. Want more accurate results? Keep training the tracker by completing more rounds of tagging.
Tracker name: This is the name you’ll see everywhere the tracker appears, so choose a name that is short yet meaningful. For example, “pricing objections” is better than “”pricing” or “customers who say that the price is too high.
Description: Describe the concept behind the tracker so that any who see this tracker understands what it is tracking. This description will appear when anyone hovers the tracker name.

Tracker filters: Filters narrow down the types of calls that the tracker will be applied to, so you get accurate, meaningful results. Mandatory filters that you’ll set here include the following:
-
Track when said by: Decide whether you want the tracker to be applied to what your team says, what the customer says, or both.
-
Web conference or telephony calls: Set whether the tracker is applied to outbound calls, inbound calls, conference calls. You can also choose all three.
-
Internal or external: Set whether the tracker is applied to calls that took place amongst team members only, or those that took place with customers, too.
If you want to further specify which calls the tracker is applied to, click More filters and you’ll see the following optional filters:
-
When it was said
-
During which opportunity stage
-
By which team
For example, let’s say you want to track how your customer support team is introducing themselves on calls from customers. You can choose to apply the tracker to:
Inbound calls: From customers to the support center
External calls: Involve team members and customers
Said during: The first 5 minutes of the call, in the discovery stage, by the Customer Support team.
Once you’ve set these filters, click NEXT and you’ll move to the page where you provide example sentences.
Important
Once you set filters for which types of calls you’ll train the tracker on, these filters will be applied going forward and cannot be changed. So, if you train the tracker on inbound calls only, you’ll only be able to use the tracker on inbound calls. If you train the tracker on Jane Smith’s team only, you’ll only be able to use the tracker on Jane Smith’s calls.
Once you’ve prepared the tracker settings, you’re ready to start building the AI model. The first step is giving example sentences.

These sentences are what the AI model uses to ‘understand’ what you are looking for. Provide at least 5 examples of real sentences from real calls that you want the tracker to surface.
Quick tips for writing great example sentences
-
Use real sentences that people really say. Check your calls or talk tracks to find them.
-
Keep the sentences short and precise.
-
“Tell me a bit more about the main challenges you’re facing right now.
-
-
Choose sentences that have different words.
-
"This is John on a recorded line."
-
"My name is Claire and I’m calling from a monitored line."
-
-
Use a variety of sentence types.
-
"That’s just not in our price range."
-
"Could you go any lower on that cost?"
-
-
Look for sentences that are specific, not general.
-
"Our main priority is driving higher conversion rates through the sales funnel."
-
-
Make sure each example is a single sentence only.
Using these sentences, we’ll create a set with sentences from your existing calls. Training the model involves tagging these sentences to indicate whether or not they fit your concept.
Using the sample sentences you provided, we created a set of sentences from your existing calls. Some of these sentences are similar to your sentences; some of them aren’t. Now, you’ll tag the sentences so the model learns which one fit your model and which ones don’t.
-
Tag the sentences YES if they fit your concept.
-
Tag the sentences NO if they don't fit your concept.
-
Tag the sentences NOT SURE if you’re not sure.

The sentences you’ll be tagging are in bold. The sentences that are not in bold, before and after the bolded sentences, are here to give you context.
Want to hear the snippet to be sure of the context? Go ahead and click Go to call in the bottom right.
Each round of tagging includes 25 sentences: During the first 4 rounds, you’re building the model. Expect to tag many calls of the NO, and that’s just fine. That’s part of the process of training the model. The model can’t learn with only YES tags, because then it doesn’t learn which types of sentences to avoid.

Each round of tagging takes about 10 minutes: This includes the amount of time it takes you to tag the sentences, and the processes time for us to train the model.
Important
During the first 4 rounds of training, expect to tag many calls of the NO. This is fine, and expected, because that’s part of the training process. The model can’t learn with only YES tags, because then it doesn’t learn which types of sentences to avoid.
After you've completed 4 rounds of tagging, you’ve trained the model enough to take review and evaluate its results.
To do this, go to the Review model page.
The results you see on this page reflect the types of sentences the tracker will surface if you activate it right now.
You’ll see 20 sentences that the model has surfaced in your calls. Unlike previous screens, these aren’t sentences that need to be tagged, and the model isn’t deliberately giving you samples of sentences that don’t match your concept. These are samples of the types of results you’ll get when you activate the tracker.
If a majority of the results fit your concept, activate the tracker. If you’re not satisfied with the results, keep tagging sentences to improve the trackers accuracy.

When you’re satisfied with the model’s results, activate the tracker. You’ll be asked to choose if you want to apply the tracker to upcoming calls only, or calls that happened 1, 3, 6, 9 or 12 months in the past.

If you apply the trackers to calls that happened in the past, it will take some time to apply the tracker to those calls. We’ll notify you by email when they are ready.
If you apply the tracker to calls that happened in the past, it will take up to 24 hours for all of these results to be processed. You’ll get an email notifying you when the results are ready. Until then, you can view partial results on the Search page, but keep in mind that these may not be complete.
Once your smart tracker is set up, you can view results in the following places:
-
Search page
-
Team stats
-
Streams
-
Saved alert emails
-
Initiative boards
-
Calls API
-
Calls CSV
-
And more
Note
Dive deeper with the smart tracker course at the Academy, and learn how to create accurate, insightful smart trackers for your team.