Delight.ai AI agent product news and feature updates
Product news and feature launches that help you deploy, monitor, and continuously improve AI agents for customer service.
Search blog posts by title and description. Results update as you type.
Product
Product [27]
27 results found.
Introducing Secure Caller Keypad Input, with built-in PII data masking
Secure Caller Keypad Input brings PII data masking to voice AI, pairing ID masking with PII scrubbing so callers enter codes and consent on keypad quietly.
Beyond conversational IVR: Introducing IVR navigation
Conversational IVR redesigns your own IVR system. IVR Navigation solves a different problem, guiding an AI agent through another call center IVR mid-transfer.
Introducing Universal Telephony: Contact center integration
Universal Telephony gives Delight voice agents real contact center integration, routing calls through your CTI integration & syncing each case to your CRM.
Meet Harper: Delight.ai's AI agent guardrails in action
See how Delight.ai's own AI agent guardrails held up over 30 days of real manipulation attempts: 28 tries, 4 attack patterns, 0 successful breaches.
Introducing Intelligent Voice Handoff for a warm transfer
Delight Intelligent Voice Handoff keeps callers connected as AI briefs agents, detects voicemail, syncs context, and manages follow-up when transfers fail.
Introducing Delight Agent MCP: Ask your AI agent about your AI agent
The delight.ai MCP connects Claude, ChatGPT, Cursor, and Codex to your live agent data, so you can ask a question or fix a problem without leaving the chat.
Accessibility statement for Delight AI Agent SDK
The Delight AI Agent SDK accessibility statement reviews known limitations, assistive technology compatibility, and the remediation roadmap.
Introducing Trust OS 2.0
Eight new capabilities for running AI agents in production with full visibility, precise control, and continuous improvement.
Voice 2.0: Outbound calling, proactive outreach, and 2,000+ quality improvements
Voice 2.0 ships outbound calling, proactive voice outreach, and 2,000+ quality improvements. Your AI can now reach customers first—before they ever need to call in.
Introducing Agent Steward: The first AI agent that owns customer issues end to end
Agent Steward resolves complex customer issues end to end. No handoffs, no transfers. See how autonomous AI cuts resolution time from 5 days to 40 seconds.
Low CSAT Analysis: Turn bad scores into actionable failure categories
Delight.ai's Trust OS 2.0 adds Low CSAT Analysis—AI that reads every 1–2 score conversation and categorizes it into one of five failure types, so you know exactly where your agent is breaking down.
Your whole Zendesk, in one click: Introducing Zendesk to Delight Desk migration
Move your entire Zendesk setup—tickets, macros, knowledge base—to Delight Desk for free, and turn resolved tickets into ready-to-use AI Actionbooks.
Test Upgrade: Build your AI agent test set from real conversations
The new Test Upgrade lets you create test cases from real conversation IDs, organize with labels, share sets across environments, and get consistent pass/fail results.
Introducing Openbook: Navigate your actionbook like a map
Openbook renders your actionbook as a visual flow so you can navigate complex logic without scrolling through markup. 10,000 feet to 10 feet in one click.
Introducing Actionbook Editor: Edit your AI's rules like a Notion doc
Actionbook Editor gives ops teams direct authorship over AI behavior—no code, no engineering tickets. Edit refund thresholds, escalation logic, and tone in real time.
Staging: The missing layer between dev & production
Delight.ai's staging environment adds the missing layer between dev and production — a full production mirror, isolated from customers, where you can validate changes on their own terms.
Find your revenue opportunities
Walk through Delight with our team and see where your customer conversations can grow sales




















