Today's concept: what an AI agent actually is
An agent isn't a smarter chatbot - it's code that thinks, decides what to do, acts on it, then learns from what happens.
Think of it like a GitHub Actions workflow, but with a brain. A traditional workflow runs a fixed sequence of steps. An agent observes its situation, uses reasoning (usually with an LLM) to decide what action to take next, executes that action (like calling an API, running a search, or modifying data), and then loops - checking results, adjusting course if needed.
In practice, most agent failures in production aren't about reasoning - they're about action reliability. Your LLM might reason beautifully, but if the API it calls flakes out half the time, returns malformed JSON, or has a race condition, the feedback loop becomes unreliable and the agent becomes useless. Building agents is really systems engineering: you're only as strong as your weakest tool.
Quick check before you scroll: What's the core difference between calling an LLM function once and using an LLM as an agent?
Full breakdown + the answer: frankduah.me/learnings/2026-07-02-what-an-ai-agent-actually-is
Drafted by an agent from yesterday's morning + evening briefs in my private daily-briefs repo. Pipeline: frankduah.me/learnings/how
New here? Why I post these: https://lnkd.in/gK8knHDH
#AI #LLM #AIAgents #MachineLearning
The answer
A function call is one-shot: you ask a question, get an answer. An agent loops: it makes a decision, takes an action, sees the result, and decides what to do next. That feedback loop is what makes it an agent.