Should You Be Using Agentic AI?

Author(s): Marc Matterson

Originally published on Towards AI.

Move over RAG, a new AI trend is about to take 2025 by storm.

This member-only story is on us. Upgrade to access all of Medium.

Since the release of ChatGPT in 2022, the field of Artificial Intelligence (AI) has grown exponentially. Large language models (LLMs) are all the range, even the world's biggest tech companies are competing to see who can produce the best-performing model with the hope of eventually reaching artificial general intelligence (AGI).

It is common knowledge that current techniques being implemented to advance LLM abilities are not sufficient to achieve AGI. In 2024, Retrieval Augmented Generation (RAG) was widely adopted helping LLMs retrieve more relevant information via the use of vector databases. Although this improved performance, more innovation was needed.

As we enter 2025, agentic AI is the newest approach believed to further close the gap between where we are today and where we need to be to achieve AGI. Agentic AI requires minimal human intervention and is a lot more equipped to solve more complex problems.

In this article, we will first discuss the history of AI and how we got to where we are today. We will discuss current steps taken when implementing a RAG-based architecture, before finally explaining what agentic AI is, when you should use… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI