SEPTEMBER 2023 RELEASES
September 2023 Releases
Context Engineering for AI Agents: When to Use RAG vs. Prompt
As AI voice agents grow in capability and complexity, so does the challenge of managing what they know, how they say it, and when they say it.
The three primary methods for context engineering a Regal AI Voice agent are:
- Prompting
- Retrieval-Augmented Generation (RAG) via Regal Knowledge Bases (KBs)
- Custom actions
Each has distinct advantages, and misusing either can lead to performance degradation, hallucinations, or bloated prompts that are hard to maintain.
We'll walk through how to decide what to keep in the prompt and what to shift to a Regal Knowledge Base or custom action, with examples and technical considerations.
When to Use the Prompt
The prompt defines core agent behavior, tone, logic, and task flow.
It's evaluated at the start of the conversation and guides all interactions. Prompt content should be compact, essential, and mostly static.
Use the prompt for:
1. Role framing and tone
You can do this in the “Role & Goals” and “Agent Style” dropdowns in Regal:
Specifically:
- Defining who the agent is (e.g. "a qualification agent for Circle Bank")
- Describing how the agent should sound (e.g. professional, upbeat, enthusiastic)
- Reinforcing behavioral guidelines ("be clear and direct")
2. Task structure and conversation logic
For this, you'll use the “Task Steps,” "Questions & Objections Handling," and "Greeting" dropdowns:
To edit things like:
- Greeting scripts
- Objection handling
- Escalation rules
- Conditional logic using dynamic variables
3. Guardrails
For example:
- Explicit instructions for what the agent should not do (e.g. “Never discuss specific interest rates”)
- Default behavior when information is missing or ambiguous
%20(1).webp)
4. Short, high-priority FAQs or objections
For common objections that require fast, consistent phrasing. Ideal for when answers are short and stable over time.
5. Triggering structured logic
Defining how and when to invoke custom actions (e.g. a pricing lookup or scheduling call).
%20(1).webp)
Why?
The prompt is the deterministic core of your agent. It governs tone, behavior, sequencing, decision-making, and when to invoke structured logic.
Because it’s always loaded and evaluated across the full conversation, the prompt is the right place for anything that needs to consistently shape how the agent acts. In contrast, RAG content is only referenced conditionally (when retrieval is triggered by context).
That makes the prompt your agent’s brain, not its encyclopedia. It’s where you define how the agent thinks and behaves, and should focus on control (i.e. logic, flow, and guardrails).
It's not for storing large amounts of reference material. Including too much static or reference material bloats the context window, risks crowding out critical instructions, and can degrade reliability.
A lean, well-structured prompt keeps your agent fast, predictable, and easier to maintain.
Sample Use Cases for Prompting
When to Use A Knowledge Base (RAG)
Regal’s Knowledge Bases allow you to ingest long, structured content like support documentation or policy language and access it dynamically during the conversation through RAG.
The agent retrieves the relevant information based on real-time context, keeping prompts lean and responses accurate.
Use RAG for:
1. Support documentation
- Help center articles
- Troubleshooting guides
- Integration steps and product walkthroughs
2. Long-form or evolving FAQs
- Dozens or hundreds of questions that change over time
- Content maintained by support or product teams in external systems
3. Legal, compliance, or policy content
- Return policies, privacy rules, benefit eligibility, etc.
- Where verbatim accuracy is critical
4. Multi-state or personalized logic
- Where rules vary based on geography or customer type but don’t require structured computation
- For example: “What’s the refund window in New York?”
5. Any content too large or volatile for a prompt
- Markdown files, long Google Docs, PDFs, etc.
- Support for up to 300 URLs or 25 files per KB
See how you can create a Knowledge Base and connect it to an AI Agent.
Why?
RAG allows agents to scale their knowledge without compromising speed or behavior.
It decouples factual content from behavior logic, enabling you to update policies, support docs, and how-to material without touching the prompt.
This separation keeps the agent’s core logic stable while allowing its knowledge to evolve.
Regal’s retrieval engine automatically indexes long-form content and surfaces relevant sections based on the RAG’s configured description and real-time conversational context.
RAG works best for unstructured or narrative information, rather than structured data, as it cannot compute values, perform sorting, or reliably extract from things like pricing tables or state-based rules.
%20(1).webp)
And because retrieval depends on context, it introduces non-determinism, meaning responses may vary slightly across otherwise similar conversations.
Sample Use Cases for RAG
When to Use a Custom Action
Custom Actions are how Regal AI agents integrate with APIs or structured data sources. They allow the agent to perform precise lookups, execute business logic, or fetch real-time information from external systems.
This is the best choice when the agent must query structured data, perform conditional logic, or execute real-time transactions.
While prompts are ideal for orchestration and RAG is great for unstructured reference material, custom actions are essential when the agent must deliver precise, dynamic outputs.
Only Custom Actions can fetch exact values (like account balances or appointment slots), evaluate multi-condition rules, or write back to external systems without risking ambiguity.
Use Custom Actions for:
1. Structured data stored in external systems
- CRM fields, pricing tables, and product catalogs
- ZIP-based eligibility rules or region-specific configurations
2. Real-time, personalized values
- Deductibles, open balances, order status, or delivery tracking
- Appointment availability or dynamic inventory by location
3. Logic-driven branching or evaluation
- "If tier = Gold and state = CA, show Option B"
- Multi-condition rules that influence what the agent should say or do
4. Triggering operations in downstream systems
- Updating contact info, submitting a support request, or creating a lead
- Logging actions or changes directly into your backend systems
5. Structured rules that require precise application
- Tax calculations, qualification thresholds, or discount rules
- Any case where data must be computed, sorted, or matched exactly
> See a detailed rundown of how to create a custom action for your AI Agent.
Why?
Custom Actions provide a deterministic, API-driven bridge between your agent and the systems it needs to interact with. They’re purpose-built for structured logic and data retrieval—tasks that cannot be reliably handled by prompts or RAG.
So on call, when a contact asks a question, the AI Agent retrieves info from an external system with the custom action, and then uses that information to respond to the question.
RAG can't perform logic or precision extraction, and prompts can't dynamically access live data.
Custom actions guarantee consistency, enable branching logic, and return exactly the values your agent needs in order to respond accurately and maintain compliance.
Sample Use Cases for Custom Actions
Prompt vs. RAG vs. Custom Action
%20(1).webp)
Context Engineering Decisions that Scale
Context engineering an AI agent requires more than just good content, it requires knowing when and how your agent should reference that content.
Prompts, knowledge bases, and custom actions each serve a different role, and using them interchangeably can lead to bloated logic and systems that are hard to manage and update.
To build agents that scale reliably:
- Use the prompt to control behavior, tone, and decision logic.
- Use the Knowledge Base (RAG) for long-form, factual, unstructured or semi-structured content that supports dynamic responses.
- Use custom actions to integrate with structured data and real-time systems.
Clear boundaries between these layers make your agents easier to test, maintain, and improve.
Frequently Asked Questions
What information should stay in the prompt instead of a knowledge base?
Keep core behavior, tone, conversation logic, guardrails, and instructions for invoking custom actions in the prompt. It should be compact, mostly static, and evaluated across the entire conversation.
When should short FAQs or objection responses live in the prompt rather than RAG?
Use the prompt for brief, high-priority FAQs or objections that need fast, consistent phrasing and don’t change often. Move longer or frequently updated FAQs to a Knowledge Base.
What types of content are best suited for RAG, and what are its limits?
RAG is ideal for support docs, long or evolving FAQs, and policy/legal text that must be referenced verbatim. It can’t compute values, sort, or reliably extract from structured tables, and responses may vary slightly due to non-deterministic retrieval.
How do I choose between RAG and a custom action for state- or customer-specific rules?
Use RAG for narrative rules that vary by geography or customer type but don’t require computation. Choose a custom action when you need precise rule evaluation, structured data lookups, real-time values, or to trigger operations.
Why is it a problem to pack lots of reference material into the prompt?
Large reference blocks bloat the context window, crowd out critical instructions, and can degrade reliability. Keeping the prompt lean preserves speed, predictability, and maintainability.
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)
