AI-Powered E-Discovery Email Dataset Generator
A free tool from QuikData — Scalable On-Prem, SaaS, and Hybrid E-Discovery solutions for law firms, service providers, and corporate/government. AI Powered.
ReelDiscovery generates realistic corporate email datasets for e-discovery training, testing, and demonstration purposes. Using OpenAI's GPT models, it creates authentic-feeling email threads based on movies, TV shows, books, or custom business scenarios.
- Storyline-driven content - Emails follow coherent narratives with beginnings, middles, and conclusions
- Character personalities - Each character has a unique voice, writing style, and email signature
- Realistic threading - Proper email threading with Message-ID, In-Reply-To, and References headers
- Variable email lengths - From quick one-line replies to detailed multi-paragraph messages
- Branching conversations - Side threads, forwards, and CC'd participants
- Word Documents (.docx) - Reports, memos, proposals with organization branding
- Excel Spreadsheets (.xlsx) - Data tables, budgets, tracking sheets
- PowerPoint Presentations (.pptx) - Slide decks with themed colors and fonts
- Document versioning - Realistic version chains (v1, v2_revised, v3_FINAL, etc.)
- Inline images - Photos embedded directly in email body
- Image attachments - Photos, screenshots, visual evidence
- Context-aware - Images match the storyline and universe
- MP3 audio files - Realistic voicemail recordings
- Character voices - Different TTS voices for each character
- Natural speech - Includes conversational elements like "um", pauses
- Auto-detection - Finds meeting references in email content
- .ics files - Standard calendar format compatible with Outlook, Gmail, etc.
- Attendee lists - Pulls participants from email recipients
- Per-domain branding - Each organization gets unique colors and fonts
- AI-selected themes - Colors match the organization's character (law firms get formal navy, tech startups get vibrant colors)
- Consistent styling - Documents from the same organization share branding
- Windows 10/11 (64-bit)
- OpenAI API key with access to:
- GPT-4o or GPT-4o-mini (for text generation)
- DALL-E 3 (optional, for image generation)
- TTS (optional, for voicemails)
Download the latest ReelDiscovery.exe from the Releases page. No installation required - just run the executable.
git clone https://github.com/yourusername/ReelDiscovery.git
cd ReelDiscovery
dotnet build
dotnet run- Launch ReelDiscovery
- Enter your OpenAI API key and test the connection
- Enter a topic (e.g., "The Office", "Game of Thrones", "Healthcare Startup")
- Review generated storylines - Edit or regenerate as needed
- Review characters - Modify names, roles, organizations
- Configure generation settings:
- Number of emails
- Attachment percentages
- Date range
- Generate - Watch as emails are created
- Open output folder - Import .eml files into your e-discovery tool
| Setting | Default | Description |
|---|---|---|
| Email Count | 50 | Total emails to generate |
| Parallel API Calls | 3 | Concurrent requests (higher = faster but more quota) |
| Attachment % | 20% | Percentage of emails with document attachments |
- Word Documents (.docx)
- Excel Spreadsheets (.xlsx)
- PowerPoint Presentations (.pptx)
| Feature | Default | API Cost |
|---|---|---|
| AI Images | Off | ~$0.04/image |
| Voicemails | Off | ~$0.015/voicemail |
| Calendar Invites | On | No extra cost |
Generated emails are saved as standard .eml files that can be imported into:
- Microsoft Outlook
- Relativity
- Nuix
- Concordance
- Most e-discovery platforms
output_folder/
├── john.smith@company.com/
│ ├── 20240115_093042_RE_Budget_Meeting.eml
│ └── 20240116_141523_FW_Q4_Report.eml
├── jane.doe@company.com/
│ └── 20240115_102315_Project_Update.eml
└── ...
ReelDiscovery works great with:
TV Shows & Movies
- "The Office" - Dunder Mifflin corporate drama
- "Game of Thrones" - Medieval politics and intrigue
- "Succession" - Family business conflicts
- "Silicon Valley" - Tech startup chaos
Business Scenarios
- "Healthcare Company Merger"
- "Tech Startup Funding Round"
- "Law Firm Partnership Dispute"
- "Manufacturing Quality Issues"
All generated content is fictional and created by AI for demonstration purposes only. Generated emails include a disclaimer banner. This tool is intended for:
- E-discovery software training
- Legal technology demonstrations
- Educational purposes
- Testing and development
Do not use generated content to mislead or deceive.
ReelDiscovery includes optional, opt-in anonymous usage telemetry to help us improve the product.
On first run, you'll be asked if you want to participate. You can change this anytime in the Generation Settings.
What we collect (if you opt in):
- Topic entered (first 50 characters only)
- Number of emails/threads generated
- AI model used
- App version
What we DON'T collect:
- Your name, email, or any personal information
- Your OpenAI API key
- Generated email content
- IP address or device identifiers
- .NET 8.0 / Windows Forms
- OpenAI API (GPT-4, DALL-E, TTS)
- MimeKit (email generation)
- DocumentFormat.OpenXml (Office documents)
ReelDiscovery is brought to you by QuikData — a leading provider of AI-powered e-discovery solutions.
QuikData offers:
- On-Premises - Full control with deployment in your own data center
- SaaS - Cloud-hosted solution with no infrastructure to manage
- Hybrid - Flexible deployment combining on-prem processing with cloud review
Built for:
- Law Firms
- Legal Service Providers
- Corporate Legal Departments
- Government Agencies
MIT License - See LICENSE for details.
Contributions welcome! Please open an issue to discuss proposed changes before submitting a PR.
- Built with OpenAI APIs
- Email handling by MimeKit
- Office documents by Open XML SDK
- Created by QuikData