Monitor Synthflow.ai Voice AI Agent Calls With Caller Journeys and Metrics

Craftsmanship is what sets great Voice AI agents apart. A Voice AI agent in the wild will encounter scenarios its designer did not expect. The best agents are built by Voice AI developers who are constantly hewing the rough edges.

But it’s hard to find the rough edges from random sampling. Most Voice AI agent developers are manually listening to call recordings. It is a tedious and slow method for improving your agent. And it’s impossible to listen to all your calls.

We’re building a Voice AI analytics platform. It’s Mixpanel for Voice AI Agents. We map the journeys that your callers have with your Voice AI agent. We show you where and why your calls are not succeeding. We also provide audio metrics (e.g., latency) and conversational metrics (i.e., outcomes and anything you define).

In this blog post, we show you how to send your Synthflow Voice AI agent calls to Canonical AI’s Voice AI analytics platform.

Voice AI Call Analytics

But wait, what is a caller journey map? Maps of Voice AI agent calls give you visibility into how your agent is performing. In the call maps, we determine the stages of the conversation (you can also specify the call stages). Then, we assign each turn in the conversation to one of the stages.

Here’s an example of a call map. The Voice AI agent answers calls to car dealerships. The Voice AI should either schedule an appointment or arrange a callback from a technician. We can see that there are 22 calls total and 17 led to a successful outcome. You can see the path the different callers took in their interaction with your Voice AI agent. It helps you identify the rough edges so you can continually craft your Voice AI assistant.

Voice AI Analytics API Key

First, you will need to generate a Canonical AI Voice Agent Analytics API key. Go to our website, click login on the top right, and authenticate as a first-time user. Once you’re logged in, you’ll see a screen with your API key. Copy it and put it somewhere safe. You can always access your API key again by clicking on your profile on the top right corner of our dashboard, then clicking on ‘Setup’.

Synthflow Monitoring and Analytics

We love Synthflow! It’s a great platform for building Voice AI assistants. We love how the product is tailored to AI Agencies. With Synthflow, agency owners can produce high quality Voice AI assistants.

Synthflow Voice AI Analytics Integration With Make

Here we’ll show you how to get Synthflow to send the data from your Voice AI assistant’s calls to Make.

First, add a custom webbook module to the Make scenario. Copy the webhook address.

Next, copy the webhook url from the Make webhook object. In Synthflow, navigate to your assistant, click on ‘Deployment', click on ‘Rest API’, then paste the webhook URL into the webhook field.

Back in Make, add a router module to your workflow. You’ll need this if you want to trigger other actions at the end of the call. After the router, we need to transform the JSON into a string so the Canonical AI servers can parse it. You'll want to pass in the entire call object by pasting in {{10.call}}.

After the JSON transformer, add a HTTP request object. Choose the ‘Make a request’ option among the different types of HTTP requests. In the URL field, paste https://voiceapp.canonical.chat/api/v1/webhooks/synthai. Set the method to POST. Add a header, and use X-Canonical-Api-Key for the name and your Canonical AI API key for the value. For the body type, select Raw. For content type, set it to JSON (application/json). In the request content, paste in the following:

{
  "call": {{15.json}},
   "speaksFirst": true
}

Be sure to turn on the scenario. Also, on your list of scenarios, make sure your scenario is turned on there as well.

You can download the Make blueprint for this scenario here.

Voice AI Analytics Programmatic Integration

If you would prefer to integrate with code, then our developer documentation here can get you started. You may also find the sample scripts for uploading calls in our GitHub repo helpful.

Analyzing Voice AI Agents YouTube Tutorial

If you prefer to learn by watching, here is a YouTube tutorial.

Next Steps

Once your calls are flowing into our pipeline, you’ll be able to see the call maps and metrics for your Voice AI agents.

Adrian and I love the Voice AI space! We love meeting Voice AI developers and learning about the neat things they’re building! If you have any questions about integrating Canonical AI into your workflow, or just want to meet others working in Voice AI, please reach out to us!

Tom and Adrian November 2024