SEPTEMBER 2023 RELEASES
September 2023 Releases
Turn AI Agent Data Into Better Customer Interactions: A Timeline-Based Approach
When teams design AI agents, the hardest part usually isn’t deciding what information to collect. It’s deciding when to collect it, and how much context the agent needs before deployment.
An AI agent doesn’t experience a conversation all at once. During a live call, it only knows what’s been said so far. After the call ends, it can finally see the full arc of the conversation: what the contact cared about, how objections evolved, and what outcome makes sense going forward.
Regal is designed around that reality. In this article, we’ll discuss how you can leverage real-time decision-making and post-call analysis to increase personalization in your customer interactions, evaluate your agent long-term, and extract insights for continuous improvement.
Real-Time Decisions: AI Actions during the call
In live customer conversations, timing is everything. The most valuable signals—frustration, intent to cancel, requests for escalation—don’t appear neatly at the end of a call. They happen in the moment, when the customer’s experience is being shaped. AI Actions make it possible to capture and act on these signals as they occur, enabling you to collect the right data at the right time and respond in ways that protect customer trust and business outcomes.
Imagine an AI agent handling an inbound qualification call. Early in the conversation, the contact becomes frustrated and says, “I don’t want to talk to an AI. Let me speak to a manager” or explicitly asks to cancel.
This is a decision point that changes the live call experience. Waiting until the call ends to act would risk frustrating the customer further, or even losing them forever.
That’s where AI Actions come in.
AI Actions allow an AI agent to trigger structured, predefined operations during a live conversation while the call is still happening, rather than just talking to a customer at the moment. For example, the AI agent can trigger an escalation, transfer the call to a human, update an external system, or emit a signal that something important just occurred, all in real-time.
In the above example, you can configure the agent to validate the contact’s frustration, and either try to contain the conversation for a bit longer (i.e., “I’d be happy to connect your to a human representative after collecting some more information”) or in more sensitive cases, call a transfer action to escalate right away. This realtime reaction signals to the contact that their concerns are heard, and acted upon.
Importantly, these actions don’t disappear after the call. Every Custom Action invocation is recorded in the transcript, which means it becomes part of the permanent call record and can be analyzed and reported on later.
Post-Call decisions: Custom AI analysis with full context
.png)
Once the call ends, a different class of questions becomes possible.
Now we’re no longer asking, “What should the agent do right now?” We’re asking questions like:
- How engaged and interested is the customer?
- What are the customers’ current needs and pain points?
- How should future outreach change for this contact?
These answers depend on the entire conversation, not a single moment. To answer these questions, you’ll require a nuanced understanding of not only what was said on the call but the contact’s engagement, interest, and needs. With Custom AI Analysis, you can easily capture these fuzzy signals to evaluate the call’s outcome and success, and personalize future outreach.
With Custom AI Analysis, you can define a set of structured data points (i.e., interest, frustration, use case) to be automatically extracted via LLM from the full post-call transcript. These results are emitted in the `call.analysis.available` event and can be used throughout Regal to trigger Journeys, update contact profiles, schedule future tasks, or drive downstream reporting.
For example, an insurance carrier can set up Custom AI Analysis data points across all discovery calls to extract each prospect’s primary question, objection, and readiness to buy. By analyzing full transcripts holistically, Custom AI Analysis can surface patterns that aren’t obvious from individual calls, such as frequent confusion around deductible structures for a specific policy. These insights can inform how your agent addresses the most common points of friction moving forward to maximize containment and conversion.
Unlike prompt AI actions, Custom AI Analysis is triggered after the call is over, so it benefits from maximum context. It’s best suited for nuanced classification and outcome decisions where meaning emerges over time, not in a single utterance.
Evaluating the agent: AI scorecards
Not every question you want to answer is about the contact. Some questions are about the agent itself.
Did the agent follow the qualification script? Did it ask the required questions? Did it handle objections appropriately? Was the tone aligned with your brand?
These are performance-focused questions, not outcome-focused questions, and AI Scorecards are designed to answer them.
AI Scorecards use LLMs to evaluate calls against success criteria you define, focusing on how the agent performed rather than what the contact decided. Scorecards make it easy to roll up insights across many conversations and identify trends in agent behavior without manually reviewing transcripts.
For example, a university admissions team can apply an AI Scorecard to inbound inquiry calls to evaluate whether AI agents followed the required tour-booking process. The scorecard automatically validates whether the agent asked for the student’s full name and email, confirmed their program of interest, offered to schedule a campus tour, and clearly explained next steps. By scoring every call against the same criteria, the team can quickly identify gaps in execution.
Since the evaluation is performed by an LLM, no manual transcript review or keyword searching is required. The model assesses agent performance using natural language understanding rather than rigid phrase matching, meaning it can recognize when an advisor offered to book a tour even if the wording varied from the script.
Scorecards also benefit from full-context visibility by evaluating the conversation after it ends. However, unlike Custom AI Analysis, the results are meant for quality assurance and iteration, not for driving contact-level actions.
zooming in on specific language: moments
Sometimes you don’t need a full interpretation of a call. When you’re troubleshooting a particular step in the agent script or validating the agent’s language to ensure appropriate messaging and tone, you just need to access a particular part of the conversation.
Moments are designed for this exact purpose. They identify and tag specific lines or segments of a conversation after the call ends, making it easy to search, filter, and audit conversations at scale without laborious or manual investigation.
Regal supports two types of Moments. Phrase-based Moments look for exact keywords or phrases for ensuring compliance language or required disclosures occurred. AI Moments go a step further, allowing you to describe a concept or provide examples in a text-based prompt, especially if you’re not sure exactly how it will be phrased (i.e., Did the contact mention they’re reviewing competitor solutions?). An LLM then tags parts of the conversation that match that description.
Moments operate at the level of individual points on the conversation timeline. They don’t attempt to classify the entire call or make outcome decisions. Instead, they make it easy to understand where certain topics appear and how often they occur.
Putting It All Together: Designing Along the Timeline
The most effective AI agents don’t rely on a single data mechanism. They’re designed with the conversation timeline in mind:
- AI Actions respond to contact signals as they happen
- Custom AI Analysis interprets the full conversation after the fact
- AI Scorecards evaluate agent performance across many calls
- Moments identify key sections within a call for reporting, troubleshooting, and compliance
If you’re ever unsure which tool to use, ask these questions:
- Does this decision change the live call experience? If so, rely on AI Actions.
- Does this decision require the full context of the conversation? If yes, consider the following questions:
2a. Is this data used for monitoring the entire conversation, or a specific part? If it is for a specific part of the conversation, use Moments to capture full-context signals during the call. If the data is used for monitoring the entire conversation, consider the next question:
2b. Is this data used to evaluate the agent or the contact? If you are evaluating the agent, use AI Scorecards to evaluate calls against success criteria you define. If you are evaluating the contact, use Customer AI Analysis to holistically interpret the contact's engagement, interest, and needs.
By aligning data collection with when decisions should be made, you give your AI agents the structure they need to act intelligently, without forcing every insight into the same moment or mechanism.
Ready to optimize your AI agent decision-making? Schedule a demo with us.
Latest Blog Posts
.png)
.png)
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.
How to Make Voice AI Agents Think and Act Like Your Best Human Agents
See how modern AI voice agents can match your best human reps by building five core capabilities into every call: spatial awareness, temporal awareness, sensory perception, proactive retrieval, and real action-taking. This post breaks down what each pillar means in practice and how they turn voice AI from a conversational bot into a fully empowered operator.
.png)
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.
.png)
.png)
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)
.png)
October 2025 Releases
October’s releases give you deeper structure and insight across your AI operations—from designing predictable, multi-state conversation flows and delivering seamless human handoffs to uncovering performance insights and strengthening your agents’ knowledge for continuous improvement.
.png)
.png)
.png)
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.
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.
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.
%20(1).png)
%20(1).png)
August 2025 Releases
New features include automated test evaluations, the Regal Improve insights dashboard, PII-safe recording actions, 25 ultra-realistic voice options, bulk Knowledge Base URL upload, and expanded quiet hours compliance—designed to accelerate iteration, improve agent performance, and safeguard customer trust.
%20(1).png)
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.
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.
.png)
%20(1).png)
.png)
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.
.png)
.png)
.png)
%20(1).png)
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.
.png)
.png)
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.
.png)
AI Voice 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).png)
June 2025 Releases
June’s releases give you more control to test, improve, and scale AI agents—while also making life easier for human agent teams. From real-time debugging tools to capacity control and a floating Chrome extension, we’re unlocking faster workflows, better control, and stronger performance across the board.
.png)
Caller ID vs. CNAM vs. Branded Caller ID: What’s the Difference?
Caller ID, CNAM, and Branded Caller ID all help identify an incoming call and, therefore, increase call answer rates. Find out how they differ and how outbound phone sales teams can utilize each to reach prospects and customers effectively.
.png)
%20(1).png)
%20(1).png)
%20(1).png)
%20(1).webp)
.avif)
.png)
The Automated Phone System Revolution: Why 73% of Enterprises Are Getting It Wrong (And How to Get It Right)
Explore how automated phone systems are transforming enterprise communication strategies. Learn how to avoid common pitfalls, optimize customer journeys, and achieve ROI through strategic deployment across industries like healthcare, insurance, and education.
%20(1).png)
.png)
.webp)
.webp)
.webp)
.webp)
.webp)
.webp)
.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)
%20(1).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.
.webp)
.webp)
.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)
.webp)
.webp)
.webp)
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.
