I spent a big chunk of today learning all about AI agents. Here’s how researchers describe them:
“As opposed to zero-shot prompting of a large language model where a user types into an open-ended text field and gets a result without additional input, agents allow for more complex interaction and orchestration. In particular, agentic systems have a notion of planning, loops, reflection and other control structures that heavily leverage the model’s inherent reasoning capabilities to accomplish a task end-to-end. Paired with the ability to use tools, plugins, and function calling, agents are empowered to do more general-purpose work.”
From: The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
Agents have a lot of potential to automate all kinds of knowledge work tasks and I’m excited to build a few things with them. I’ll be sharing my first experiment with them tomorrow.