Data Export API: conversations keep their Topic when there is no classified Intent
The v2 Conversations endpoint now returns a conversation’s Topic even when the conversation has no classified Intent.
Before, a conversation with a real Topic and no classified Intent returned an empty classifications array, so the Topic was missing. Now classifications includes the Topic, and its intents field is an empty array. A conversation with a real Topic and a real Intent returns the same result as before.
See the Conversation object reference for the full schema.
Variable references in Playbook General Guidelines read as names
Fixes
A Variable reference in a Playbook’s General Guidelines now reads as the variable’s name instead of raw template text. Before this change, a reference such as {{ variable:... }} could reach the end user as written. General Guidelines are guidance, so a reference names the variable; to use a variable’s value, put it in a SEND, ASK, or SET step.
For more information, see Configure a Playbook.
Initiate phone calls with your AI Agent using Voice Proactive Outreach
Proactive Outreach, formerly called Proactives, now has its own page at Config > AI AGENT > Outreach. The page replaces the Proactives tab in Config > CHANNELS > Chat/Messaging. Your existing Proactive Outreach items show on the new page and work as before.
We’ve also added the ability for your Voice AI Agent to proactively reach out to your end users with Voice Proactive Outreach. Your AI Agent calls an end user by phone, and the Agent runs a linked Playbook when a person answers. Start a call in one of two ways:
- Send
POST /v2/conversations/proactive/to the Conversations API. Ada places the call over your own outbound SIP trunk and detects answering machines. Thev1.proactive_callwebhooks report the state of each call. - Let your contact center dialer place the call. When a person is on the line, the dialer sends a SIP INVITE with the
X-Ada-Proactive-Idheader to Ada.
To get access to Voice Proactive Outreach, contact your Ada team.
Snapshots carry the image redaction setting
The Snapshot API now exports and imports the image redaction setting, in the image_redactions section. The section holds the 2 image types that you can let your AI Agent read: government_id and other_credential. The Agent always withholds payment card images, so the section does not include them.
- Export: the snapshot includes both image types.
truemeans that the Agent withholds the image.falsemeans that the Agent reads it. - Import: the import replaces the setting on the target Agent. If the section does not include an image type, the target Agent withholds that type. If the import does not include the section, the setting does not change.
- Validate: a
mode: validaterun names each image type that the import changes. - Audit log: if the import changes the setting, it writes one Updated row for Image Redactions.
For more information, see What a snapshot includes.
Clearer reply when the AI Agent withholds an image
When your AI Agent withholds a sensitive image, its default reply now names the document type, for example “your card” or “your passport or ID”. The Agent then gives one next step. For a payment card, it may ask for the last 4 digits as text. For an identity document or other credential, it offers a human agent when a handoff is available. When no handoff is available, it says that human support is not available and keeps helping. The Agent still never asks for a full card number or a document number.
For more information, see Images.