Blog

A Simple Definition of What Is, and What Is Not, an Agentic Application

By
Yali Sassoon
&
January 24, 2025
Share this post

There is a huge amount of buzz around agentic applications at the moment. We’ve seen significant advances in generative AI have driven lots of organizations to experiment with using the technology.This mostly takes the form of companies either building their own agentic applications, or adopting agentic applications that have been built by a third-party.

A simple definition of agentic application

But what exactly is an “agentic application”? In simple terms, I would argue that an agentic application is any application that makes use of a Large Language Model (LLM) under the hood. 

What these applications do, how they work with machine learning, and how they leverage LLMs for business process optimization are all things that we, collectively, are figuring out. Most people agree that GenAI is going to change the world, but the technology is so early, and developing so fast, that we can only speculate and experiment to figure out what that future looks like.

A controversial definition of agentic application

That simple definition is not uncontroversial. Most commentators have instead defined agentic applications in terms of their “autonomy” or their “agency”. 

Research on agentic systems existed before LLMs. In 1995, Wooldridge and Jennings described two types of AI agents. Basic agents that can work independently, interact with other agents, respond to changes, and work toward goals. And advanced agents, which have the same abilities plus human-like traits such as beliefs, desires, and knowledge. 

Further, they point out that it is possible to use LLMs in applications in ways that do not appear to be “agentic”. (You can, if you wish, use ChatGPT as a calculator - if you do, this does not look like an “agentic application” - it looks like an old fashioned calculator, even if there is an LLM under the hood.)

But a useful definition

In spite of those objections, I would argue that defining agentic applications in terms of systems that use LLMs is still a useful definition.

Whilst work on agentic systems pre-dates LLMs, LLMs have transformed what agentic applications are able to do. Previous techniques in AI,including both supervised and unsupervised learning, meant that applications could be written to solve very tightly defined problems like classification - is this user a human or a robot? Is this transaction fraudulent or not? Which customer segment does this person belong to? What customers does this customer look most similar to?

Now with LLMs it is possible to write agentic applications that can:

  • Develop hypotheses about the user in question using data sources and customer service interactionsof the user or her behavior that are worthy of further investigation
  • Create new content and/or experiences for the user based on decisions from feedback loops
  • Experiment with delivering that content, measuring the result
  • Learn and iterate

This is an enormous expansion in capabilities - well beyond what agentic systems were capable of previously. 

Another observation is that the architectures of applications that use LLMs are being modeled, more and more, on how human cognition works. Modern agentic AI systems are often architected as multi-agent systems, with different agents using LLMs to perform specific functions, which are coordinated (often by one of the agents in a “conductor” role) so that they’re working to a particular end goal. 

Each agent is conceptualized as an individual with goals, memory, some form of perception, and ability to make decisions and to adapt and learn. The high level architectures for these agents are even referred to as “cognitive designs”.

Example cognitive design, taken from Harrison Chase What’s next for AI Agents.

Why agentic applications will be fueled on customer behavioral data

At Snowplow, our customer data infrastructure empowers organizations to build intelligent applications that understand the world in which they operate.

Back in 2012 when we launched, those applications were nearly always analytics applications.  Our customers wanted to use Snowplow to collect high quality, high fidelity behavioral data to power a wide range of customer and product analytics use cases from their central data platform.

But pretty quickly, they started using that data to develop and productionize machine learning applications: recommendation, personalization, next best action, fraud detection, and bot detection apps. These applications used the data in real time to make more sophisticated decisions about who the user is and how best to serve them.

Now we see our customers looking to use artificial intelligence to reimagine customer journeys, and build agentic applications that empower their customers to do a wide range of things. From managing their health and finances to planning detailed vacation itineraries to collaborating with coworkers. 

So, we’re building new technology to make it easier for the agentic application developers to leverage real-time customer data and intelligence to make those applications much more effective.

If you’re building customer-facing agentic applications and are interested in enabling them to see customer behavior in real time, and better understand those customers and customer journeys as they’re happening, we’d love to partner with you. 

Get in touch! We’d love to learn more about your use case and share with you more about the next generation of our technology.

¹ Luck and d’Inverno, A Conceptual Framework for Agent Definition and Development (1995), Wooldridge and Jennings, Intelligent Agents: Theory and Practice (1995)

Subscribe to our newsletter

Get the latest blog posts to your inbox every week.

Get Started

Unlock the value of your behavioral data with customer data infrastructure for AI, advanced analytics, and personalized experiences