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.
Product
Product [19]
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.
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.
Thinking Messages: The gap between question and answer
The typing indicator tells users to wait. Thinking Messages tell them why. Trust OS 2.0 adds per-tool messages that replace the generic dots with something that actually communicates.
Gradual rollout and A/B testing: Stop guessing whether your AI changes worked
Delight.ai's Trust OS 2.0 adds two tools for shipping AI agent changes safely: gradual rollout to validate with real traffic and A/B testing to prove if a change actually worked.
Introducing Zero-Touch Improvement: Your AI gets better while you sleep
Zero-Touch Improvement is a graduated AI optimization system that evolves from human-guided learning to fully autonomous improvement. Part of Trust OS 2.0 by delight.ai.
Delight.ai — The Next Chapter of Sendbird
Delight.ai is the next era of AI customer experience — one that listens, remembers, and moves with your customers.
How For You Conversations Make Every Interaction Feel Personal
Discover how brands can deliver experiences that are consistent, intelligent, and deeply human with For You Conversations from delight.ai.
Introducing AMP: The Agent Memory Platform
Agent Memory Platform (AMP) is delight.ai’s new intelligence layer that gives your AI agents a living memory and a business brain. It connects what your agent remembers about every customer with what your business wants to achieve.
The future of customer connection starts with Omnipresence
Built by delight.ai and backed by Sendbird’s decade of communication expertise, Omnipresence introduces a new standard for connection—always on, always aware, always personal.
Introducing role-based access control (RBAC) for AI agents
Learn how to scale access to AI agents for streamlined AI change management and collaboration at scale.
