The silent revolution of AI agents

You've probably heard of AI agents, right? If this term sounds strange to you, you may have already interacted with these systems in their simplest form: chatbots. However, the concept of agents goes beyond simple chatbots. They are powerful artificial intelligence tools that tend to impact the future of how we currently work in companies.

Trying to simplify the concept of AI agents in a few words: They are artificial intelligence architectures “empowered” with tools.

These programs are capable of observing the environment in which they are inserted, interacting with the user via LLMs (e.g. ChatGPT), processing information and achieving specific objectives using their tools (e.g. analyzing and creating documents, analyzing databases, reading and creating emails, making phone calls, creating presentations, etc.). They are also able to remember previous iterations (memory) or retrieve specific information (RAG) to provide more contextualized responses.

Let's look at a practical example of an agent that can help companies in their supply chain (an area in which I have worked throughout my career). It is known that many companies waste valuable time “fire-fighting” with daily issues, that is, analyzing and solving unexpected problems that arise in the supply plan on a daily basis.

Now imagine an agent capable of analyzing the tables of your ERP, identifying and solving problems proactively. Watch the video below:

It seems simple, but what this agent is doing is: receiving input from the user, in natural language that is understandable to humans, using SQL commands to analyze the MRP and purchase order database and returning the information to the user. The system also understands terms used by the company: in this example, the system understands that material "at risk" is a material that will have a future availability problem for the customer (stockout).

See the SQL commands an user should use to do the same analysis:

Interesting, isn't it? Using the RAG technique (similar to a "procedure"), the system understands the database, the terms used by the company and executes the activities in the data tables.

But that's not all. With the right tools, agents can interact with each other and perform different tasks. In this example, imagine other agents sending emails to suppliers requesting advances on deliveries, or even requesting fast loads from transport companies. Other agents, for example, creating presentations based on the outputs of other agents. The possibilities are endless.

Finally, AI agents are shaping the future of work, optimizing processes and boosting efficiency in companies. But as they evolve, new challenges arise. How do you imagine adopting these agents in your company? What opportunities and concerns do you see on the horizon?

At 4SME, we are ready to boost your company's results through advanced data analysis. We apply machine learning techniques and adopt best process practices to offer high-quality services and products, helping your business reach new heights.