Build reusable sub-flows and functions to keep your agents maintainable and consistent across your entire account with our new Update the component once, and it syncs with all other agents that use it.
Example use cases:
Security check — "Before I help you, can I verify your account? What's your date of birth and the last 4 digits of your phone number?" → use billing/support component
Language specific sub-flows — "I can help you in English or Spanish. Which would you prefer?" → transfers to the right language component
End-of-call survey — "On a scale of 1-5, how satisfied were you with this call? What could we improve?" → use a follow-up component
Get started: Agent Builder → Components Tab → + Create → Build your component flow
Warm Transfer Caller ID - No more "Who called? confusion
You can now control which caller ID appears when transferring calls, warm and cold — showing either your AI agent's number or the original caller's number.
Why this matters:
When your sales or support team sees the real caller's number, they can pull up CRM records instantly before picking up and call customers back if the call drops. Critical for lead qualification workflows and HIPAA-compliant healthcare operations where caller tracking is required.
Set it up: Call Transfer Node → Caller ID Settings → Select "User's Number"
You can now add custom fields to track exactly what matters for your business and reorder your Call History columns to match your workflow.
Custom Attributes — Add your own fields for deeper tracking and context. Track appointment IDs, lead scores, customer tier, or any data point your team needs to see at a glance.
Custom Column Arrange — Reorder your Call History view to prioritize what you check first. Put duration up front for billing teams, or lead source first for sales teams.
Set it up: Call History → Customize View → Add Custom Attribute / Drag to Reorder
Other Improvements
Claude 4.5 Sonnet support — Now available for all agents
Recommended Voices — Get started faster with top-performing voices surfaced at the top.
Webhook settings in Agent Swap — Configure which agent's webhook endpoint to use for sending call updates.
Simulation test case management — Import/export test cases as JSON, duplicate them in the editor, and auto-copy them when duplicating agents
Batch calls override — Override, which agent handles calls in batch operations with override_agent_id
Fields in Post-Call Analysis are now optional
Important: Model Deprecation & Speaker Requirements
The following LLM models have been deprecated. Please update your agents to the latest models.
OpenAI:
gpt-4o → gpt-4.1
gpt-4o-mini → gpt-4.1-mini
Anthropic:
claude-3.7-sonnet and claude-4.0-sonnet → claude-4.5-sonnet
Google:
gemini-2.0-flash → gemini-2.5-flash
gemini-2.0-flash-lite → gemini-2.5-flash-lite
Additionally, start_speaker is now also required in the create-retell-llm API.