Tool Use: How Agents Take Action
Discover why tool calling — letting the model invoke functions — is what transforms a chat model into an agent that affects the world.
Tool Use: How Agents Take Action is a free AI Agents lesson on CoddyKit — lesson 3 of 3. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the AI Agents learning path, one of 3 lessons in the course, and your progress syncs across the web and the CoddyKit app.
Beyond talking
An LLM can only produce text. To really help, an agent needs tools: ways to act in the real world. 🛠️
What's a tool?
A tool is just a function the agent can call, like search the web, check the weather, or do some math.
An everyday analogy
Think of tools as apps on a phone. The agent picks the right one for the task, just like you tap the right app.
How it decides
You describe your tools to the agent. It reads the task and chooses which tool fits, then asks to use it.
A simple tool
A tool can be tiny. Here's one that adds two numbers, the kind of thing an agent might call.
def add(a, b):
return a + b
print(add(2, 3))The agent doesn't run it
The LLM doesn't run code itself. It says 'please call add with 2 and 3', and your program runs it and returns the answer.
Back to the loop
Remember think-act-observe? The agent calls a tool (act), reads the result (observe), then decides the next step.
Chaining tools
Hard tasks become easy when an agent chains tools: search, then summarize, then send. One small step at a time.
Clear tool descriptions
Just like prompts, tools need clear descriptions. The better you explain a tool, the smarter the agent's choices.
You did it! 🚀
You now know agents = brain + prompts + tools, working in a loop. That's the foundation. Be proud, you moved fast!
Quick Check
Last one! When an agent uses a tool, who actually runs it?
Frequently asked questions
Is the “Tool Use: How Agents Take Action” lesson free?
Yes — the full text of “Tool Use: How Agents Take Action” is free to read here on the web, and the AI Agents course includes 3 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the AI Agents course, upgrade to CoddyKit PRO.
What will I learn in “Tool Use: How Agents Take Action”?
Discover why tool calling — letting the model invoke functions — is what transforms a chat model into an agent that affects the world. You practise AI Agents with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.
Do I need any experience to start AI Agents?
No prior experience is required. AI Agents on CoddyKit is structured for beginners through advanced learners; this is — lesson 3 of 3, so you can start here or from the beginning and move at your own pace.
How long does the “Tool Use: How Agents Take Action” lesson take?
Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.
Can I write and run code in this AI Agents lesson?
Yes. Every AI Agents lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.
All lessons in this course
- What Is an LLM-Based Agent?
- Prompts, Roles and System Messages
- Tool Use: How Agents Take Action