Autonomous Test Strategy (ATS) Generator

🤖 Cognitive Process Automation (CPA) tool that automates Test Strategy creation using AI agents powered by Large Language Models (LLMs).

📋 Table of Contents

What is ATS Generator?
Functional Requirements
Key Features
How It Works
Quick Start
Run Locally with Free Resources
LLM Provider Setup
Usage Guide
Architecture Deep Dive
API Reference
Project Structure
Customization
Troubleshooting
Contributing

🎯 What is ATS Generator?

The Autonomous Test Strategy Generator is a tool that transforms raw software requirements (user stories, epics, tickets) into comprehensive Test Strategy documents using AI.

The Problem It Solves

Creating a Test Strategy document manually requires:

Hours of analysis to identify risks
Deep expertise in testing methodologies
Knowledge of BDD/Gherkin syntax for test scenarios
Experience in resource estimation

ATS Generator automates all of this in seconds.

Who Is This For?

QA Engineers - Generate test strategies quickly
Test Leads - Get a starting point for test planning
Developers - Understand testing requirements for features
Product Managers - Review testing scope and coverage
Students - Learn about test strategy components

📜 Functional Requirements

This section describes what the system does from a user's perspective.

FR01: Requirements Ingestion

Aspect	Description
What	Accept raw, unstructured requirements as input
Input	User stories, epics, feature descriptions, tickets - any text format
How	Single text area where users paste their requirements
Example Input	`"As a user, I want to login with email so I can access my account"`

FR02: Risk Analysis (Agent 1 - Risk Analyst)

Aspect	Description
What	Analyze requirements to identify testing risks
Output	Risk assessment report
Includes	• High-risk features that need extensive testing
	• Complexity assessment (Low/Medium/High)
	• Potential failure modes and their impact
	• Dependencies and integration points
	• Risk mitigation recommendations

FR03: Test Design (Agent 2 - Test Architect)

Aspect	Description
What	Generate comprehensive test scenarios and recommendations
Output	Test design document with BDD scenarios
Includes	• BDD/Gherkin scenarios (Given/When/Then format)
	• Test type recommendations (UI, API, Performance, Security, etc.)
	• Test coverage matrix
	• Edge cases and boundary conditions
	• Positive and negative test scenarios

FR04: Strategy Synthesis (Agent 3 - QA Manager)

Aspect	Description
What	Compile all analyses into a formal Test Strategy document
Output	Executive-ready Test Strategy
Includes	• Executive Summary
	• Scope and Objectives
	• Testing Approach and Methodology
	• Test Types and Levels
	• Entry and Exit Criteria
	• Resource Requirements
	• Timeline and Milestones
	• Risk Management Plan
	• Deliverables

FR05: Output Display

Aspect	Description
What	Present generated strategy in a readable format
Features	• Tabbed interface (Strategy / Risk Analysis / Test Design)
	• Scrollable content areas
	• Copy to clipboard functionality
	• Download as Markdown file
	• Duration metrics for each agent

FR06: Progress Indication

Aspect	Description
What	Show real-time progress during generation
Features	• Visual agent pipeline showing current stage
	• Progress percentage
	• Status messages for each agent
	• Non-blocking UI during processing

Sample Input → Output

Input (Raw Requirements):

User Story 1: As a user, I want to register with my email address 
so that I can create an account.

User Story 2: As a user, I want to login with my credentials 
so that I can access my dashboard.

User Story 3: As a user, I want to reset my password via email 
so that I can regain access if I forget it.

Output (Generated by System):

Agent	Output
Risk Analyst	Identifies authentication as high-risk, flags security concerns (brute force, session hijacking), assesses complexity as Medium-High
Test Architect	Generates 15+ BDD scenarios covering login success, login failure, password reset flow, edge cases; Recommends UI, API, Security, and Performance testing
QA Manager	Produces formal Test Strategy document with executive summary, scope, approach, resources, timeline, and deliverables

✨ Key Features

Feature	Description
🔍 Risk Analysis	Automatically identifies high-risk features, complexity, and failure modes
📝 BDD Scenarios	Generates Gherkin-style test scenarios (Given/When/Then)
🎯 Test Type Recommendations	Suggests UI, API, Performance, Security testing needs
📄 Strategy Document	Creates formal, executive-ready Test Strategy
🔄 Multiple LLM Support	Works with Ollama (free/local), LM Studio, or Gemini
⚡ Real-time Progress	Shows agent progress during generation
📥 Export Options	Download as Markdown document

🧠 How It Works

The system uses a Three-Agent Pipeline where each agent is a specialized AI persona:

┌─────────────────────────────────────────────────────────────────────────┐
│                         YOUR REQUIREMENTS                                │
│   "As a user, I want to login with email so I can access my account"    │
└─────────────────────────────────────────────────────────────────────────┘
                                    │
                                    ▼
┌─────────────────────────────────────────────────────────────────────────┐
│                        AGENT 1: RISK ANALYST                             │
│  • Identifies authentication as high-risk                                │
│  • Flags security concerns (brute force, session hijacking)             │
│  • Assesses complexity: Medium-High                                      │
└─────────────────────────────────────────────────────────────────────────┘
                                    │
                                    ▼
┌─────────────────────────────────────────────────────────────────────────┐
│                       AGENT 2: TEST ARCHITECT                            │
│  • Creates BDD scenarios:                                                │
│    Given a registered user                                               │
│    When they enter valid credentials                                     │
│    Then they should be logged in                                         │
│  • Recommends: UI Testing, API Testing, Security Testing                │
└─────────────────────────────────────────────────────────────────────────┘
                                    │
                                    ▼
┌─────────────────────────────────────────────────────────────────────────┐
│                        AGENT 3: QA MANAGER                               │
│  • Compiles formal Test Strategy document                                │
│  • Includes: Scope, Approach, Resources, Timeline, Metrics              │
│  • Executive-ready format                                                │
└─────────────────────────────────────────────────────────────────────────┘
                                    │
                                    ▼
┌─────────────────────────────────────────────────────────────────────────┐
│                      COMPLETE TEST STRATEGY                              │
│   Ready for review, export, and implementation                          │
└─────────────────────────────────────────────────────────────────────────┘

🚀 Quick Start

Prerequisites

Node.js 18+ - Download
npm or yarn
One of these LLM options:
- 🆓 Ollama (Recommended - Free, runs locally)
- 🆓 LM Studio (Free, runs locally with GUI)
- 💰 Google Gemini (Requires API key)

Installation

# 1. Clone the repository
git clone <repository-url>
cd "Autonomous Test Strategy (ATS) Generator"

# 2. Install dependencies
npm install

# 3. Set up environment
cp .env.example .env
# Edit .env with your LLM configuration (see next section)

# 4. Start the backend server
npm run server

# 5. In a new terminal, start the frontend
npm run dev

# 6. Open http://localhost:5173 in your browser

🆓 Run Locally with Free Resources (No API Key Required)

You can run this entire system 100% free on your local machine using Ollama. No cloud services, no API keys, no costs.

What You Need

Requirement	Cost	Notes
Node.js 18+	Free	Download here
Ollama	Free	Local LLM runtime
~4GB disk space	-	For model download
8GB+ RAM	-	16GB recommended for better performance

Step-by-Step Setup

1. Install Ollama

macOS:

brew install ollama

Linux:

curl -fsSL https://ollama.com/install.sh | sh

Windows: Download installer from ollama.com/download

2. Start Ollama & Download a Model

# Terminal 1: Start Ollama service (keep this running)
ollama serve

# Terminal 2: Download a model based on your RAM
# For 8GB RAM:
ollama pull llama3.2:3b

# For 16GB RAM (recommended):
ollama pull llama3.2

# For 32GB+ RAM (best quality):
ollama pull mistral

3. Verify Ollama is Working

# Should return a list of installed models
curl http://localhost:11434/api/tags

# Or test with a simple prompt
ollama run llama3.2 "Say hello"

4. Set Up ATS Generator

# Navigate to project
cd "Autonomous Test Strategy (ATS) Generator"

# Install dependencies
npm install

# Create environment file (already configured for Ollama!)
cp .env.example .env

The default .env is pre-configured for Ollama:

LLM_PROVIDER=ollama
OLLAMA_MODEL=llama3.2
OLLAMA_BASE_URL=http://localhost:11434

5. Start the Application

# Terminal 1: Start backend
npm run server
# ✓ Should show: "Server running on port 3001"

# Terminal 2: Start frontend
npm run dev
# ✓ Should show: "Local: http://localhost:5173/"

6. Test It!

Open http://localhost:5173 in your browser
Click "Generator" in the navigation
Paste these sample requirements:

User Story 1: As a user, I want to register with my email address 
so that I can create an account.

User Story 2: As a user, I want to login with my credentials 
so that I can access my dashboard.

User Story 3: As a user, I want to reset my password via email 
so that I can regain access if I forget it.

User Story 4: As an admin, I want to view all users 
so that I can manage the user base.

Click "Generate Test Strategy"
Wait 30-90 seconds (local models are slower than cloud)
View your generated Test Strategy! 🎉

Model Recommendations by Hardware

Your RAM	Model	Command	Speed	Quality
8GB	Llama 3.2 3B	`ollama pull llama3.2:3b`	Fast	Good
8GB	Phi-3 Mini	`ollama pull phi3`	Fast	Good
16GB	Llama 3.2	`ollama pull llama3.2`	Medium	Better
16GB	Mistral 7B	`ollama pull mistral`	Medium	Better
32GB+	Llama 3.2 70B	`ollama pull llama3.2:70b`	Slow	Best
32GB+	Mixtral 8x7B	`ollama pull mixtral`	Slow	Best

Alternative: LM Studio (GUI-based)

If you prefer a graphical interface:

Download LM Studio from lmstudio.ai
Open LM Studio → Search tab → Search "llama" or "mistral"
Download a model (GGUF format)
Go to Local Server tab → Click Start Server
Update your .env:

LLM_PROVIDER=lmstudio
LMSTUDIO_MODEL=local-model
LMSTUDIO_BASE_URL=http://localhost:1234/v1

Common Issues & Solutions

Issue	Solution
"Ollama not running"	Run `ollama serve` in a terminal
"Model not found"	Run `ollama pull llama3.2`
Very slow generation	Use smaller model: `ollama pull llama3.2:3b`
Out of memory errors	Close other apps, use smaller model
"Connection refused"	Check Ollama is running on port 11434
Port 3001 already in use	Change `PORT=3002` in `.env`

Performance Tips

Close unnecessary applications - LLMs need RAM
Use SSD storage - Faster model loading
Start with smaller models - Test setup before downloading large models
Keep Ollama running - First request loads model into memory (slow), subsequent requests are faster

🤖 LLM Provider Setup

Choose ONE of these options:

Option 1: Ollama (Recommended - FREE & Local)

Ollama lets you run open-source LLMs locally on your machine.

# 1. Install Ollama
# macOS
brew install ollama

# Linux
curl -fsSL https://ollama.com/install.sh | sh

# Windows - Download from https://ollama.com/download

# 2. Start Ollama service
ollama serve

# 3. Pull a model (choose one)
ollama pull llama3.2        # Recommended - Good balance
ollama pull mistral         # Fast and capable
ollama pull codellama       # Better for code-related tasks
ollama pull llama3.2:70b    # Best quality (needs 48GB+ RAM)

# 4. Configure .env
LLM_PROVIDER=ollama
OLLAMA_MODEL=llama3.2
OLLAMA_BASE_URL=http://localhost:11434

Recommended Models by Hardware:

RAM	Recommended Model
8GB	`llama3.2:3b`, `phi3`
16GB	`llama3.2`, `mistral`
32GB+	`llama3.2:70b`, `mixtral`

Option 2: LM Studio (FREE & Local with GUI)

LM Studio provides a user-friendly interface for running local LLMs.

# 1. Download LM Studio from https://lmstudio.ai/

# 2. Open LM Studio and download a model:
#    - Click "Search" tab
#    - Search for "llama" or "mistral"
#    - Download a model (GGUF format)

# 3. Start the local server:
#    - Go to "Local Server" tab
#    - Click "Start Server"
#    - Note the port (usually 1234)

# 4. Configure .env
LLM_PROVIDER=lmstudio
LMSTUDIO_MODEL=local-model
LMSTUDIO_BASE_URL=http://localhost:1234/v1

Option 3: Google Gemini (Cloud - Requires API Key)

# 1. Get API key from https://makersuite.google.com/app/apikey

# 2. Configure .env
LLM_PROVIDER=gemini
GEMINI_API_KEY=your-api-key-here
GEMINI_MODEL=gemini-1.5-flash

Option 4: OpenAI-Compatible APIs

Works with LocalAI, vLLM, text-generation-webui, etc.

LLM_PROVIDER=openai-compatible
OPENAI_BASE_URL=http://localhost:8080/v1
OPENAI_MODEL=your-model-name
OPENAI_API_KEY=optional-api-key

Complete .env Example

# ===========================================
# LLM CONFIGURATION (Choose ONE provider)
# ===========================================

# Provider: ollama | lmstudio | gemini | openai-compatible
LLM_PROVIDER=ollama

# --- Ollama Settings ---
OLLAMA_MODEL=llama3.2
OLLAMA_BASE_URL=http://localhost:11434

# --- LM Studio Settings ---
# LMSTUDIO_MODEL=local-model
# LMSTUDIO_BASE_URL=http://localhost:1234/v1

# --- Gemini Settings ---
# GEMINI_API_KEY=your-api-key
# GEMINI_MODEL=gemini-1.5-flash

# --- OpenAI-Compatible Settings ---
# OPENAI_BASE_URL=http://localhost:8080/v1
# OPENAI_MODEL=gpt-3.5-turbo
# OPENAI_API_KEY=optional

# ===========================================
# LLM PARAMETERS (Optional)
# ===========================================
LLM_TEMPERATURE=0.7
LLM_MAX_TOKENS=8192

# ===========================================
# SERVER CONFIGURATION
# ===========================================
PORT=3001
NODE_ENV=development

📖 Usage Guide

Step 1: Enter Requirements

Navigate to the Generator page and paste your requirements:

User Story 1: As a user, I want to register with my email address 
so that I can create an account.

User Story 2: As a user, I want to login with my credentials 
so that I can access my dashboard.

User Story 3: As a user, I want to reset my password via email 
so that I can regain access if I forget it.

User Story 4: As an admin, I want to view all users 
so that I can manage the user base.

User Story 5: As a user, I want to update my profile 
so that my information stays current.

Step 2: Generate Strategy

Click "Generate Test Strategy" and watch the three agents work:

Risk Analyst (10-15 seconds) - Analyzes risks
Test Architect (10-15 seconds) - Creates test scenarios
QA Manager (10-15 seconds) - Synthesizes strategy

Step 3: Review Output

The generated strategy includes:

Risk Analysis Tab

High-risk features identified
Complexity assessment
Potential failure modes
Risk mitigation recommendations

Test Design Tab

BDD/Gherkin scenarios for each feature
Recommended test types (UI, API, Performance, Security)
Test coverage matrix

Test Strategy Tab (Main Output)

Executive Summary
Scope and Objectives
Testing Approach
Test Types and Levels
Entry/Exit Criteria
Resource Requirements
Timeline Estimates
Risk Management
Deliverables

Step 4: Export

Click Download to save as Markdown, or Copy to clipboard.

🏗️ Architecture Deep Dive

System Overview

┌──────────────────────────────────────────────────────────────────┐
│                         FRONTEND                                  │
│                    (React + TypeScript)                          │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────────────────┐  │
│  │  HomePage   │  │ Generator   │  │   StrategyViewPage      │  │
│  │             │  │    Page     │  │   (Output Display)      │  │
│  └─────────────┘  └──────┬──────┘  └─────────────────────────┘  │
│                          │                                        │
└──────────────────────────┼────────────────────────────────────────┘
                           │ REST API
                           ▼
┌──────────────────────────────────────────────────────────────────┐
│                         BACKEND                                   │
│                   (Express + TypeScript)                         │
│  ┌─────────────────────────────────────────────────────────────┐ │
│  │                    API Routes                                │ │
│  │  POST /api/strategy/generate                                 │ │
│  │  GET  /api/strategy/llm/status                              │ │
│  │  GET  /api/strategy/agents                                  │ │
│  └─────────────────────────┬───────────────────────────────────┘ │
│                            │                                      │
│  ┌─────────────────────────▼───────────────────────────────────┐ │
│  │              StrategyGeneratorService                        │ │
│  │  • Orchestrates three-agent pipeline                        │ │
│  │  • Manages progress callbacks                               │ │
│  │  • Handles errors and retries                               │ │
│  └─────────────────────────┬───────────────────────────────────┘ │
│                            │                                      │
│  ┌─────────────────────────▼───────────────────────────────────┐ │
│  │                  LLM Provider                                │ │
│  │  • Abstracts different LLM backends                         │ │
│  │  • Supports: Ollama, LM Studio, Gemini, OpenAI-compatible   │ │
│  └─────────────────────────┬───────────────────────────────────┘ │
│                            │                                      │
└────────────────────────────┼──────────────────────────────────────┘
                             │
                             ▼
┌──────────────────────────────────────────────────────────────────┐
│                      LLM ENGINE                                   │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────────────┐ │
│  │  Ollama  │  │LM Studio │  │  Gemini  │  │ OpenAI-Compatible│ │
│  │ (Local)  │  │ (Local)  │  │ (Cloud)  │  │    (Any)         │ │
│  └──────────┘  └──────────┘  └──────────┘  └──────────────────┘ │
└──────────────────────────────────────────────────────────────────┘

Agent Prompts (The Secret Sauce)

Each agent has a carefully crafted system prompt that defines its persona and output format:

Risk Analyst Agent

You are a Senior Risk Analyst specializing in software testing.
Your role is to analyze requirements and identify:
- High-risk features that need extensive testing
- Complexity factors that increase testing effort
- Potential failure modes and their impact
- Dependencies and integration points
...

Test Architect Agent

You are a Senior Test Architect specializing in test design.
Your role is to create comprehensive test scenarios including:
- BDD/Gherkin scenarios (Given/When/Then)
- Test type recommendations (UI, API, Performance, Security)
- Test coverage matrix
- Edge cases and boundary conditions
...

QA Manager Agent

You are a QA Manager responsible for test strategy.
Synthesize the analyses into a formal Test Strategy document:
- Executive Summary
- Scope and Objectives
- Testing Approach
- Resource Requirements
...

Data Flow

1. User enters requirements in textarea
                    │
                    ▼
2. Frontend sends POST /api/strategy/generate
   Body: { rawRequirements: "...", sessionId: "..." }
                    │
                    ▼
3. StrategyGeneratorService.generateStrategy()
   │
   ├─► runRiskAnalysis(requirements)
   │   └─► callLLM(prompt, RISK_ANALYST_PROMPT)
   │       └─► Returns: Risk Analysis text
   │
   ├─► runTestDesign(requirements, riskAnalysis)
   │   └─► callLLM(prompt, TEST_ARCHITECT_PROMPT)
   │       └─► Returns: Test Design text
   │
   └─► runStrategySynthesis(riskAnalysis, testDesign)
       └─► callLLM(prompt, QA_MANAGER_PROMPT)
           └─► Returns: Test Strategy text
                    │
                    ▼
4. API returns combined results
   {
     success: true,
     riskAnalysis: "...",
     testDesign: "...",
     testStrategy: "...",
     totalDuration: 45000
   }
                    │
                    ▼
5. Frontend stores in sessionStorage, navigates to /strategy
                    │
                    ▼
6. StrategyViewPage displays results in tabbed interface

📡 API Reference

POST /api/strategy/generate

Generate a test strategy from raw requirements.

Request:

{
  "rawRequirements": "User Story 1: As a user...",
  "sessionId": "optional-session-id"
}

Response:

{
  "success": true,
  "riskAnalysis": "## Risk Analysis\n...",
  "testDesign": "## Test Scenarios\n...",
  "testStrategy": "# Test Strategy Document\n...",
  "agentOutputs": [
    {
      "agent": "Risk Analyst Agent",
      "output": "...",
      "timestamp": "2024-01-15T10:30:00Z",
      "duration": 12500
    }
  ],
  "totalDuration": 45000
}

GET /api/strategy/llm/status

Check LLM provider status and configuration.

Response:

{
  "provider": "ollama",
  "model": "llama3.2",
  "baseUrl": "http://localhost:11434",
  "available": true,
  "error": null,
  "supportedProviders": [...]
}

GET /api/strategy/agents

Get descriptions of the three agents.

Response:

{
  "agents": [
    {
      "id": "risk_analyst",
      "name": "Risk Analyst Agent",
      "description": "Analyzes requirements to identify high-risk features...",
      "icon": "shield"
    }
  ]
}

📁 Project Structure

Autonomous Test Strategy (ATS) Generator/
│
├── 📁 src/                           # Frontend Source Code
│   ├── 📁 components/
│   │   ├── Layout.tsx               # Main layout with navigation
│   │   └── 📁 ui/                   # shadcn/ui components
│   │       ├── button.tsx
│   │       ├── card.tsx
│   │       ├── textarea.tsx
│   │       └── ...
│   │
│   ├── 📁 pages/
│   │   ├── HomePage.tsx             # Landing page with features
│   │   ├── GeneratorPage.tsx        # Requirements input + generation
│   │   └── StrategyViewPage.tsx     # Strategy output display
│   │
│   ├── 📁 lib/
│   │   └── api.ts                   # Axios API utilities
│   │
│   ├── 📁 types/
│   │   └── index.ts                 # TypeScript type definitions
│   │
│   ├── App.tsx                      # Main React app with routing
│   ├── main.tsx                     # React entry point
│   └── index.css                    # Global styles + Tailwind
│
├── 📁 server/                        # Backend Source Code
│   ├── 📁 lib/
│   │   ├── llm-provider.ts          # Multi-LLM abstraction layer
│   │   └── gemini.ts                # Agent prompts + Gemini client
│   │
│   ├── 📁 services/
│   │   └── StrategyGeneratorService.ts  # Three-agent orchestration
│   │
│   ├── 📁 routes/
│   │   ├── strategy.ts              # Strategy generation endpoints
│   │   └── requirements.ts          # Requirements parsing endpoints
│   │
│   ├── 📁 agents/                   # Legacy agent implementations
│   │   ├── BaseAgent.ts
│   │   ├── RiskAssessorAgent.ts
│   │   └── ...
│   │
│   └── index.ts                     # Express server entry point
│
├── 📁 public/                        # Static assets
│
├── .env.example                     # Environment template
├── package.json                     # Dependencies
├── tsconfig.json                    # TypeScript config
├── vite.config.ts                   # Vite bundler config
├── tailwind.config.js               # Tailwind CSS config
└── README.md                        # This file

🔧 Customization

Modifying Agent Prompts

Edit server/lib/gemini.ts to customize agent behavior:

export const AGENT_PROMPTS = {
  RISK_ANALYST: `
    You are a Senior Risk Analyst...
    // Customize the persona and output format
  `,
  TEST_ARCHITECT: `...`,
  QA_MANAGER: `...`
}

Adding New LLM Providers

Edit server/lib/llm-provider.ts:

// Add new provider type
export type LLMProvider = 'gemini' | 'ollama' | 'lmstudio' | 'your-provider'

// Add configuration
case 'your-provider':
  return {
    provider: 'your-provider',
    model: process.env.YOUR_MODEL,
    baseUrl: process.env.YOUR_BASE_URL
  }

// Add API call function
async function callYourProvider(prompt, systemPrompt, config) {
  // Implementation
}

Changing UI Theme

Edit tailwind.config.js and src/index.css for theming.

🔍 Troubleshooting

"Ollama not running" Error

# Start Ollama service
ollama serve

# Check if running
curl http://localhost:11434/api/tags

"No models installed" Error

# Pull a model
ollama pull llama3.2

# List installed models
ollama list

LM Studio Connection Failed

Open LM Studio
Go to "Local Server" tab
Click "Start Server"
Verify port matches LMSTUDIO_BASE_URL in .env

Gemini API Error

Verify API key is correct
Check quota at https://console.cloud.google.com/
Ensure billing is enabled (free tier available)

Generation Taking Too Long

Local LLMs are slower than cloud APIs
Try a smaller model: ollama pull llama3.2:3b
Reduce LLM_MAX_TOKENS in .env

Out of Memory (Local LLMs)

Use a smaller model
Close other applications
Consider cloud provider (Gemini)

🤝 Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Make your changes
Submit a pull request

📄 License

MIT License - feel free to use in personal and commercial projects.

🙏 Acknowledgments

Ollama - Local LLM runtime
LM Studio - Local LLM GUI
Google Gemini - Cloud LLM API
shadcn/ui - UI components
Tailwind CSS - Styling

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
docs		docs
prisma		prisma
server		server
src		src
.env.example		.env.example
.gitignore		.gitignore
README.md		README.md
index.html		index.html
package-lock.json		package-lock.json
package.json		package.json
postcss.config.js		postcss.config.js
tailwind.config.js		tailwind.config.js
tsconfig.json		tsconfig.json
tsconfig.node.json		tsconfig.node.json
vite.config.ts		vite.config.ts

Folders and files

Latest commit

History

Repository files navigation

Autonomous Test Strategy (ATS) Generator

📋 Table of Contents

🎯 What is ATS Generator?

The Problem It Solves

Who Is This For?

📜 Functional Requirements

FR01: Requirements Ingestion

FR02: Risk Analysis (Agent 1 - Risk Analyst)

FR03: Test Design (Agent 2 - Test Architect)

FR04: Strategy Synthesis (Agent 3 - QA Manager)

FR05: Output Display

FR06: Progress Indication

Sample Input → Output

✨ Key Features

🧠 How It Works

🚀 Quick Start

Prerequisites

Installation

🆓 Run Locally with Free Resources (No API Key Required)

What You Need

Step-by-Step Setup

1. Install Ollama

2. Start Ollama & Download a Model

3. Verify Ollama is Working

4. Set Up ATS Generator

5. Start the Application

6. Test It!

Model Recommendations by Hardware

Alternative: LM Studio (GUI-based)

Common Issues & Solutions

Performance Tips

🤖 LLM Provider Setup

Option 1: Ollama (Recommended - FREE & Local)

Option 2: LM Studio (FREE & Local with GUI)

Option 3: Google Gemini (Cloud - Requires API Key)

Option 4: OpenAI-Compatible APIs

Complete .env Example

📖 Usage Guide

Step 1: Enter Requirements

Step 2: Generate Strategy

Step 3: Review Output

Risk Analysis Tab

Test Design Tab

Test Strategy Tab (Main Output)

Step 4: Export

🏗️ Architecture Deep Dive

System Overview

Agent Prompts (The Secret Sauce)

Risk Analyst Agent

Test Architect Agent

QA Manager Agent

Data Flow

📡 API Reference

POST /api/strategy/generate

GET /api/strategy/llm/status

GET /api/strategy/agents

📁 Project Structure

🔧 Customization

Modifying Agent Prompts

Adding New LLM Providers

Changing UI Theme

🔍 Troubleshooting

"Ollama not running" Error

"No models installed" Error

LM Studio Connection Failed

Gemini API Error

Generation Taking Too Long

Out of Memory (Local LLMs)

🤝 Contributing

📄 License

🙏 Acknowledgments

About

Resources

Uh oh!

Stars

Watchers

Packages