Avoid Messy Code: Design Patterns for AI Agents in Python

From the creator

Check out https://www.squarespace.com/arjancodes to save 10% off your first purchase of a website or domain using code ARJANCODES. If you’re building AI agents in Python and your code is starting to get messy, this video shows you how to use proven design patterns to keep things clean, testable, and scalable. We’ll explore a real-world travel assistant powered by Pydantic AI and apply patterns like Chain of Responsibility, Observer, and Strategy to structure your agents step by step. 💡 Learn how to design great software in 7 steps: https://arjan.codes/designguide. 🔥 GitHub Repository: https://git.arjan.codes/2025/aidesign. 🎓 ArjanCodes Courses: https://www.arjancodes.com/courses. 💬 Join my Discord server: https://discord.arjan.codes. ⌨️ Keyboard I’m using: https://amzn.to/49YM97v. 🔖 Chapters: 0:00 Intro 0:35 Chain of Responsibility — A Modular AI Travel Pipeline 8:33 Observer Pattern — Logging Agent Behavior with Context 12:53 Strategy Pattern — Personalities as Pluggable Agent Prompts 16:58 Why This Matters 17:36 Closing #arjancodes #softwaredesign #python

Published 2025-09-12 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.