SEPTEMBER 2023 RELEASES
September 2023 Releases
November 2026 Product Recap
Build More Dynamic Multi-State Agents, Write and Host Code, and Improve AI Agent Testing
This month, we released features that make multi-state agents more goal oriented and easier to build, test, and monitor. A new Director node helps agents adapt when conversations go off script, and Logic nodes make instant, deterministic decisions without an LLM call. Building and debugging large flows is faster too, with search, quicker node connections, and live path highlighting during tests. Once agents are live, new call analysis fields show exactly which states each call moved through and where it ended.
We’re also expanding our developer tools with Regal Functions, so you can write and host code right alongside your agents, plus new Public API endpoints. Here’s what’s new:
AI Building AI
Write and Host Code with Regal Functions
Write and host code in Regal, then call it from an AI agent as a custom action. Build functions in the editor or in natural language through Copilot, which can create, update, activate, test, attach, and delete functions for you. Each function declares input and output schemas and has draft and active versions you can test before going live. Functions replace code that used to live in Twilio Functions, and they can securely call OAuth-protected systems like Salesforce.
For example, Regal Functions can be used for custom logic like data cleanup, payload reshaping, and CRM lookups in systems like Salesforce, without scattered code or waiting on a developer. Learn more
Quickly Update and Change Call Restriction Settings with Copilot
Copilot and MCP can now create, read, update, and delete Call Restrictions, Daily Available Hours, and State of Emergency settings. This allows admins to adapt to a holiday or an emergency in one conversation.
For example, if a hurricane is declared in Florida, ask Copilot to "pause outbound calls to Florida contacts until Friday" and it adds the State of Emergency restriction for you. Before Thanksgiving, ask it to "add Thursday, November 26 as a holiday and move our daily calling window to 10am to 6pm" instead of clicking through each settings page.
Build
Move Conversations Forward with Goal-Oriented, Multi-State Agents
Multi-state agents now keep the control required for complex calls, without feeling rigid. A new Director node moves the conversation forward: when the conversation doesn’t fit the planned path, the Director can point to where to go next. That makes your multi-state agents more goal oriented, so they can:
- Handle edge cases better. When a conversation goes off plan, the agent finds the right next step instead of getting stuck.
- Adapt when callers change course. Whether a contact brings up something new or changes an earlier answer, the Director helps pivot the agent to the right node.
- Remember what contacts already said. The Director reviews the full transcript, so contacts never have to repeat themselves.
When triggered, the Director uses a stronger reasoning model to review the full transcript and available transitions, then picks the best next step. A fallback path you define ensures the agent always has a way forward. Now in Early Access; reach out to your Regal CSM for access.
Serve Customers Better with Image Context in AI SMS Agents
When a contact sends an image, your AI SMS agent now gets a summary of what's in it, and can reference this in the conversation. For example, let’s say a property insurance claims agent asks about damage. Subscribers can now send damage photos while filing a claim, and the agent can steer the conversation using what the photo shows.
Easily Edit Contact Attributes from the Profile Slide-Out
Admins can now edit a contact’s existing custom properties, and add new top-level ones, right from the profile slide-out. Changes save the same way they do on the Agent Desktop, so the slide-out updates right away and journeys still get the attribute-edited event. For example, say an admin is reviewing a contact who just upgraded and sees their plan tier still says “Basic.” They can change it to “Gold” right in the slide-out, without creating a task on the Agent Desktop.
Protect Credentials with Secrets in Functions
Functions can now reference brand secrets with context.secrets.<name>, so API keys stay out of the code. This is used when calling Regal's own APIs or your own endpoints from a function without exposing credentials to anyone who can open it. Learn more
Make Deterministic Decisions with Logic Nodes
Now, you can add a Logic node to a multi-state agent and it checks conditions against data it already has, then immediately takes the first matching path, or a default path if nothing matches. The agent doesn't speak on a Logic node, and because there's no LLM call, the decision is fast and comes out the same every time. Combine conditions with AND and chain multiple Logic nodes in a row. For example, this is helpful for decisions that shouldn't be left to the model, like whether a balance is over a limit, whether a value was already collected, or what an incoming SIP header says. Learn more
Deploy
Look Up Profiles and Queues with New Public API Endpoints
Three new endpoints let you look up contact profiles and queue data from your own systems:
- List Contact Profiles (GET /v1/contactProfiles): Look up live contact profiles by phone, email, externalId, or profileId, with optional trait filters. It respects each brand's shared-profiles setting.
- Queues (GET /v1/queues, GET /v1/queues/{id}, GET /v1/queues/{id}/stats): Pull queue configuration and live stats.
For example, you can now verify a caller who's calling from a different phone, disambiguating shared profiles from your own systems or AI agents, and pulling queue data into your own reporting or workforce tools. Learn more
Usability Enhancements
Edit and Test Nodes More Efficiently in Multi-State Agents
Now, in the multi-state agent builder, you can connect or remove nodes by picking a target node in the node editor, see thicker connector lines on hover, and jump node to node with the new rewind and fast-forward controls. This allows admins to navigate large multi-state agent graphs without losing track of connections.
In addition, when you test a multi-state agent on the node graph, the canvas now shows the path the agent is taking. It follows the agent to each new node and leaves a trail behind it, in both Test Logic and Test Audio. Closing the test drawer or disconnecting clears the highlight, and you can still select and edit nodes during the test. This way, you can watch a multi-state agent move through specific nodes during a test, instead of guessing from the chat context alone.
Navigate the Agent Builder Faster with Search
A new search input on the Agent Details and Multi-State Flow tabs lets you:
- Search your Agent Details, including content in collapsed sections, action nodes, and Custom AI Analysis
- Search multi-state agents by node name or content and jump straight to the relevant node
Monitor, Debug, and Improve
Catch Flaky Agent Performance with Bulk Simulations
Run each test scenario 1, 5, 10, or 20 times to see whether it's consistently passing, consistently failing, flaky, or aborted. For example, this is especially helpful for stress-testing the scenarios that come up often or that your AI agent struggles with, then reviewing individual transcripts on the simulation outcome page to find where it falls short and apply targeted fixes before going live.
Test with Real Profiles Using Profile-Populated Test Variables
Pick a profile to fill test variables for Test Logic, Test Audio, and Simulations. Regal uses static values from the selected profile, so you can validate how your agent performs with specific profiles and contact attributes.
Track Actions and States with New call.analysis.available Fields
Five new deterministic fields give factual metadata on each AI agent call, and you can reference them in journeys:
- actions_invoked
- action_failures
- state_transitions (multi-state only)
- final_state (multi-state only)
- duration_seconds
Together, these allow you to track which actions fired or failed and where multi-state agents ended up, without prompting an LLM to figure it out. Learn more
More Improvements
- See Which Agents Use a Custom AI Analysis Data Point: From a data point's modal, you can now see which AI agents use it, so you know exactly which agents you'll affect when you edit it.
- Pass the Regal Phone Line in IVR Webhook Payloads: When you add a webhook node to an IVR, you can now include the Regal phone line in the JSON payload.
- Delete Non-SCIM Users Without Contacting Support: Admins can now delete non-SCIM users themselves, without writing in to Regal Support.
Coming Soon
- Manage phone numbers in Copilot: Buy and configure phone numbers from Copilot.
- Redact PII automatically: Automated PII and PCI redaction detects and removes sensitive data like card numbers and SSNs from transcripts, recordings, and events, with no manual pause required.
- Build campaigns and journeys in Copilot: Describe the outcome you want, such as calling new leads, texting anyone who doesn't pick up, and handing interested leads to a person.
- Use Regal Functions in Journeys and IVRs, plus OAuth-based secrets and referencing other files.
Frequently Asked Questions
Treat your customers like royalty
Ready to see Regal in action?
Book a personalized demo.
Thank you! Click here if you are not redirected.
Oops! Something went wrong while submitting the form.
Founded in 2020, Regal is an enterprise voice AI agent platform for contact centers. Regal helps businesses build, deploy, and manage autonomous AI agents across sales, support, and operations teams.
Latest Blog Posts
.avif)
.webp)
%20(1).webp)
.webp)
%20(1).webp)
.webp)
Dialing Compliance: How We Scaled Outbound Calling Reliably
Behind a fragmented and ever-changing regulatory landscape is a simple goal: protecting people from unwanted or poorly timed outreach and giving them control over how they’re contacted. In practice, that responsibility translates into a set of checks that must be validated.
No Need to "Press 1": How AI Phone Agents Go Beyond Automation
AI phone agents aren't just better phone trees. They are autonomous systems that can understand caller intent, retrieve relevant information from your CRM in real time, execute actions, handle objections and clarifications, and complete the conversation without human involvement.
.webp)
.webp)
The PII Question Every Regulated Industry Asks Before Deploying AI Agents
When prospects in healthcare and financial services hear "PII," they often imagine bulk data transfer: the idea that deploying an AI agent means copying a database somewhere. In most modern deployments, that's not what's happening.
.webp)
Why Your Appointment Scheduling Is Still Broken (And What AI Agents Actually Fix)
With AI agents, every appointment gets a confirmation call. Each contact gets a chance to reschedule, and the confirmation rate goes to 100%, not because the AI is better at conversations than your agents, but because the AI never runs out of capacity.
.webp)
The Knowledge Gap: Why Your AI Agent Can’t Answer Real Customer Questions
AI agent performance depends on how well it aligns with real customer language, not just fluency. Regal Improve helps teams identify gaps and improve outcomes by analyzing real conversations and surfacing high-impact opportunities
March 2026 Releases
In March, we made it faster than ever to build, launch, and continuously improve AI agents with Copilot, Regal's AI agent for building AI agents. Together, these updates lessen the time needed to launch and maintain agents, so you can focus on understanding your customers, unlocking new use cases, and driving faster business outcomes.
.webp)
.webp)
February 2026 Releases
In February, we made AI agents sound and feel more natural, even when handling complex, multi-step conversations with conditional logic. These updates give you the control to build AI agents that don't just follow a script: they adapt, respond, and engage naturally with each customer.
.webp)
.webp)
Pinpoint Critical Knowledge Base Gaps with Regal Improve
Customer conversations are inherently dynamic, and Regal Improve’s Knowledge Base Coverage tracks changes in retrieval performance over time and at scale. This makes it easy to verify that KB updates increase coverage and if your documentation is keeping up with evolving customer requests.
November 2025 Releases
November's releases make it easier to scale your transfer-heavy call flows, with new tools that align dialer pacing to downstream agent capacity and streamline complex handoffs. You’ll also see improved post-call workflow accuracy, with reliable data extraction and disposition outcomes driven by LLM configurability and earlier validation.
.webp)
Teaching Voice AI to Behave: Prompting Principles Every Parent Already Knows
Building a great AI voice agent isn’t so different from parenting a five-year-old: clarity, examples, and structure make all the difference. This post breaks down proven prompting principles—from positive framing and persona design to conversational guardrails—that help AI agents sound natural, stay on task, and follow directions every time.
.webp)
How Kin Insurance & a360inc Achieved Faster Outreach and Better Customer Experiences with AI Agents
In this fireside chat, Regal Co-Founder & CEO Alex Levin sits down with Kin Insurance’s Austin Ewell and a360inc’s Henry Davidson to share how their organizations are using AI agents to transform outreach, customer experience, and operational efficiency. They discuss real-world deployments—from qualification and human agent handoffs to complex negotiation workflows—break down the results, and offer practical guidance for leaders adopting AI agents at scale.
.webp)
Single vs Multi-State: How to Pick the Right AI Agent for the Job
Learn about the difference between single-state and multi-state AI agents, and how each impacts speed, scale, and reliability. Discover when simplicity is enough and when enterprise workflows demand structured orchestration, so you can choose the right design for your use case.
.webp)
The Rise of Voice AI Agents: Real-World Deployments Across the Enterprise
In this AI4 fireside chat, Regal.ai COO Sahil Mehta and TaskUs CCO Jarrod Johnson explore how enterprise organizations are deploying voice AI agents across customer experience, support, and sales. They share real-world deployments, discuss quality and ROI trade-offs, and outline best practices for aligning operations and product teams when adopting AI agents at scale.
Automatically Evaluate Test Suites with Simulations
Discover how you can use Simulations to evaluate scenario-specific conversational flows that pinpoint AI Agent failures before launch. Speed up regression testing, validate prompts, knowledge bases, and custom actions at scale, and deploy reliable AI Agents with confidence.
%20(1).webp)
Apple iOS 26 Caller Screening: An Enterprise Guide
Apple’s iOS 26 introduces new call-screening controls that will reshape outbound performance. This guide explains what’s changing, how adoption may impact enterprise contact centers, and the proactive steps leaders can take now to protect answer rates and customer trust.
.webp)
The RAG Playbook: Structuring Scalable Knowledge Bases for Reliable AI Agents
Learn how to structure a knowledge base that keeps AI Agents accurate and on-script. Discover why human-style KBs fail, and apply best practices like single-topic chunking, concrete instructions, and explicit outcomes to reduce hallucinations and scale reliable RAG performance.
RAG Hygiene: How to Scale and Maintain AI Agent Knowledge
Learn how to maintain a clean, reliable RAG system for AI Agents. Discover best practices for structuring source docs, chunking content, titling for retrieval, avoiding redundancy, and keeping knowledge bases fresh to ensure accurate, scalable performance.
Announcing Regal + Rime: Human-Like Voices at Enterprise Scale
Regal is partnering with Rime to deliver ultra-realistic, emotionally nuanced AI voices for enterprise contact centers. Discover new voice options that capture human qualities like pacing, resonance, and subtle expression, and learn how Rime’s technology powers conversations that build trust at scale.
.webp)
.webp)
.webp)
%20(1).webp)
Announcing Regal + Cartesia: Expanding Voice Options for Enterprise AI
Regal is partnering with Cartesia to deliver ultra-low latency, high-fidelity AI voices for enterprise contact centers. Explore new voice options, hear them in action, and learn about Cartesia's industry-leading voice AI offerings.
.webp)
Anatomy of an AI Voice: What Makes It Sound Human
This article outlines the core characteristics that influence how voice AI is perceived on live calls. From mechanical traits like speed and volume, to more emotional and conversational behaviors, we’re going to look at what those characteristics mean, why they matter, and how they impact your bottom line.
.webp)
Voice AI Customization 101: Settings That Work Best
Learn how to configure your AI Voice Agent for real performance. This guide covers the most important voice settings in Regal, what ranges top brands use in production, and how adjusting speed, tone, and responsiveness impact cost, containment, and overall customer experience.
%20(1).webp)
%20(1).webp)
.webp)
.webp)
.webp)
.webp)
.webp)
%20(1).webp)
%20(1).webp)
.webp)
.webp)
.webp)
.webp)
%20(1).webp)
%20(1).webp)
.webp)
%202.webp)
AI Agents for Education: 8 Use Cases for More Meaningful Student Outcomes
AI Agents for Education are transforming student engagement—boosting enrollment, improving retention, and making support more human. Discover 8 game-changing use cases that free up your staff while delivering better student outcomes.
Regal Named One of Forbes America’s Best Startup Employers 2025!
Regal is officially one of Forbes America’s Best Startup Employers 2025, ranking #164 out of 500. This recognition is a testament to our incredible team, our innovative work culture, and our unwavering commitment to advancing AI technology.
AI in Education: The Future of Student Engagement & Enrollment
AI in education is helping to streamline admissions, automate student engagement, and enhance higher ed outreach. Discover key education technology trends to boost enrollment and learn why automated student engagement tools are the future.
.webp)
.webp)
How are Generative AI Voice Agents Different from AI Voice Assistants?
When it comes to comparing AI Agents vs. AI Assistants, Siri & Alexa handle simple tasks, but Gen AI Voice Agents—like Regal’s AI Phone Agent—drive real business impact with human-like conversations, automation, and seamless integration.
.webp)
.webp)
.webp)
7 Best Use Cases for AI Voice Agents in Your Contact Center
As AI technology continues to evolve, the use cases for AI Voice Agents in contact centers will only increase. By answering these six key questions, you can identify where AI agents fit best today in your contact center and plan for future integrations.
.avif)
The Next Step Forward in AI will come from Consumer Businesses
Consumer businesses are implementing AI-enabled customer experiences without any change in behavior on the part of consumers, which is leading AI to become common with more speed than past transitions like the internet and the smartphone. And it means that the next step in AI will not come from the LLM providers. The next big step forward in AI rests in the hands of consumer businesses.