So, I was delivering an AI awareness session earlier this week to 120 eight- to ten-year-olds at my sons’ school. In the Q&A bit, one of the children asked me – “What is Agentic AI?”. Needless to say, I was quite surprised to be asked that question by a nine-year-old. We actually decided to us AI to explain it to the class…. which I must say it did a better job that I would have done.
Agentic AI Explanation for a ten-year-old.
Here is what AI said: “imagine you’ve got a super-duper smart robot friend. This friend doesn’t just follow orders and obey instructions like a regular robot. It is like a super robot, the Dyson of Robots. This Robot can make decisions on its own, like deciding what to do next or how to do something when you haven’t taught it. ‘
Agentic AI’ is like that robot friend, but way more advanced. It can make its own choices, set its own goals, and figure out how to achieve them, almost like it’s got its own mind but by following a set of guidelines and rules. So, it’s not just reacting to commands, it’s thinking ahead and planning like a little strategist!”
Agentic AI for everyone else
I was then thinking, well what if you don’t work in an IT role. Does everyone know what Agentic AI is? It is certainly the buzz term of 2025 and certainly a leap forward from the “chat bots” we have played around with over the past 2 years or so with ChatGPT, Copilot etc.
I was then thinking about how I need to explain Agentic AI to some my co-workers so in my usual style I wanted to write it down to get my wording right. here’s what I came up with which I think and hope anyone can understand. As such I wanted to share it.
So…..
Think of agentic AI as more of “system” than a chat bot. Unlike a chat bot which is generally more about responding to a request or returning information, Agentic AI operates with a high degree of autonomy. Rather than just follows predefined instructions or responding based on information it has been fed/trained on, agentic AI can set its own objectives and determine. by itself, the best course of action to achieve them. This is a very different approach to what we have seen before now since it can not only executes tasks but also identifies opportunities, develops strategies, and takes initiative without constant oversight or being asked.
This has the potential to be a powerful tool in many different roles and organisations. Here’s a few examples I have pulled together based on some of the customer converations and usecases we are exploring at the moment.
Agentic AI Use Cases
- Healthcare : Agentic AI could proactively identify potential health risks in patient data, following or before treatment, suggest personalised treatment plans, and even coordinate with pharmacy and supply chains to ensure medication availability. It could even be used to help patients better understand their health and nurses better explain to patients.
- Gym: It could create personalised workout plans for members, monitor equipment usage to predict maintenance needs, and even suggest new classes based on emerging fitness trends. For Mangement it could suggest changes to class schedules based on enquiries, booking history, attendance etc.
- Retail : It could autonomously manage inventory, predict trends by analysing customer data, external factors such as weather, news events etc, and even optimise pricing strategies based on market demand and competitor analysis such as changing the price of suncream when it gets hot and the price of umbrellas when it rains.
- Public Sector : It could streamline citizen services, anticipate infrastructure needs based on usage patterns, and improve disaster response by dynamically allocating resources. It could also pre-empt and influence bin collections based on realtime data, or take proactive action and make recommendations from transcripts based on interviews or care notes in social services.
- Legal: It could autonomously manage case documentation, chase up cases, predict case outcomes based on historical data, and even recommend legal strategies or layers most likely to win particualr cases. It could provide guiance to customers, based on “learned” cases for that firm and provide “virtual lawyer” services fully automonosly.
- Insurance : Agentic AI could assess risk profiles, help detect fraudulent claims, and tailor policy recommendations to individual customers.
- School Admissions : It could predict enrollment trends, identify potential gaps in student demographics, and optimise the selection process to ensure a diverse and well-balanced student body.
These are just a few examples of Agentic AI’s ability to act independently and adapt to complex, changing environments makes the applications and use cases almost endless as long as we can guide it, trust it and step in when needed.