AI-Driven Autogen_demo: Simplify Requirement Analysis & Test Case Creation

Introduction Autogen_demo is an AI‑powered automated testing tool developed with Streamlit that streamlines requirement analysis and test case generation.

Core Features

Requirement Parsing

Supports uploading PDF/Word documents or direct text input

Automatically extracts key requirement information into structured data

Requirement Management

Built‑in database for storing and version‑controlling requirement documents

Keyword search for quick retrieval of historical requirements

Test Case Generation

Functional verification flow

Boundary condition testing

Exception scenario coverage

Automatically generates test plans covering multiple dimensions

Exports to Excel, Markdown, or JSON formats

Value Proposition

Reduces manual effort in writing test cases

Standardized templates prevent test omissions

Facilitates team collaboration and requirement version tracing

The system is suitable for software development and testing, especially agile teams requiring rapid iteration.

System Architecture

The tool adopts a modular architecture with the following components:

Functional Module Division

Data model layer defining structured standards for requirements and test cases

Database module for persistent storage and version management

Document parser handling semantic analysis of PDF/Word files

Test generation engine that uses AI models to automatically build test plans

Asynchronous processing framework to improve responsiveness and concurrency

Interaction Design

Web UI built with Streamlit

Three‑step standardized workflow with visual progress indicators and error validation

Requirement upload/input

Database retrieval and management

Test case configuration and export

Technical Highlights

Standardized interfaces allow independent module upgrades

Layered architecture separates business logic from data storage

Configuration‑driven parameterization supports various testing standards

Built‑in guides and documentation lower learning curve

The architecture ensures flexibility while providing template‑driven, guided interactions suitable for testers of diverse technical backgrounds.

Applicable Scenarios

The tool serves the entire software R&D lifecycle, offering specific benefits for:

Developers

Automates creation of basic test frameworks, reducing repetitive work

Ensures test completeness with standardized templates

Enables rapid validation of core functionality, allowing focus on business logic

Test Engineers

Systematically builds multi‑dimensional test suites (functional, boundary, exception)

Provides traceable test baselines for regression testing

Exports standardized test documents to improve team collaboration

Requirement Analysts

Stores historical requirement documents in a searchable knowledge base

Supports version comparison and change tracking

Uses semantic linking to quickly locate related requirement items

Cross‑Team Collaboration Value

Unified, standardized representation of requirements and tests

Bidirectional traceability between requirements and tests

Reduces communication overhead across roles

The tool fits agile development and continuous integration environments, significantly improving efficiency from requirement analysis to test acceptance.

autogen_demo/
├── app.py          # Refactored main application entry
├── main.py         # Compatibility entry (imports app.py)
├── database.py     # Database operations module
├── core/           # Core service layer
│   ├── pdf_service.py          # PDF processing service
│   ├── testcase_service.py     # Test case service
│   ├── requirement_service.py   # Requirement service
│   └── ui_service.py           # UI component service
├── modules/        # Functional modules
│   ├── export_utils.py         # Export utilities
│   ├── pdf_processor.py        # PDF processing
│   └── ui_components.py        # UI components
├── agents/         # AI agent modules
│   ├── test_case_generator.py          # Test case generation
│   └── requirement_analysis_generator.py  # Requirement analysis generation
├── models/         # Data models
│   └── data_models.py          # Data model definitions
├── config/         # Configuration
│   └── llm_config.py          # LLM configuration
└── data/           # Data storage directory

Technical Selection Considerations

Automation Process Optimization

Integrates NLP for intelligent parsing of requirement documents

Algorithmic models automatically generate compliant test plans

Empirically improves efficiency 5‑8× over manual processing

Quality Assurance Mechanism

Positive functional paths

Boundary value extremes

Exception handling flows

Built‑in ISTQB‑compliant test templates

Triple‑validation logic ensures coverage

System Compatibility Design

Excel output for non‑technical stakeholders

Markdown for easy integration into technical documentation

JSON for automated testing pipelines