Subscribe to release notes

Configurable Session Timeouts now available

Custom session timeouts are now available in the dashboard.

Dashboard session timeouts can now be configured to specify session maximum length and inactivity limits.

For more information about session timeouts, see our documentation.

Conversations API is now available

Ada’s Conversations API enables you to seamlessly embed Ada’s intelligent AI Agents anywhere–whether you’re building a custom messaging UI, integrating with a preferred email provider, or launching a new third party channel that Ada doesn’t already support.

Effortlessly manage conversations and messages between users, AI Agents, and your human team–all through a single, flexible API.

For more information about the Conversations API, see our API documentation.

Docs updates: Improvement tactics & best practices

We’ve added new help articles to make it easier for customers and teams to improve and optimize AI Agents. This includes a new Improvement tactics page as well as several new Best practices topics that provide practical examples and guidelines.

What’s new

• 🚀 Improvement tactics
  Practical strategies for diagnosing issues and improving Agent performance.

• 📖 Best practices (first set now published):

  • 📚 Topics: How to structure and manage topics for performance and clarity.
  • 📘 Knowledge setup: Guidelines for organizing knowledge articles so answers are accurate and reliable.
  • ⚙️ Actions: Tips for controlling when and how Actions are triggered.
  • 🎯 Coaching: Recommendations for monitoring and coaching Agents to improve over time.
  • 🎨 Personalization: How to use variables and conditions to tailor responses for different end users.
  • 👋 Greetings: Latest addition! Covers how to create warm, on-brand greetings that set the right tone and expectations for conversations. Stay tuned — more best practices to come!

Fetch Chat Metadata improvements

The Fetch Chat Metadata block now generates summaries for conversations in all languages and uses an updated LLM model for improved performance.

What’s new

• Summaries are now generated for conversations in any language (previously English-only)
• Upgraded the LLM used for generating the summaries

For more information about the Fetch Chat Metadata block, see the help documentation.

Enhanced Inquiry Summary and Reason for Classification

We’ve upgraded the language model used to generate Inquiry Summary and Reason for Classification, delivering more accurate insights into customer conversations.

What’s new?

• Upgraded language model: Enhanced LLM provides more detailed and accurate conversation analysis
• LLM-based translation: Replaced Google Translate with LLM translation for better quality
• Improved Topic assignment: More detailed Inquiry Summaries enable better conversation categorization

These improvements provide better visibility into customer intent and conversation outcomes, making it easier to identify trends and optimize your AI Agent’s performance.

Chat settings update

Updated the Chat settings area, reorganizing settings for: launching Ada, managing chat persistence, and controlling privacy and security.

Previous organization:

• Launch controls
• Persistence
• Privacy & security
  • Privacy: IP tracking
  • Configuration: Enable chat
  • Approved domains

New organization:

• Launch
  • Chat availability: Enable chat
  • Allowed websites (formerly “Approved domains”)
  • Launch controls
• Data & privacy
  • Persistence (formerly its own “Persistence” tab)
  • Privacy: IP tracking
  • Approved link protocols

Custom link protocols

Configure custom link protocols so that your AI Agent can send deeplinks, such as yourbrand://your-app.

By default, your AI Agent can already send links with these standard protocols: https, http, ftp, ftps, mailto, tel, callto, sms, cid, xmpp.

What’s new

Add custom link protocols (URI schemes) for your AI Agent to use in your chat settings.

Why this matters

This allows your AI Agent to send deeplinks so that your customers can more easily take action to address their issue.

Introducing an Email Conversation Length Limit

Introduced safeguards to prevent potential long-running loops (eg accidental automatic replies).

Learn more about Email conversation length limits here.

Support for Multiple Participants in Email Conversations

Your AI Agent now seamlessly supports email conversations involving multiple participants!

When additional recipients are included — whether in the “To” or “CC” fields — the AI Agent keeps the exchange in a single thread and can respond to inquiries from any participant. This ensures clearer, more coherent conversations for everyone involved.

Learn more about Email conversations with multiple participants here.

Introducing Playbooks

Enterprises invest heavily in customer service, but complex inquiries still rely on human agents, because traditional bots can’t follow real-world standard operating procedures (SOPs).

Playbooks empowers your AI agent to follow your standard operating procedures, handling complex, multi-step inquiries with the same precision and flexibility as your best human agents. That means:

• Interpreting instructions in real time
• Adapting to unique customer inquiries
• Using Actions to get information and perform tasks
• Referencing Variables for personalization
• Escalating when needed

Like your SOPs, Playbooks are written in natural language with step-by-step instructions, making them easy for you to review and maintain over time. We’ve also made it easy for you to create your first Playbooks through a simple prompt or an existing PDF.

Learn more about Playbooks in our launch blog post, documentation, and best practices guide.

Limitations

While Playbooks offer powerful capabilities, it’s important to be aware of their current limitations:

• Not supported on Ada Voice: Playbooks currently only work with Messaging and Email channels.
• Limited Coaching support: While you can coach the AI Agent on when and which Playbook to use, Coaching is not considered once the AI Agent is executing a Playbook. Additionally, you cannot currently coach individual steps or messages taken during a Playbook. To adjust the AI Agent’s behaviour in these cases, edit the Playbook directly.
• Limited knowledge access: The AI Agent currently cannot initiate a search for knowledge articles while using a Playbook. If relevant knowledge would be helpful, consider incorporating it directly into the Playbook content.

Being aware of these limitations helps ensure realistic expectations and supports better use of Playbooks in your workflows.