Episode 3: Demystifying agentic AI

Paula Rivera: Welcome to the AI Factor where we explore how artificial intelligence is shaping the way businesses work. I’m your host, Paula Rivera, and today we’re diving into one of the most exciting frontiers in the AI space, agentic AI.

To help demystify it all, I’m joined by two incredible minds from IntelePeer’s AI application engineering team, Cora Brito and Erica Rusch. They’ve been at the forefront of building real-world agentic systems, and today they’re here to give us an inside look.

Cora Brito: Thank you for having us.

Erica Rusch: Glad to be here.

Paula Rivera: Wonderful. I’m so excited to be talking to you guys.

Before we jump into the heart of the discussion, I just wanted to get a little bit of a fun opener going on here. Taylor Swift recently won a lawsuit that basically made it illegal for people to use AI images specifically for revenge purposes. Think revenge porn.

But likewise, OpenAI recently brought back the Sky voice after Scarlett Johansson controversy, raising questions about consent, AI voice ethics, and how far is too far in synthetic personality creation.

Cora Brito: I think it’s fascinating how voice is like a bridge now between technology and human connection. We’re starting to see more and more cases like this from AI voices and scenarios. It’s a consent and authenticity matter; your voice could almost be considered part of your fingerprint or overall person print.

Erica Rusch: I think maybe Ellen Pompeo from Grey’s Anatomy. She has the most comforting voice, clear, articulate, so you always know what she’s saying, but it doesn’t sound robotic.

Let’s start with some myth-busting.

Cora Brito: One misconception is that all AI is the same. It’s like using the word AI is covering all descriptions. People think that all AI would be exactly the same, like asking if you would get a bike or a rocket ship to go from Point A to Point B.

Another misconception is that AI is a magic employee. Companies believe that if they just get an AI-automated feature, it’s a “set it and forget it” solution. AI will be like an intern, very smart, but still requires training and monitoring that goes behind it.

Erica Rusch: Traditional automation is like an assembly line, while advanced AI in business is adaptable to the real-life nuances of a live interaction. It’s not hard-coded; it adapts in real time.

So, what is agentic AI in simple terms?

Erica Rusch: Agentic AI goes beyond traditional prompting for LLMs; it’s not just a job description but a detailed set of instructions that includes experience. It’s taking the power of building out a beautiful conversation design flowchart and pairing it with the adaptability of generative AI.

Cora Brito: It’s like having tools that allow agentic AI to do tasks previously thought to require human interaction, automating many tasks that previously demanded multiple human inputs.

Erica Rusch: We give it a map of different expected conversation paths and what to do if the conversation deviates from those paths. If it isn’t intelligent enough, we haven’t provided enough context or clarity in our map.

Cora Brito: Yes, many industries, especially customer service and healthcare, will benefit from agentic AI. For example, in healthcare, it can automate tasks such as insurance verification and scheduling.

Paula Rivera: What are the biggest benefits for businesses when implementing agentic AI?

Cora Brito: Costs, scalability, and overall customer experience. The upfront cost may be heavy, but the ROI compounds over time, saving money and growing service capabilities.

Erica Rusch: Companies can see value very quickly with agentic AI—often reducing the time between signing a contract and starting to bill for usage. It’s adaptable and customizable to meet various industry needs.

Cora Brito: We’ve seen customers experience a 20-30% improvement within a month of implementing agentic AI.

Erica Rusch: I believe agentic AI will become more adaptable and configurable as it’s further developed, especially regarding handling voice interactions and customizing customer experiences.

Cora Brito: If we have multiple agents working together, we can create an agent that manages other agents, creating experts in specific tasks and working collaboratively.

Paula Rivera: Before we wind down, I like to do a rapid-fire wrap-up. What AI-powered tool or feature do you use almost daily?

Erica Rusch: Anytime I need to write a document or administrative tasks, I use Gemini or GPT.

Cora Brito: I use Copilot for emails and ChatGPT for various queries.

Paula Rivera: Would you rather have an AI that does your email or your errands?

Erica Rusch: Definitely email.

Cora Brito: I would prefer having AI do my errands, as it can be more complex than managing emails.

Paula Rivera: What’s a movie or TV show that got AI right or hilariously wrong?

Erica Rusch: I loved the series on Netflix called Love, Death & Robots, especially the episodes about AI.

Cora Brito: I found the series Year Million intriguing, as it explores advanced concepts of AI and longevity.

Thank you IntelePeer’s Cora Brito and Erica Rusch for helping us decode agentic AI. If you’re looking to level up your business processes or elevate your customer experience, this episode should give you a strong sense of where the future is headed.