Welcome to Ada’s release notes. Scroll down to see a list of recent releases.
You can subscribe to updates with our RSS feed, or sign up to get news about updates directly in your inbox.
Sign up for email notifications
At the end of every week that has had at least one feature release, we’ll send you an email on Friday at 11 a.m. Eastern to let you know about our last few releases.
Improved AI Agent persona settings
We’ve introduced some new settings to customize your AI Agent’s persona, so you don’t have to control its behavior in your Guidance. This includes settings that control:
- How long you want messages to be
- How many steps you want your AI Agent to put in a message
- Whether your AI Agent mentions your company’s competitors
To learn about all of your AI Agent’s persona settings, see Customize your AI Agent’s personality in automatically generated content.
Use natural language to create complex Processes
We’re excited to release the newest version of Processes, which allow you to train your AI Agent to solve problems that require multiple steps and logic.
Now, instead of using blocks, you can write out multi-step instructions for your AI Agent to execute, complete with conditional logic and referencing Actions you’ve already configured. This way, you can use the same language you would use training a human agent to dictate what your AI Agent does.
This change also comes with some additional minor enhancements:
-
For Actions, we’ve added a checkbox that restricts your AI Agent to only running the Action when a Process references it. By default, the checkbox is selected, but you can clear it to allow your AI Agent to run the Action on its own.
-
We’ve added some new items to the reasoning log that indicate when your AI Agent ran a Process, or when it needed to gather information from the customer to run a Process.
-
We’ve added auto-capture variables to handoffs and other areas of the dashboard where you build content with blocks. That way, you can define information that your AI Agent needs to execute the block (e.g., the customer’s account number), and your AI Agent can autonomously ask the customer for that information and save it in the variable.
For more information on our enhancements to Processes, see Create workflows with Processes.
Get more accurate analytics data
As part of continually improving the accuracy of our automated resolution classification model, we have made two exciting updates for generative clients:
-
Your AI Agent now evaluates all of its conversations for automated resolutions, instead of just a sample.
-
We’ve improved the way your AI Agent evaluates whether it provided relevant information grounded in your knowledge content, meaning its classifications are more accurate.
Going forward, all of the the data on automatic resolutions in your reports, and your conversation topics, will include all conversations.
For more information, see Understand and improve your AI Agent’s automated resolution rate.
