Ada release notes

When you're looking through your AI Agent's conversations, you can now see points where your AI Agent searched your knowledge base or performed an Action, and you can see the active Guidance it had available for consideration. You can use this new information to target areas for improvement in its training, so you can be even more confident in its decisions.

For more information, see Learn about how your AI Agent used knowledge content, Actions, and Guidance.

In generative AI Agents, in Actions, we've made it required to add a name for each API output. This was optional before, but we've determined that adding names allows the bot to integrate API data into responses more consistently.

For more information, see Configure API calls in your generative bot with Actions.

We've moved a few things around in the Conversations view:

• In the Details panel, we've removed the tabs, so you can see resolution classification information and meta variable information in the same place.

• We've moved the link to view other conversations from the same chatter into the top header, under the chatter's name.

• If your bot is configured to show messages whenever a variable's value changes, you can now turn those messages off.

For more information, see Show or hide variable change messages.

In generative AI Agents, we've introduced the ability to configure API calls, so your AI Agent can fetch information for your customers on demand.

For more information, see Configure API calls with Actions.

For Voice bots, we've improved the experience around giving the bot more time to process things like API calls. We've removed the artificial typing sound, and replaced it with periodic messages like "one moment" to fill any silence.

For more information, see Minimize pauses while your bot performs backend actions.

In our ongoing efforts to ensure the highest quality and accuracy of your chatbot's responses, we've decided to deprecate the Auto-training feature.

We've introduced the ability to guide your AI Agent's behavior by creating custom instructions for it to follow.

For more information, see Customize your AI Agent's generative content with Guidance.

You can now send surveys to measure customer satisfaction (CSAT) in your generative AI Agent. For more information, see Collect and analyze customer satisfaction data with Satisfaction Surveys.

We're excited to announce a new measure of your AI Agent or bot's success. In addition to measuring whether conversations were contained, Automated resolution rate is a measure of whether conversation content was also relevant, accurate, and safe.

To learn more:

• If you have a generative AI Agent, see Understand and improve your AI Agent's automated resolution rate.
• If you have a scripted bot, see Understand and improve your bot's automated resolution rate.

To improve security, we've made some minor changes to the Ada dashboard.