SEPTEMBER 2023 RELEASES
September 2023 Releases
Introducing Knowledge Bases for AI Agents
LLMs can only generate responses based on what they’ve been trained on. They have no built-in access to proprietary business logic, documentation, or contact-specific data.
Some of that can be solved through prompting.
To drive consistent, best-in-class AI experiences, however, prompting alone isn’t enough. You need a way to dynamically enrich agent context with hyper-relevant information—for any user, at any given time, without sacrificing performance.
That's where retrieval comes into play. Retrieval-Augmented Generation (RAG) further determines what your agent says and when, by dynamically pulling data from trusted, proprietary data sources.
Regal’s new Knowledge Base feature enables Retrieval-Augmented Generation (RAG) directly within the Regal platform, allowing Voice AI Agents to dynamically retrieve information from your internal databases at runtime.
So, instead of having to build and maintain massive prompts or custom API/ETL pipelines (which introduce latency, more failure points, and ongoing maintenance costs), you’re able to have AI Agents pull real context from your data, while preserving low latency, and lower costs, at any scale.
A Closer Look
Regal’s Knowledge Base feature is a new capability that connects AI Agents to your proprietary data sources (product catalogs/documentation, policy docs, support guides, FAQs, etc.).
Here’s what makes it work:
1. Agent-Level Knowledge Configuration
Each agent can have a customized set of Knowledge Base (KB). And each KB can be connected to more than one agent via the Regal platform.
2. Smart, Dynamic Retrieval
Retrieval is triggered dynamically at runtime. Regal invokes the KB only when needed, minimizing unnecessary context injection. This means tighter control, keeping standard call flows clean and performant.
3. Optimized for Relevance and Speed
Retrieval is powered by vector-based search using Amazon Bedrock. The system fetches only the most contextually relevant chunks, which keeps response time low and improves answer precision.
Responses can be further guided by the guardrails and logic defined in your prompts.
4. Flexible Data Ingestion
Knowledge can be ingested from web URLs, PDFs, DOC files, or raw long-form text. So you can centralize data from existing documentation without reformatting or writing new code.
For internal-facing resources like help docs, support wikis, or policy guides that evolve regularly, ingesting via URL allows Regal to periodically rescrape the source. This keeps your AI Agent’s knowledge up to date without requiring manual edits to the agent itself.
5. Context-Aware Usage
Each KB includes a structured usage description that informs the AI Agent when and how to use the content. This allows you to govern retrieval behavior, reducing the risk of hallucinations and improving consistency in how your agents apply the knowledge.
.png)
Real-Time Retrieval Without Prompt Bloat
The Regal Knowledge Base gives you a scalable way to inject proprietary knowledge into your AI Agents so they can deliver smarter, brand-aligned, compliant conversations, without relying on bloated prompting or custom integrations.
Here’s what the feature enables:
Predictable Agent Behavior
Because KB content is separate from the prompt, your agent’s tone and logic stay tight, even as you scale up the knowledge they use on calls.
Faster, More Accurate Answers
Regal AI Agents fetch answers in real-time, while always reverting to the correct source of truth.
RAG enables us to determine when the LLM should or should not be relied on. When the answer requires a more grounded or branded response, we never rely on the LLM.
This allows agents to handle everything from lightweight inquiries, to complex, regulated scenarios, ensuring every response is contextually accurate, brand-safe, and compliant.
Lower Prompt Latency
Decoupling the KB from the prompt keeps token size small, which leads to faster LLM responses and lower processing costs (while still allowing you to prompt and build guardrails as strictly as you’d like).
Contextual Retrieval at Scale
Whether it’s answering product FAQs, scheduling appointments, or resolving policy-related questions, the RAG approach ensures that agents retrieve only the most relevant knowledge based on the specific context of the contact and the call itself.
If a contact is based in California, for instance, the AI Agent can pull California data only, referencing legislation, product availability, and other FAQs. It keeps conversations compliant, targeted, and useful.
Where to Use It
Regal’s Knowledge Base feature is ideal for use cases where the AI Agent must reference detailed, dynamic, or regulated content mid-call.
For short, predictable content, you can use prompting to dictate LLM responses. For scalable, more dynamic information, use a Knowledge Base.
Common Use Cases Include:
%20(1).png)
Why It Matters for Your Business
RAG-based Knowledge Bases are a key enabler of real AI transformation, because they help:
- Preserves prompt space for high-impact logic: Shifts reference material into structured retrieval so prompts can focus on agent tone, behavior, and decision-making.
- Improves answer quality and accuracy: Responses are grounded in authoritative content, reducing hallucinations and ensuring alignment with current business policies.
- Scales humanlike conversations efficiently: AI Agents can deliver humanlike responses at any scale, without requiring you to increase headcount. A major cost-saver.
With Regal Knowledge Bases, your AI Agents can now deliver more accurate conversations at scale, while giving your team full control over what’s being said.
How to Configure Knowledge Bases in Regal
You can configure Knowledge Bases directly inside the Regal Agent Builder. Here’s how:
- Upload your content via the Knowledge Base tab (URL, doc, or plain text).
- Link the KB to the relevant Agent via the Agent settings.
- Write a KB Description to tell the LLM what the content is and when to use it, along with other essential guidance. This will help improve retrieval relevancy and speed.
- Prompt stylistically by including examples of how the agent should format its responses coming from KB content. Tailor prompts to your use case across both voice and SMS.
- Test the Agent to view what content is being retrieved and when, and if the agent is phrasing everything correctly.
Manually monitoring scripts and measuring containment rate (depending on the use case) will give you a good sense of whether or not the AI is effectively referencing your knowledge bases.
Tip: Start with 1–2 KBs per agent, and expand from there if needed. Tune from there based on call type and complexity.
See detailed instructions on how to add a Knowledge Base to Regal.
Enterprise-Grade Knowledge in Every Conversation
With Regal Knowledge Bases, you can scale your AI Agents with real data, without sacrificing speed, performance, or control.
Want help launching your first KB-backed agent? Book time with our team.
Latest Blog Posts
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)
.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)
.avif)
.avif)
5 Ways to Improve Agent Productivity & 5X Outbound Performance
In this blog, we share tips to improve agent productivity for handling high volumes of calls, whether it's inbound support teams or outbound sales teams. The guiding principle is simple — focus your agents on tasks that absolutely requires their attention, and automate everything else.
.avif)
8 Strategies to Improve Call Answer Rates by 40%
Discover 8 proven strategies to improve call answer rates by 40%. Learn how personalized outreach, Branded Caller ID, and AI-driven solutions can transform your outbound contact center and boost engagement. Increase your call answer rates and drive more revenue today!
.avif)
.avif)
Insurtech Insights: How Regal Drives Revenue Across the Policy Lifecycle
Our Co-Founder & CTO, Rebecca Greene, delivered a presentation at the recent Insurtech Insights NYC 2024 event about how insurance brands can meet the moment of global uncertainty and rebuild trust by turning untapped customer data into personalized, revenue driving conversations across the Policyholder lifecycle.
.avif)
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.
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.
