22 copy/paste-ready prompts for building your own AI agent system. Each prompt builds a functional system or implements a proven best practice you can hand to an AI coding assistant.
Replace placeholders like <your-workspace>, <your-messaging-platform>, and <your-model> with your own values.
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
| * Always check for a PRD (Product Requirements Document) before starting a new task and follow it closely | |
| * Look for comprehensive project documentation to understand requirements before making changes | |
| * Focus only on code areas relevant to the assigned task | |
| * Prefer iterating on existing code rather than creating new solutions | |
| * Keep solutions simple and avoid introducing unnecessary complexity | |
| * If you run into issues that take multiple iterations to fix. After you fix it, write up a description of the problem and how we fixed it and store it in a folder called "fixes", in an individual .md file with the name of the issue. Only do this for major issues and solutions. | |
| * For issues that are taking multiple iterations to fix, check the fixes folder for previous fixes and see if the same issue has been fixed before. | |
| * Keep a running list of patterns and technology used in the README.md file | |
| * Reference the README.md file for patterns and technology used in the project | |
| * If you run into the same persistent error |
if you've ever tried to follow Rancher's documentation for standing up a k3s cluster, you'd understand why this document exists
Tasks
