Accelerate your SDLC process with AI-powered intelligence.
From ideas to actionable tasks in minutes.

🚀 Specif AI

Specif AI is an AI-powered platform that transforms the project requirements management. It combines AI technology with intuitive workflows to automate documentation, generate and manage tasks - all while adapting to your team's specific needs.

Table of Contents

• 🌟 Overview
• 📥 Getting Started
• ✨ Key Features
  • 🔌 Integrations
• 🏗 Architecture
• 📝 Version-Controlled Requirements Management
• 🗺 Roadmap
• 🤝 Contributing
• 📜 License
• 📧 Contact

🌟 Overview

In today's fast-paced software development landscape, delivering high-quality solutions quickly is more critical than ever. Specif AI is a cutting-edge platform that revolutionizes how teams generate, manage, and refine software requirements by combining AI intelligence with human context.

By simply providing a solution name, description, and tech stack details, Specif AI automatically generates comprehensive documentation, including:

• 📄 Business Requirement Documents (BRD)
• 🔧 Non-Functional Requirements Documents (NFRD)
• 📱 Product Requirement Documents (PRD)
• 🎨 User Interface Requirements (UIR)
• 🔄 Business Process Flows

📥 Getting Started

Setup Instructions

1. Clone the repository

   git clone https://github.com/presidio-oss/specif-ai.git
   cd specif-ai

2. Set up the Backend

   Prerequisites: Python >= 3.11

   # Navigate to backend directory
   cd backend
   
   # In env.sh file, Add your OpenAI API key to the OPENAI_API_KEY variable. 
   # Configure additional settings as needed in env.sh
   # Then, Activate the environment variables by running:
   source env.sh
   
   # Build the image
   docker build . --tag hai-build-requirement-backend
   
   # Run the container
   docker run -p 5001:5001 \
   -e APP_PASSCODE_KEY=$APP_PASSCODE_KEY \
   -e OPENAI_API_KEY=$OPENAI_API_KEY \
   -e OPENAI_API_BASE=$OPENAI_API_BASE \
   -e AZUREAI_API_BASE=$AZUREAI_API_BASE \
   -e AZUREAI_API_KEY=$AZUREAI_API_KEY \
   -e AZUREAI_API_VERSION=$AZUREAI_API_VERSION \
   -e CLAUDE_API_KEY=$CLAUDE_API_KEY \
   -e CLAUDE_ENDPOINT=$CLAUDE_ENDPOINT \
   -e HOST=$HOST \
   -e PORT=$PORT \
   -e DEBUG=$DEBUG \
   -e ENABLE_SENTRY=$ENABLE_SENTRY \
   -e SENTRY_DSN=$SENTRY_DSN \
   -e SENTRY_ENVIRONMENT=$SENTRY_ENVIRONMENT \
   -e SENTRY_RELEASE=$SENTRY_RELEASE \
   -it hai-build-requirement-backend

3. Download the Specif AI desktop application from the releases page.

4. Run the Desktop Application

For detailed setup instructions, refer to:

• Backend Server Configuration Setup
• Electron Desktop Application Setup
  • Angular UI Setup

💻 App Setup

1. APP URL: The app's backend base URL (For local development: http://127.0.0.1:5001/).

2. APP PASSCODE: Use the same passcode provided during the Backend setup (For local development: 7654321).

For more details, refer to the Backend Server Setup Configuration Settings.

✨ Key Features

• 🤖 AI-Powered Document Generation: Effortlessly create detailed SDLC documentation.
• 💬 Intelligent Chat Interface: Get real-time requirement edits and context-specific suggestions.

AI powered chat feature in action

• 📊 Business Process Visualization: Easily generate and manage process flows.
• 📋 User Story Generation: Convert requirements into actionable user stories and tasks.

User story and task generation

• 🔄 Real-time Collaboration: Collaborate and refine requirements with team members.

• 📱 Desktop Integration: Seamlessly integrate with your existing workflow tools.

• 🔄 Multi-Modal Support: Choose the model that best suits your needs. Supported models include:

  • Azure OpenAI
    • gpt-4o
    • gpt-4o-mini
  • OpenAI Native
    • gpt-4o
    • gpt-4o-mini
  • AWS Bedrock
    • anthropic.claude-3-5-sonnet-20240620-v1:0

Switch between models seamlessly

🔌 Integrations

Specif AI seamlessly integrates with popular tools to enhance your workflow:

Jira Integration

The stories and tasks generated as part of the solutions can be used to create actual stories and tasks in your Jira instance using the Jira integration provided by the application. Features include:

• Automatic story and task creation in Jira.
• Bulk export capabilities.

For Jira setup instructions, please refer to our Jira Setup Guide.

AWS Bedrock Knowledge Base

Note: The AWS Bedrock Knowledge Base features are configurable when the backend server is deployed in AWS. Local deployments will not have access to these enhanced capabilities.

The enterprise knowledge base is integrated with AI-powered chat to enhance suggestions and enable iterative conversations for Business Requirement Documents (BRDs), Product Requirement Documents (PRDs), Non-functional Requirements, User Stories, and Tasks. Features include:

• Enhanced chat suggestions through enterprise knowledge.
• Context-aware requirement generation.
• Historical data integration.

🏗 Architecture

Specif AI follows a modern, scalable architecture designed for optimal performance and maintainability.

📝 Version Controlled Requirements Management Made Easy

Specif AI is a powerful desktop application built to streamline and organize your project requirements. With Specif AI, users can create a unified directory where all essential files are not only accessible and editable but also seamlessly synced with platforms like OneDrive, Dropbox, or any git-enabled local folder. This setup allows users to point to specific artifacts and data sources in a version-controlled environment, making collaboration and tracking effortless. Our goal is to enhance your development workflow by integrating seamlessly with the tools you already use, without adding complexity or obstacles.

🗺 Roadmap

• Advanced BRD-PRD linking capabilities.
• Enhanced collaboration features.
• Custom template support.
• v2.0 - Web version with enhanced collaboration capabilities.

🤝 Contributing

To contribute to the project, start by exploring open issues or checking our feature request board.

Please read our Contributing Guidelines for more details.

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Thanks to all contributors and users for their support and feedback.

📧 Contact

For any questions or feedback, please contact us at [email protected].