Agents is the latest hot topic in the world of AI. It’s what is needed to fill the concern about how many current AI solutions require the right prompting to get value. What if something was on the endpoint to help understand what is needed? This way all of the input doesn’t come from a user hence users don’t have to always prompt to get value. This reminds me of classic Clippy where you would start writing a resume and Clippy would pop up saying “looks like you are writing a resume, here are ways I can help”.
What exactly is an Agent? huyenchip.com posted a good article giving a overview of Agents found HERE. Here is the agent definition from this post
Agent Overview
The term agent has been used in many different engineering contexts, including but not limited to a software agent, intelligent agent, user agent, conversational agent, and reinforcement learning agent. So, what exactly is an agent?
An agent is anything that can perceive its environment and act upon that environment. Artificial Intelligence: A Modern Approach (1995) defines an agent as anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
This means that an agent is characterized by the environment it operates in and the set of actions it can perform.
The environment an agent can operate in is defined by its use case. If an agent is developed to play a game (e.g., Minecraft, Go, Dota), that game is its environment. If you want an agent to scrape documents from the internet, the environment is the internet. A self-driving car agent’s environment is the road system and its adjacent areas.
The set of actions an AI agent can perform is augmented by the tools it has access to. Many generative AI-powered applications you interact with daily are agents with access to tools, albeit simple ones. ChatGPT is an agent. It can search the web, execute Python code, and generate images. RAG systems are agents—text retrievers, image retrievers, and SQL executors are their tools.
There’s a strong dependency between an agent’s environment and its set of tools. The environment determines what tools an agent can potentially use. For example, if the environment is a chess game, the only possible actions for an agent are the valid chess moves. However, an agent’s tool inventory restricts the environment it can operate in. For example, if a robot’s only action is swimming, it’ll be confined to a water environment.
Check out the rest of the post if you want to get a good basic understanding of agents. If you are interested in AI, you need to understand Agents.