Project: Creative Apps - PromptSpark AI Creative Agent (CLI)

[a-villarruel]

Track

Creative Apps (GitHub Copilot)

Project Name

PromptSpark – AI Creative Agent (CLI)

GitHub Username

@a-villarruel

Repository URL

https://github.com/a-villarruel/promptspark

Project Description

PromptSpark is a lightweight AI Creative Agent built in Python that transforms simple user input into structured, pitch-ready product concepts.

The system is designed as a modular agent rather than a simple API wrapper. It separates orchestration, prompt engineering, and model communication into independent layers. The CLI interface collects user intent, the prompt module enforces structured reasoning, and the API layer securely handles interaction with the language model.

Given a category and a base idea, PromptSpark generates a complete innovation outline including product name, tagline, description, key features, target audience, and a unique creative twist. The structured output is driven by intentional prompt engineering to ensure clarity, consistency, and usability.

The project was intentionally built as a focused MVP emphasizing clean architecture, secure environment handling, and scalability. It can evolve into a multi-agent system, integrate memory or scoring mechanisms, or be deployed as a web-based ideation tool.

PromptSpark demonstrates how practical, task-oriented AI agents can be designed with modular architecture and controlled reasoning instead of unstructured text generation.

Demo Video or Screenshots

Demo video: https://youtu.be/XbGdlCVr0Io

Primary Programming Language

Python

Key Technologies Used

• Python 3
• OpenAI API
• python-dotenv
• Modular CLI architecture
• Prompt engineering techniques
• Git & GitHub

Submission Type

Individual

Team Members

No response

Submission Requirements

• My project meets the track-specific challenge requirements
• My repository includes a comprehensive README.md with setup instructions
• My code does not contain hardcoded API keys or secrets
• I have included demo materials (video or screenshots)
• My project is my own work with proper attribution for any third-party code
• I agree to the Code of Conduct
• I have read and agree to the Disclaimer
• My submission does NOT contain any confidential, proprietary, or sensitive information
• I confirm I have the rights to submit this content and grant the necessary licenses

Quick Setup Summary

1. Clone the repository
2. Create a virtual environment
3. Install dependencies
4. Create a .env file and add your OPENAI_API_KEY
5. Run the agent (python main.py)

Technical Highlights

• Modular agent architecture separating orchestration, prompt design, and model integration
• Structured prompt engineering to enforce consistent multi-section outputs
• Secure environment variable handling (no hardcoded secrets)
• Clean CLI UX with input validation and formatted output
• Designed for scalability toward multi-agent evolution

Challenges & Learnings

One key challenge was designing prompts that consistently produce structured, non-generic outputs. Early iterations generated creative but inconsistent responses.

Through prompt refinement, I learned how to enforce output structure while preserving creativity. Separating prompt logic from orchestration also reinforced the importance of modular design when building AI-driven systems.

Another important learning was treating the system as an agent rather than just an API call. Thinking in terms of orchestration, reasoning structure, and scalability significantly improved the design quality.

Contact Information

antonio_villarruel@hotmail.com

Country/Region

Argentina