Messaging Proactive Outreach

Overview

Proactive Outreach lets you configure your AI Agent to reach out at the right moment to assist end users, resolve issues, and improve the customer experience. When the end user engages with the conversation, you can link a Playbook or a Process to drive the interaction.

Limitations

Messaging Proactive Outreach has the following constraints:

• Messaging Proactive Outreach is available only on web or mobile web.
• No conversation is created unless the end user clicks the widget to open the chat. Until then, the conversation is not visible in the Conversations view.

Use cases

The following scenarios illustrate common applications for Proactive Outreach:

• 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 message:

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

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

Metrics available in the report include:

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

Use this data to identify which messages drive engagement and resolution, and which ones need refinement. To learn more about the report, see this topic.

Quick start

Set up a Proactive Outreach item in a few steps.

To create a Proactive Outreach item:

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 messages to reach 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 Outreach item with a static message:

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

2. Click New Proactive Outreach.

3. Give the item 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:

   • 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 message to be triggered.

   • You can choose whether the message 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 message should show immediately after page load, or after a delay. You can choose the delay in seconds.

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

Message templates

A message template lets you personalize the content of a proactive message by passing in dynamic content when you trigger it through the Embed2 Javascript API.

To create a Proactive Outreach item with a message template:

1. On the Ada Dashboard, go to Config > CHANNELS > Chat, then open the Outreach tab.
2. Click New Proactive Outreach.
3. Give the item 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.

Link a Playbook

You can link a Playbook to a Proactive Outreach item so that when an end user engages, the Playbook drives the conversation instead of the default AI Agent behavior. The proactive message is still shown as the initial bubble. The Playbook takes over once the end user opens the chat.

To link a Playbook:

1. On the Ada Dashboard, go to Config > CHANNELS > Chat, then open the Outreach tab.
2. Create a new Proactive Outreach item or edit an existing one.
3. In the Playbook section, select a Playbook from the dropdown. Only active Playbooks are listed.
4. Save the item.

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 Outreach:

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.