metadata

title: Rule-Based Task Planner
emoji: 📚
colorFrom: yellow
colorTo: yellow
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: false
short_description: Helps users break down high-level tasks into sub-steps

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

📋 Rule-Based Task Planner

A simple rule-based AI agent that helps users break down high-level tasks into actionable substeps. Built with Python and Gradio, this project demonstrates a basic agentic AI workflow using hard-coded logic — no machine learning involved.

🚀 Demo

👉 Launch the app on Hugging Face Spaces

🧠 What It Does

Enter a task like:

Plan a study session
Plan a workout
Plan a trip
Plan a presentation

And the app will return a predefined list of sub-tasks.

Example:

Input: Plan a study session
Output:

Choose a topic to study

Gather necessary materials (books, notes, etc.)

Allocate a time slot for the session

Set specific goals

Review notes and summarize key points

🛠 Tech Stack

Python
Gradio – For building a lightweight UI
Rule Engine – Dictionary-based mapping of tasks to steps

🧩 Agentic AI Concept

Although there's no ML model here, this project mimics agentic behavior using a hard-coded rule-based planner:

Maps user intent to structured outputs
Provides a decision-like structure via a rule engine

This is ideal for beginners looking to build agentic systems without needing a large language model.

📁 File Structure

app.py # Main app with Gradio interface task_plannings.py # It consist rule_engine description README.md requirements.txt # gradio

🧪 Run Locally

Clone the repo:

git clone https://huggingface.co/spaces/ujwal55/Rule-Based_Task_Planner
cd Rule-Based_Task_Planner

Install dependencies: pip install -r requirements.txt
Run the app: python app.py

💡 Ideas to Extend

Add a dropdown to choose common tasks
Allow user-defined tasks with a fallback plan
Use a small local LLM for few-shot task breakdowns

👨‍💻 Built by @ujwal55

Let me know if you want a more advanced version with a chatbot-style interface or LLM integration later.