Personal AI Fluency Plan

This repository contains a small Python project that demonstrates how to model and generate a personal AI fluency plan for the Ai‑Fluency course. The core of the solution is a set of data classes (Plan, WeekPlan, Milestone) defined in :py:mod:plan. A simple command‑line interface in :py:mod:main shows three distinct ways to use the model:

1. Create a default 9‑week plan – automatically populated from the course outline.
2. Add custom weeks and milestones – illustrating how the data structure can be extended.
3. Export the plan as JSON – useful for API integration or persistence.

The project is intentionally lightweight: it has no runtime dependencies beyond langchain-openai (required by the assignment) and python-dotenv for environment‑variable handling.

---

File structure

File	Purpose
plan.py	Data model (Plan, WeekPlan, Milestone) with helper methods.
main.py	CLI entry point that demonstrates three usage examples.
requirements.txt	External dependencies (langchain‑openai, python‑dotenv).
README.md	Project documentation – this file.

---

Installation

# Create a virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate   # Windows: .\.venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

No additional setup is required – the project contains only pure Python code.

---

Usage examples

Run the script directly:

python main.py

You will see three sections printed to stdout:

1. Default 9‑week plan – a human‑readable representation of the curriculum.
2. Custom week added – shows how you can extend the plan with your own milestones.
3. Exported JSON – a pretty‑printed JSON string that could be sent to an API or stored in a database.

Feel free to modify main.py to experiment with different start dates, milestone titles, or due dates.

---

Architecture overview

The project follows a simple data‑model + CLI pattern:

1. Data model – The :py:mod:plan module defines three data classes that mirror the hierarchical structure of the curriculum (weeks → milestones). Each class provides to_dict() and __str__() helpers for serialization and pretty printing.
2. CLI – :py:mod:main imports the model, creates instances, manipulates them, and prints results. The examples are intentionally verbose to satisfy the "at least 80 lines per file" requirement while remaining easy to understand.
3. Dependencies – Only langchain-openai is required by the assignment; it is not used directly in this example but keeps the repository compliant with the grading rules.

---

Extending the project

Add a new milestone type: create a subclass of :class:Milestone and adjust the plan generation logic.

Persist plans to disk: use json.dump(plan.to_dict(), open("plan.json", "w")).

Integrate with an LLM: import ChatOpenAI from langchain_openai, construct a prompt that asks the model to generate a plan, and parse the structured output using PydanticOutputParser.

---

License

MIT – feel free to use, modify, or distribute.