SEPTEMBER 2023 RELEASES
September 2023 Releases
Introducing Custom AI Analysis: Extract Data from Every Conversation
AI Agents can handle thousands of conversations a day.
Inside each of those conversations, there are dozens of signals that impact the outcome of each individual interaction, and ultimately, the overall performance of your sales and support outreach.
As AI conversations grow in richness and volume, however, it’s become harder to gather these signals at scale in a uniform, automated way.
The challenge isn’t just how you collect data, either. It’s about collecting the right data.
It’s easy to flag keywords in a transcript, but that doesn’t tell you whether a customer was frustrated, or if they were actually interested. Surface-level tagging can’t capture nuance, but LLMs can.
With Regal’s Custom AI Analysis, you can define exactly what data to extract from your AI interactions, doing so automatically, even at enterprise-level call volumes.
What Is Custom AI Analysis?
Custom AI Analysis uses a large language model (LLM) to analyze post-call transcripts and extract the data points you define as most important for reporting and actioning.
You can:
- Capture custom data points: Define what you want to extract (like interest level, use case, competitor mentions, region, or objection reasons).
- Action on data points directly in workflows: Personalize downstream actions with the custom data collected from the previous call.
- Analyze and improve at scale: Segment and report on call outcomes, conversation topics, customer sentiment, etc.
Customized, automated post-call analysis helps unlock the business intelligence buried in every conversation, including (but not limited to):
.webp)
Define the Call Signals that Drive Revenue
Custom AI Analysis lets you define data points (i.e. structured outputs) that capture what happened in the conversation, not explicitly how the agent performed.
For example:
- Identifying the language spoken (e.g., Spanish vs English).
- Detecting opt-out requests or competitor mentions.
- Flagging customer intent (“interested_in_financing”, “needs_callback”).
- Tracking which scripts or objection-handling flows were used and why.
While you can do some light QA with custom analysis (i.e. tracking disclaimer usage and script accuracy), your AI Agent performance measurement should generally be left to scorecards.
When defining data points, you can:
1. Choose from multiple data formats (Boolean, text, number, single-select, or multi-select).
.webp)
2. Either let the AI determine outputs from the conversation (via Text or Number data types), OR explicitly dictate the outputs you want to extract (via Single/Multi-State and Boolean data types).
For example:
- AI Determined Output: Detect if the caller mentions any competitor or brings up pricing objections, and classify it as either “Competitor Comparison,” or “Pricing Concern.”
- Explicit Extraction: Capture when the caller specifically mentions “[Competitor] Premium Package” by name and output a Boolean value (Yes or No).
.webp)
Below, you can see this in practice. On the call, the AI Agent determines:
- An objection (via text, "Are there any fees?")
- The caller's age (via number, "23")
The agent also extracts:
- The caller's intent (via Single Select, "Medium")
- The caller's product interest (via Multi Select, "Checking Account" and "Credit Card")
.webp)
Data points are reusable across agents:
Once defined, a data point isn’t tied to a single agent or workflow.
So, once you’ve created data points for common details like contact information and sentiment, you can apply them across any range of call types, whether it’s for a sales flow, support, or otherwise.
This ensures you’re measuring intent consistently in aggregate, no matter what agent or workflow the data is coming from (more on this later).
Personalize Follow-ups Based on Real Call Context
These custom data points integrate directly into Regal Customer Journeys.
They’re immediately actionable for personalizing follow-up outreach (again, carrying across as many agents or workflows as needed).
For example, on a prospecting call:
- If use_case = home policy bundle inquiry, then follow-up with a call or SMS highlighting home policy bundles and info on how to apply.
- If interest_level = Ready to Buy, route the next call to a licensed specialist.
- If competitor_mentioned = Yes, trigger an SMS designed to address competitive objections.
This turns every call into a self-optimizing feedback loop, meaning the data captured today improves tomorrow’s conversations automatically.
.webp)
Analyze Call Trends at Scale
Regal includes the data points gathered with Custom AI Analysis directly in the call.analysis.available event, so you can pinpoint exactly what happened in a single conversation (intent, objections, competitor mentions, or sentiment) and quickly identify where it succeeded or broke down.
That event would look something like:
"call_analysis": {
"no_ai": false,
"qualification_decision": "qualified",
"did_mention_competitor": true,
"follow_up_required": true,
"budget_confirmed": true,
"compliance_acknowledged": false
These call-level insights are rolled up into aggregate reporting, so you get macro-level performance insights that reveal patterns across entire workflows.
You can:
- Build reporting funnels to see where prospects drop off across different call flows.
- Segment performance by key topics (e.g., how pricing objections impact conversion rates).
- Understand distribution of conversation topics at scale (e.g., what percentage of calls mention competitors vs. product features vs. claims).
Instead of guessing what your customers care about, you know, because every call transcript is being turned into structured data.
.webp)
How does this drive action?
Example 1: Improve Value Positioning to Respond to Competitor Mentions
You know that calls with competitor mentions typically have lower conversion.
One thing you can do is track a “did_mention_CompetitorXYZ” data point.
When tracked across conversations, you find that calls where a competitor is mentioned have lower conversion rates.
Not only does this show how many times Competitor XYZ is mentioned, it points to a solution.
In that case, you could:
- Update the AI Agent’s prompt to include additional/stronger differentiators.
- Trigger follow-ups that directly address Competitor XYZ.
Because the signal is captured in structured form, you can also monitor whether these updates lead to improved outcomes over time.
Example 2: Inform Resource Investment Using Topic Distribution
Let’s say you’re a Medicare provider tracking plan_interest_type across thousands of enrollment calls. After a few weeks, you discover:
- 55% of callers are asking about PPO plans
- 30% mention HMO plans
- The remaining 15% are either interested in dual-eligibility plans, or are unsure what they need
With that data, your team can confidently:
- Prioritize marketing and ad spend on PPO plans
- Reallocate resources to better support that demand
- Update AI Agent flows to focus more heavily on PPO-related questions and objection handling
In both cases, Custom AI analysis enables you to turn conversation signals into structured insights that drive action.
How Different Teams Use Custom AI Analysis
Because Custom AI Analysis is completely configurable, it works across any call type and any industry.
From lead qualification, to inbound support, scheduling, and billing inquiries, the examples below show just how flexible it is.
.webp)
> See a more detailed rundown of how to set this up in Regal.
Put Your Call Data to Work
For contact centers running thousands of calls daily, Custom AI Analysis turns unstructured conversation data into actionable intelligence, without requiring call review and manual logging of highlights.
Custom AI Analysis automatically extracts the signals that matter most, and unlocks the ability to feed them directly into future outreach workflows and performance reporting.
The result: Consistent, detailed insight into customer needs, automated personalization in follow-ups, and faster improvements to your scripts and workflows at scale.
Frequently Asked Questions
How does this feature analyze calls to produce insights?
It uses a large language model to review post-call transcripts and extract structured data points you define as important for reporting and actioning.
What types of data points and formats can I capture?
You can capture Boolean, text, number, single-select, and multi-select fields, such as interest level, use case, competitor mentions, language, opt-out requests, objections, intent flags, and which scripts or flows were used.
How are the extracted data points used in workflows and reporting?
They feed into Regal Customer Journeys for personalized follow-ups, appear in the call.analysis.available event for per-call visibility, and roll up into aggregate reports for funnel analysis, segmentation, and topic distribution.
Can I control whether outputs are inferred by AI or restricted to predefined options?
Yes. Use Text or Number for AI-determined values, and use Single/Multi-Select or Boolean to constrain outputs to specific states or detect explicit mentions.
Are these data points tied to a single agent or used across teams, and do they replace scorecards?
Data points are reusable across agents and workflows for consistent measurement. They can support light QA, but dedicated agent performance evaluation should generally be handled with AI Scorecards.
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
.webp)
.webp)
Outbound Call Center: What It Is, How It Works & Best Practices
The fastest growing High Consideration brands have invested heavily in outbound call centers for sales and marketing. With the right technology, staffing and measurement, you too can build a high performing outbound call center to help hit your growth goals.
Introducing Goal Oriented Agents: Conversational, Dynamic, and Built to Reach Resolution
With Goal Oriented Agents, you can define goal nodes with the information the agent must collect and the prerequisites to get there. A dual-model design keeps the call natural and on track. This makes the agents well suited to complex intake and qualification.
.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.
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.
%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.
%20(1).webp)
.webp)
%20(1).webp)
Beyond CCaaS: How to turn your Contact Center into a Revenue Center
Why are so many contact centers stuck being cost centers? Why do they keep looking for cost reductions instead of revenue increases? Bad data and technology decisions are at the core of this issue. We need "marketing automation" (aka unified customer profiles, event-driven systems and a/b testing) like Regal.io in the contact center to empower teams to start looking for incremental revenue instead.
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.
Innovating on Patient Care | B2C Sales Podcast Episode 7
Explore Eric Hauser's remarkable career journey from GovTech to healthcare disruption at Cadence, highlighting the transformative power of innovation, collaboration, with a special focus on the pivotal role of Regal in driving patient engagement and outcomes.
How SoFi, Perry Health & Allstate Personalize CX at Scale
Discover how Regal.io's AI-powered personalized outreach solutions are revolutionizing outbound sales and customer experience across industries like healthcare, finance, and insurance in our latest eBook, "Modernizing Outbound Contact Centers: How to Treat Millions of Customers like One in a Million."
.jpeg)
Introducing Collaboration-Native Features to CCaaS
Combining collaboration functionality into CCaaS workflow tools invites more cross-functional users from a company to participate in designing the end-customer experience, leading to better omni-channel orchestration and customer outcomes. Learn more about Regal's collaboration features.
How Regal.io is Turning the $40B CX Industry on Its Head
Jon Heaps, former VP, Channel at Observe.ai, Talkdesk, and inContact interviews Alex Levin, Co-Founder & CEO of Regal.io, about the history of the contact center industry and some of the key challenges teams making outbound calls face as customers demand more online experiences.
New SMS & Branded Caller ID Rules Are Enhancing Customer Experience
Are you using Branded Caller ID for outbound calls or SMS? New SMS and Branded Caller ID regulations rolled out in Q2 2023 that you MUST KNOW ABOUT. The new regulations require that every company register their SMS campaigns and Branded Caller ID campaigns before being allowed to send texts or brand calls.
Announcement: Regal Conversation Intelligence
Regal’s Conversation Intelligence drives higher conversion rates for B2C sales teams. We use both the traditional QA/coaching tools, and brand new conversational triggers that allow you to update customer profiles and send automated follow up messages based on what is said in a conversation.
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.
How Regal Helps Consumer Lenders Achieve Growth in Tough Times
Our Co-Founder & CTO, Rebecca Greene, spoke with journalist Tony Zerucha at the recent Fintech Nexus USA 2023 event about how consumer lenders are using personalized phone and SMS sales outreach to obtain growth despite high inflation and rising interest rates.
Meet Regal Call Branding™: Branded Caller ID for 400M+ US Devices
We are excited to announce Regal Call Branding™ including Branded Caller ID. Available on all 400M wireless devices in the US (as well as most of Canada and the UK), Regal Call Branding™ puts you in control of what people see when you call their cell phone – including showing your brand and/or logo.
Q&A with Perry Health’s Scott Chesrown
Get behind-the-scenes insights about Perry Health’s 23% revenue increase with Regal.io. Perry Health’s Scott Chesrown sat down with Regal.io and discussed how they implemented outbound sales technology, integrated new capabilities into their process, and built on their early success.
Drive More Contact Center Revenue With These 6 Holiday Tips
It’s the holiday season and you’d like to hit your December revenue goals. Outbound B2C sales during the holidays can be a major performance driver – if you're prepared and you have the right tools in place. Use these seven tips to get your outbound B2C sales in shape for holiday success.
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.
.png)
.png)
.png)
October 2026 Product Recap
Last month, we shipped releases that improve your contact center operations by extracting business insights with Copilot and reducing wasted agent minutes with our new Voicemail Detection model. The result is more reliable, productive AI agents that can drive revenue for your business.
.png)
How We Built the Voice CX Benchmark
Enterprises need voice agents that hold a natural, human-like conversation while moving each call toward its goal and staying within compliance boundaries. The Voice CX Benchmark scores models on exactly that: how well they progress the call turn by turn, how safely and clearly they communicate, and how quickly they respond.
.png)
Introducing Regal’s Voicemail Detection Model: How We Reduced Voicemails Routed to Agents by 45%
With Regal’s next-generation Voicemail Detection model, you can now classify voicemail, iOS or Google call screeners as separate categories with very high accuracy. This enables screener-specific handling, ultimately reducing missed agent connections.
.png)
September 2026 Product Recap
Last month, we shipped releases that make it easier to build, monitor, and test agents in one interface. Copilot Canvas brings building, editing, and testing into one interface and it can work straight from your files. Multi-state sticky notes let your team document decisions directly on a live agent.
.png)
.png)
August 2026 Product Recap
Last month, we launched features that extend your management of AI agents via MCP and CCaaS platforms. Debug based on agent versions or simulation runs, and manage AI analysis data points via Copilot and Regal MCP. As a Five9 AI Agent Connect partner, Regal now has a dedicated integration API built for Voice AI agents.
.avif)
.webp)
.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.
.webp)