Proactive messaging

Overview

Proactive Conversations enable you to configure your AI Agent to reach out at the right moment to assist customers, resolve issues, and enhance the customer experience. Once the customer engages with the conversation, you can also use the context to trigger a relevant Process.

Limitations

Proactive Conversations have the following constraints:

• Proactive Conversations are currently available only on web or mobile web.
• No conversation is created unless the user clicks on the widget to open the chat, so unless a user clicks on the widget, a Proactive Conversation is not visible in the Conversations View.

Use cases

The following scenarios illustrate common applications for Proactive Conversations:

• For a frequently occurring question, such as how to check an order status, you can configure a proactive message, such as “Need help checking your order status?” to show up on your ‘Contact Us’ page.
• If you have a system outage, you can notify end users as soon as they navigate to your webpage. They can then engage with the AI Agent to ask for help.
• When a new user logs in for the first time, the AI Agent can proactively offer to share more about the services your business offers.

Capabilities & configuration

There are two ways to trigger a Proactive Conversation:

1. URL Matching: The Proactive Conversation is triggered based on the page URL.
2. Embed2 Javascript API: You can programmatically trigger a Proactive Conversation and optionally pass in parameters to personalize the message.

When you trigger a conversation proactively, you may want to disable any greeting message that you have already configured.

Performance measurement

To understand how your Proactive conversations are performing, refer to the Proactive conversations report. This report compares your overall conversation volume with Proactive engagement and includes detailed metrics for each message.

Metrics available in the report include:

• Conversations: Number of Proactive conversations initiated.
• % of conversations: The proportion of Proactive conversations relative to all conversations.
• AR rate: Percentage of Proactive conversations that were automatically resolved by the AI Agent.
• Containment: Percentage of Proactive conversations that did not result in a handoff.
• CSAT: Customer satisfaction score, based on positive CSAT responses among rated Proactive conversations.

Use this data to identify which Proactives are driving engagement and resolution, and which ones may need refinement. To learn more about the report, see this topic.

Quick start

Set up a Proactive Conversation in a few steps.

To create a Proactive Conversation:

Your AI Agent now displays the Proactive message on matching pages. For more options, including message templates, see Static messages.

Implementation & usage

Create and configure Proactive Conversations to engage end users at the right moment.

Static messages

A static message displays the same content to all end users who trigger it.

To create a Proactive Conversation with a static message:

1. On the Ada Dashboard, go to Config > CHANNELS > Chat, then open the Proactives tab.

2. Click New Proactive.

3. Give your Proactive a name.

4. Select Use a static message.

5. Craft your message in the text box.

6. If you want to trigger through URL matching, add Trigger conditions for your Proactive:

   • Click Add.

   • Select the appropriate URL matching option from the drop-down menu. To learn more about URL matching, see the table below.

   • Input the full URL or URL component.

   • Repeat for additional URLs where you want the proactive to be triggered.

   • You can choose whether the proactive should trigger for every page load, or once per session.

     Option	Definition	Example
     Exactly Matches	Looks for the exact match of your URL. Query parameters are not part of the matching logic.	Specifying https://www.example.com/checkout matches https://www.example.com/checkout?q=hello and https://www.example.com/checkout/
     Contains	Matches URLs that contain your specified string anywhere in the URL. Query parameters containing your values are also included in the matching.	Specifying example matches https://www.example.com/checkout and https://www.hello.com?q=example
     Ends With	Matches URLs ending with your specified string. Query parameters are ignored for this option.	Specifying /checkout matches https://www.example.com/checkout and https://www.hello.com/checkout?q=example
     Regular Expression	Provides full control over URL matching by allowing you to define regular expression patterns against the entire URL, including query parameters.	Specifying product [0-8]+[^9]$ matches any page that includes the string product and any number of any length afterwards, as long as the number 9 never appears. Specifying ^https://acme.com(?!.*\/(promo｜pricing)$).* matches on all https://acme.com pages except for those ending with /promo or /pricing.

7. Now that you have your Trigger Conditions, you can choose whether the Proactive should start immediately after page load, or if it should show after a delay. You can choose the delay in seconds.

8. You can also configure how long the proactive should be displayed, if the customer does not click on it. You can opt to show it indefinitely, or dismiss it after a set time in seconds.

Message templates

A message template allows you to personalize the content of your Proactive Conversation by passing in dynamic content when you trigger the proactive through the Embed2 Javascript API.

To create a Proactive Conversation with a message template:

1. On the Ada Dashboard, go to Config > CHANNELS > Chat, then open the Proactives tab.
2. Click New Proactive.
3. Give your Proactive a name.
4. Choose Use a message template.
5. In the given text box, you can type out the content of your message, using double curly brackets for placeholders: {{placeholder_name}}
6. As a message with placeholders cannot be triggered through URL matching, the configuration options for URL matching are disabled. You can trigger this message using your Embed2 Javascript API.

Disable Greetings

To ensure that your Greeting does not show up in addition to the Proactive message when an end user clicks to chat to the AI Agent, use the proactive_conversation metavariable. This metavariable becomes available in the Greeting block builder once you have at least one conversation with a triggered proactive.

To disable Greetings for Proactive Conversations:

1. On the Ada Dashboard, go to Config > AI AGENT > Greeting.

   The Greeting page opens.

2. Add a conditional to only show the Greeting if the metavariable proactive_conversation Is Not Set. You can also customize your Greeting using the same variable. The value of the metavariable is the messageKey of the latest proactive delivered to the user.