You can now choose how you want to roll out your agents with three deployment options:

Deploy for all users pushes your agent to 100% of traffic immediately—perfect for when you're ready to go fully live.

Staged Deployment lets you deploy to a specific phone number, so your agent only activates for calls or texts from that inbound number. Great for controlled testing with a specific audience.

Canary Deployment gives you a traffic percentage slider to gradually roll out your agent. Start at 10%, monitor performance, then scale up as you gain confidence.

Include files directly in your saved text templates - think pricing sheets, lookbooks, welcome guides, claim forms, diagrams, and more!

Access the feature by clicking Templates in the sidebar and selecting +Add Template (top right). Choose Text Template and give it a name.

What’s New: In the Content section, click the paperclip icon to upload a file from your device.

While you could already personalize headings and body text, this update allows you to insert dynamic data into button actions, such as "Open URL" or "Dial Phone Number."

Why would I use this feature? To completely personalize your campaigns. For example, an "Open URL" button can now point to a unique, personalized link for every recipient, making it easier to direct customers to their specific account pages, tracking links, or custom booking sites.

We’ve expanded the communication capabilities of your AI agents! Previously, agents were limited to sending text-only messages. With this update, you can now direct your agents to send messages with attachments, allowing them to automatically share PDFs, csv files, images, videos, and other important items during a conversation.

How to set it up:

1. While in the AI Agent Builder, add a new node or click the pencil icon to edit an existing one.

2. Under the Tools section, click Add Tools.

3. Select Conversations and choose Send message with attachments.

4. Don't forget to save your work!

When viewing a conversation that includes a voice interaction, you can now click the three dots on any call recording to access a suite of powerful tools which include viewing a transcript, copying a call link, showing the internal discussion thread, and viewing pipeline logs of how the AI processed that specific call.

We’ve added an extra layer of protection to your campaign workflow to help prevent accidental sends and ensure carrier compliance.

Now, when you finish setting up your campaign, selecting your list, writing your message, and choosing a send time, you’ll encounter a final confirmation after clicking "Send Now."

What’s new in this confirmation?

• Acknowledge Opt-in: A reminder to confirm that you have obtained proper consent from all contacts in your campaign, helping you stay compliant with messaging regulations.

• Highlighted Recipient Count: The pop-up clearly highlights exactly how many recipients will receive your message, giving you one last chance to verify your list size before it goes out.

This update is designed to give you total peace of mind that your messages are going to the right people, at the right time, with the right permissions.

Tag colleagues in discussions: Use the @ sign within any message or call discussion thread (accessible by clicking the "show comments" icon) to tag a colleague, provided they have access to that phone number inbox.

Custom compliance per phone number: Create default START, STOP, HELP, and first messages individually for each phone number inbox. This allows you to customize the automated responses customers receive (for example, after replying STOP), ensuring your team meets regulations. Find these settings within the phone number inbox settings.

AI agent output response structure: AI agents can only output a structured JSON response. If your agent needs to send a message to the user (via SMS or RCS), it must use the dedicated "Send Text Message" or "Send RCS Message" tool.

Improved tool descriptions: When you add or edit a node, you can now hover over each node type and tool to see a clear, brief description. This improves usability and helps you quickly choose the right component for your workflow.

Improved variable picker during agent setup: When adding or editing a node (like the HTTP request tool), you can select data types and methods directly from a user-friendly sidebar interface, instead of needing to edit the JSON.

Unsaved changes alert: We've added extra safeguards to prevent accidental loss of work when editing an AI agent! Now, if you have unsaved changes, the save button will highlight as a reminder. Furthermore, if you attempt to navigate away from the page without saving, you will see a confirmation pop-up asking, "You have unsaved changes that will be lost. Are you sure you want to leave?"

Prompt copy button: For agents builders, we've added a handy "click to copy" icon to the right of the prompt section when editing a node. This lets you quickly copy the prompt you've used for easy reuse or documentation.

Duplicate an AI agent: Visit Agents in the sidebar, find the agent you want to copy, and look for the new + icon next to its details. Clicking this instantly creates a clone. You can then rename and edit the copy as needed.