Model Anatomy · Episode 03 · 30-second cut · 0:39
The one loop inside every AI agent, in 9 lines of Python
Think, act, observe, repeat, with a step limit so it never runs forever. It searches Q3 revenue (4.2 million), takes 15% and answers $630,000.
Key moments
What you’ll needPython 3.10+
What you’ll need
- python.org/downloads →
Python 3.10 or newerRuns the code. Check yours with python3 --version. - code.visualstudio.com →
VS Code or CursorEither works; so does any editor you like. - git-scm.com/downloads →
gitGets the code from GitHub. - No packages needed: it uses only the Python standard library.
Set it up
- 1Get the code
git clone https://github.com/DayanEbrar0X/data-anatomy.ai.git cd data-anatomy.ai
- 2Make a virtual environmentIt keeps this project's packages separate from the rest of your computer.
python3 -m venv .venv source .venv/bin/activate
- 3Run it
cd ai-engineering/03-ai-agent-loop python3 src/agent.py
Project structure03-ai-agent-loop/
Project structure
ai-engineering/03-ai-agent-loop/Open on GitHub →
- data/
- warehouse.jsonthe numbers the search tool can find
- src/
- agent.pymainthe loop from the video
- model.pythink(): stand-in for the LLM
- tools.pysearch and calculator
- README.mdthe idea, how to run it, a line-by-line walkthrough, things to try
agent.pyOpen on GitHub →
from model import think
from tools import TOOLS
memory = ["What is 15% of Q3 revenue?"]
for step in range(5):
action, arg = think(memory)
if action == "answer": break
memory.append(TOOLS[action](arg))
print("answer:", arg)Transcript
Every AI agent runs on one tiny loop. Think. Act. Observe.
Repeat. Finance asks: what's 15% of Q3 revenue? Give it two tools and a memory holding the question. Each step, the model thinks, then picks an action.
If it's ready, it answers and stops. If not, it runs the tool and saves the result to memory. range(5) is the step limit, so it never loops forever. Run it.
It searches, finds 4.2 million, takes 15%, and answers: $630,000. Think, act, observe, with a limit. That's every agent.
Read the lesson on GitHub →- #aiagents
- #python
- #llm
- #aiengineering
