Introduction: Transform Your Email Investigations
This isn’t just an incremental improvement; it’s a fundamental change that can dramatically cut review times, uncover hidden insights, and reduce costs. Our solution is also one of the few on-premises eDiscovery tools offering this advanced capability.
Aid4Mail’s approach fundamentally differs from traditional Technology-Assisted Review (TAR) systems. While TAR platforms require extensive training phases—manually reviewing hundreds or thousands of documents to “teach” the system what’s relevant—Aid4Mail leverages Large Language Models (LLMs) for structured analysis and classification. You start analyzing emails immediately with natural language prompts, without any training data, seed sets, or iterative feedback loops.
Imagine the Possibilities
Important Note Regarding AI Providers
Aid4Mail doesn’t provide direct access to online AI services. You must obtain API keys directly from providers (Anthropic, Google, Meta AI, Mistral AI, OpenAI, or xAI) and manage associated costs independently.
AI tools can make mistakes and have limitations. However, concerns about AI hallucination are largely irrelevant to Aid4Mail’s structured classification approach, as explained in Section 4.
How Aid4Mail’s AI Differs from Traditional TAR
If you’re familiar with Technology-Assisted Review (TAR) platforms used in eDiscovery, the difference is fundamental, not incremental.
Traditional TAR Workflow
- 1. Training Phase: Experts manually review 200–2,000+ documents as a “seed set”
- 2. Iterative Learning: System finds documents similar to seed set using statistical models
- 3. Feedback Loops: Additional rounds of manual review refine accuracy
- 4. Project-Specific: Each new case requires training from scratch
Aid4Mail’s AI Approach
- Immediate Operation: No training phase. Write a prompt and start processing instantly
- True Comprehension: LLMs understand language, context, nuance, and meaning
- Universal Flexibility: One model handles filtering, classification, translation, and extraction across multiple languages
- Natural Language Control: Plain language prompts replace training by examples
TAR’s Key Limitations
The Cold Start Problem
Requires substantial upfront manual review before automation begins—days or weeks of delay and significant costs.
Inflexibility
Struggles with new document types, evolving case theories, multiple classification schemes, and multilingual datasets.
Single-Purpose Design
Primarily designed for binary responsive/non-responsive classification. Other analytical tasks require separate tools.
Expertise Requirements
Requires specialized knowledge of predictive coding protocols, statistical validation, and continuous quality control.
The Paradigm Difference
TAR asks:
“Can we find more documents similar to these examples?”
Aid4Mail’s AI asks:
“Can we understand what these documents actually mean and process them accordingly?”
When Might TAR Still Be Relevant?
To provide balanced perspective, TAR retains some advantages in specific scenarios:
- • Established Protocols: Organizations with mature TAR workflows and proven defensibility records
- • Massive Productions: Hundreds of millions of documents where marginal per-document cost differences become significant
- • Highly Repetitive Cases: When exact same legal issues appear repeatedly and training investment can be amortized
However, even these advantages diminish as AI costs decrease, processing speeds increase, and legal acceptance grows.
The Power of AI: Key Benefits
Integrating AI into your email processing workflow with Aid4Mail offers significant advantages over traditional methods.
Enhanced Accuracy
AI-powered filtering produces more accurate results than keyword searches, reducing the risk of false positives and false negatives.
Easier To Create
AI prompts are simpler to create than Boolean queries and can often be improved with the help of AI itself, requiring less specialized knowledge.
Multilingual Support
AI filtering and classification excel at handling multiple languages reliably, a challenge for keyword-based approaches.
Streamlined Classification
Go beyond simple “relevant” or “not relevant.” AI classifies emails into many categories, enabling efficient organization and targeted review.
Automated Analysis
Perform email summarization, translation, information extraction, and inference generation directly in Aid4Mail.
Faster EDRM Workflow
AI can automate many steps in the Electronic Discovery Reference Model (EDRM) process, from collection to production.
Reduced Manual Review Burden
By automating filtering, classification, and analysis, AI significantly lowers the amount of manual review required, saving time and resources.
AI Features in Detail
Aid4Mail offers three core AI-powered features that transform how you process email evidence.
3.1. AI Email Filtering
Problem with Traditional Filtering
- • High false-positive rate (irrelevant emails included)
- • High false-negative rate (relevant emails missed)
- • Requires specialized knowledge for effective queries
- • Language limitations with multilingual datasets
AI Solution
- • Improved precision and recall
- • Natural language prompts, less specialized knowledge needed
- • Robust and efficient multilingual capability
- • Context and meaning-based identification
3.2. AI Email Classification
Classification extends filtering by grouping emails into multiple categories, not just “relevant” or “not relevant.”
Open-Ended Classification
The AI model determines the category based on your prompt.
“Identify the primary language used in this email”
Restricted Classification
You provide a list of allowed categories.
Categories: Responsive, Unresponsive, Review
Output Options
- • Folder Organization: Automatically sort emails into folders named by classification
- • Archival Output: Include classification as a field in PDF, HTML, CSV, XML, or JSON
3.3. AI Email Analysis
Perform a wide range of analytical tasks to extract insights and intelligence from email content.
Summarization
Translation
Extraction
Inference
Store analysis results in PDF, HTML, CSV, XML, or JSON files for review, reporting, and further processing.
Understanding AI Classification Errors
AI hallucination refers to instances where AI models produce information that appears plausible but is factually incorrect. While this is a legitimate concern in creative text generation, Aid4Mail’s structured classification approach makes it largely irrelevant.
Why Aid4Mail’s AI Implementation Is Different
Constrained Responses
AI responds with predefined categories or simple determinations (e.g., “Responsive” vs. “Unresponsive”), eliminating the opportunity for fabrication.
Verifiable Input-Output
Every AI response is directly tied to specific email content you can verify. The email being analyzed is always available for review, making any classification decision fully auditable.
No External Knowledge Required
Prompts instruct the AI to evaluate only the email content provided—not to draw on external knowledge or training data.
Deterministic Classification
When an AI model selects “English” as a language or “Responsive” as a category, it’s making a judgment based on input data, not inventing information.
Proven Reliability
Our extensive internal testing demonstrates that top-tier models achieve 95–98% classification accuracy. These accuracy rates are exceptional for classification tasks and confirm that AI models perform reliably in Aid4Mail’s structured framework.
Important: Not all models perform equally well. Our testing revealed significant variation, with some models achieving accuracy rates below 60%. Model selection matters—see Section 5 for detailed performance metrics.
Classification Errors vs. Hallucination
Classification Error
The AI selects an incorrect category based on ambiguous content or misinterpretation of context. Example: An email discussing both legal and technical issues might be classified as “Technical” when “Legal” would be more appropriate.
Hallucination
The AI fabricates information not present in the source material. Example: Claiming an email mentions a person or date that doesn’t appear anywhere in the email. This does not occur in Aid4Mail’s constrained implementation.
Best Practices for Maximum Accuracy
- Use Clear, Specific Prompts: Well-defined classification criteria help the AI make accurate decisions. Avoid ambiguous language or overlapping categories.
- Start with Small Test Sets: Run a representative sample to verify classifications before processing large volumes.
- Choose Appropriate Models: Some models perform better than others for specific tasks. See Section 5 for model performance data.
- Implement Quality Controls: Sample reviews help maintain accuracy and identify areas for prompt refinement.
AI Speed, Cost, and Model Selection
Choosing the right AI model is crucial for performance and cost-effectiveness. Our comprehensive testing reveals important insights about accuracy, speed, and value.
5.1. Performance Example
Gemini 2.5 Flash processed a 3 GB mailbox (34,097 emails) in five hours and 20 minutes—about 1.8 emails per second (including document attachments). Cost: $20.65 USD using 67.33 million tokens.
67.33M
Tokens processed
5h 20m
Processing time
<$21
Total cost
Token usage note: Including attachment data can increase token consumption by 30% to 90% and reduce processing speed by ~15%. AI filter and classification tasks consume very few output tokens with non-thinking models (often fewer than 10 per email).
5.2. Choosing the Right AI Model
Performance Criteria
- Context Window: Larger windows (1M+ tokens) handle full emails with attachments without truncation
- Speed: Faster models (4,000+ tokens/sec) significantly reduce investigation time
- Accuracy: Test models on sample data to verify classification and analysis quality
Technical Requirements
- Output Schema Support: Essential for filtering; important for predefined classification
- Rate Limits: Enterprise platforms offer better quotas than consumer APIs for large datasets
- Cost Efficiency: Balance per-token pricing against processing speed and accuracy
5.3. Our AI Model Tests
Test Methodology
We tested 1,130 emails total across three classification tests to evaluate real-world performance:
Test 1: 200 Forensic Emails
- • 9 categories (IFA, Bribery, Threats, Harassment, OER, Phishing, Spam, Clean, Inconclusive)
- • English, German, and Korean
Test 2: 100 FOIA Emails
- • 50 climate science (Responsive)
- • 50 weather events (Unresponsive)
Test 3: 830 Business Emails
- • Real-world mailbox (226 MB)
- • SYSTEM, PRIVATE, WORK categories
- • Includes attachment text extraction
Models Tested
Alibaba: Qwen 2.5 32B, 72B, 7B
Anthropic: Claude 3.0–4.5 Haiku, 3.7 Sonnet, Sonnet 4/4.5, Opus 4.5
Deepseek: Deepseek V3
Google: Gemini 1.5 Pro, 2.0 Flash, 2.5 Flash/Light, 3 Flash (preview)
Meta AI: Llama 4 Maverick, Llama 4 Scout
Microsoft Foundry: Kimi K2 Thinking
Mistral AI: Magistral Medium/Small, Ministral 8B, Mistral Large 2/3, Medium 3, Small 3.0–3.2, NeMo
OpenAI: GPT-4.1/Mini/Nano, GPT-4o/Mini, o1, o3 Mini, GPT-5/5 mini/5.2
xAI: Grok 3/3 Mini, Grok 4/4.1 (fast, reasoning)
Local (Ollama/LM Studio): 17 quantized model variants (DeepSeek R1, Gemma 3, GPT-OSS, Llama 3.3, Magistral, Ministral 3, Mistral Small 3.2, Qwen 2.5, etc.)
5.4. Test Results
Use Enterprise-Grade Platforms: Our latest tests strongly recommend using models hosted on Amazon Bedrock, Google Vertex AI, or Microsoft Foundry rather than rate-limited consumer APIs. These platforms offer superior performance, better regional availability, and fewer rate-limit issues.
Top Commercial Models (Accuracy)
1. Claude Opus 4.5
MOST ACCURATE97.6%
accuracy
Highest composite accuracy across 1,130 test emails. Strongest PRIVATE and SYSTEM classification in business triage. Premium investment justified by exceptional precision.
2. Grok 4.1 (fast, reasoning)
EXCEPTIONAL VALUE97.6%
accuracy
Ties Claude Opus 4.5 for top accuracy at a fraction of the cost. Slower than other top commercial models.
3. OpenAI GPT-5.2
STRONG CONTENDER97.1%
accuracy
5. Gemini 2.5 Flash
BEST ALL-ROUND95%
accuracy
Very fast and exceptional value. Broad availability via Google Vertex AI across Americas, Europe, and Asia-Pacific.
Top Commercial Models (Speed)
8,261
Gemini 2.5 Flash
tokens/sec — $0.30/M
5,636
Mistral Large 3
tokens/sec — $0.50/M
4,604
Gemini 3.0 Flash
tokens/sec — $0.50/M
Top Open-Source Models
Kimi K2 Thinking
96.7%Requires data-center-class hardware. Available on Microsoft Foundry.
GPT-OSS 120B (Q4_K_M)
94.7%Requires data-center-class hardware.
Mistral Small 3.2 24B (Q4_K_M)
92%Requires high-end consumer hardware for best speed.
Ministral 3 14B (Q4_K_M)
89.6%Fast on consumer hardware (e.g., NVIDIA RTX 4090 with 24 GB VRAM).
5.5. AI Model Features
Pricing can change; always verify with the provider. For best performance, use enterprise platforms rather than consumer APIs.
| Model | Context | Input $/M | Speed | Platforms |
|---|---|---|---|---|
| Claude Opus 4.5 | 200K | $5.00 | 1,772 t/s | Anthropic, Bedrock, Vertex, Foundry |
| GPT-5.2 | 400K | $1.75 | 2,396 t/s | OpenAI API, Foundry |
| Grok 4.1 (fast) | 2M | $0.20 | 946 t/s | xAI API, Foundry |
| Gemini 2.5 Flash | 1M | $0.30 | 8,261 t/s | AI Studio, Vertex |
| Gemini 3.0 Flash | 1M | $0.50 | 4,604 t/s | AI Studio, Vertex |
| Magistral Medium | 128K | $2.00 | 1,134 t/s | Mistral AI |
| Mistral Large 3 | 128K | $0.50 | 5,636 t/s | Mistral AI |
| Kimi K2 Thinking | 262K | N/A local | hardware | Foundry, LM Studio |
| GPT-OSS 120B | 128K | N/A local | hardware | Ollama, LM Studio |
5.6. Regional Availability by Platform
Amazon Bedrock
Claude Opus 4.5 & Sonnet 4.5: Brazil, Canada, USA, France, Germany, Ireland, Italy, Spain, Sweden, Switzerland, UK, Australia, Japan, Korea
Google Vertex AI
Gemini 2.5 Flash: Canada, USA, Belgium, Finland, France, Germany, Italy, Netherlands, Poland, Spain, UK, Australia, Japan, Korea
Gemini 3.0 Flash: Check Google Vertex AI for current regional availability
Claude Opus/Sonnet 4.5: USA, Belgium
Microsoft Foundry
Claude Opus/Sonnet 4.5, GPT-5.2, Grok 4.1 (fast), Kimi K2 Thinking: USA, Sweden
Regional availability changes frequently. Always verify with your platform provider before deployment. For GDPR compliance, European organizations should prioritize providers with EU-based infrastructure.
5.7. Multilingual Support
AI models can process multiple languages within a single prompt, recognizing context and meaning regardless of language. Not all models handle all languages equally well—select a model that reliably handles the languages in your dataset.
| Model | Primary | Strong Support |
|---|---|---|
| Claude Opus 4.5 | English | Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Indonesian |
| Gemini 2.5 Flash | — | 35+ languages including English, Arabic, Chinese, Japanese, Korean, and most European languages |
| Grok 4.1 Fast | English | Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, Dutch, Turkish, Polish, Swedish |
| GPT-5.2 | English | Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Indonesian, Bengali |
| Mistral-family | French, English | Spanish, German, Italian, Portuguese (strong choice for French-language datasets) |
Gemini models offer the broadest multilingual coverage (35+ languages). Always test with a representative sample before large-scale processing in a non-primary language.
5.8. Offline AI: Maximum Security with Local Processing
Complete Data Privacy
Keep all information within your security perimeter
Regulatory Compliance
Meet stringent legal standards for data handling
Consistent Performance
Avoid external API quotas and service availability constraints
Cost Efficiency
Eliminate recurring token charges after initial setup
Implementation
Aid4Mail uses JSON configuration files (in the program folder under the AI Config subfolder) to control model interactions. Our helpdesk team can assist with configuring for offline use.
Recommended Hardware (GPT-OSS 120B / Kimi K2 Thinking)
- • Latest-generation CPU with 16+ cores
- • NVIDIA A100 (80 GB VRAM) or equivalent GPU
- • 128 GB system RAM
High-end consumer GPUs (RTX-class) can run smaller models or quantized variants at reduced speeds.
5.9. Enterprise-Ready Alternatives
Local inference speeds (typically 1,500–4,200 tokens/sec for recommended 14–27B models) are generally slower than the fastest cloud models (up to 8,300 tokens/sec), though the gap depends heavily on model choice and hardware. Enterprise platforms offer a practical compromise—delivering high performance while meeting data residency, compliance, and security requirements.
Microsoft Foundry
GPT-5.2 & Grok models with enterprise compliance, regional data residency
Google Vertex AI
Gemini & Claude models with scalable multi-region infrastructure
Amazon Bedrock
Claude models in AWS ecosystem with compliance tools and reservable throughput
Configuration Support: Aid4Mail gives you full control over your AI setup. Our helpdesk can assist with customizing your configuration for enterprise platforms.
Getting Started: AI Provider Setup
Before using Aid4Mail’s AI features, you need an account and API key from a supported provider. Follow each provider’s instructions to create an account, generate an API key, and manage billing.
Anthropic
Claude Opus & Sonnet 4.5 models
Google AI
Gemini 2.5 & 3.0 Flash models
Meta AI
Llama & Gemma models
Mistral AI
GDPR-compliant Magistral models
OpenAI
GPT-5.2 models
xAI
Grok 4.1 models
What You’ll Need
- • Create an account with your chosen provider
- • Generate an API key from the provider’s console
- • Set up billing and add credits to your account
- • Review the provider’s terms of service and privacy policy
Configuring Aid4Mail for AI Processing
Follow these steps to configure your API key, set up AI tasks, create sessions, and run your processing.
7.1. Entering Your API Key
Configuration Steps
- 1
Open Aid4Mail
Launch the Aid4Mail application on your computer.
- 2
Navigate to App Settings
Access through the View menu or the left-side toolbar.
- 3
Select the AI Tab
Click on the AI tab to access API key configuration.
- 4
Enter Your API Key
Select your desired provider, click “Configure,” and paste your API key.
7.2. Configuring AI Tasks (Filter, Classify, Analyze)
Open Project Settings (View menu or left-side toolbar) and select the AI tab. You’ll see sections for Filter, Classify, and Analyze, each configured independently.
Common Configuration Options
1. Select an AI Model
Choose a model for which you’ve entered an API key. Smaller models are often faster and cheaper.
2. Create or Load a Prompt
- • Write your own prompt, or click Open to access the library of pre-written prompts
- • Use Verify to test your prompt with the selected AI model
- • Click Save to store custom prompts for future use
3. Include Attachment Data (Optional)
Camera metadata, plain text documents, and extracted text from Word, PDF, Excel, PowerPoint.
Filter
Configure model and prompt to identify relevant emails based on meaning and context.
Classify
Organize emails into categories. Optionally enter a comma-separated list of predefined categories.
Analyze
Summarization, translation, extraction. Specify the maximum output tokens.
Attachment Text Size Limit
Under the Options heading, set an appropriate limit to control token usage and costs.
| Model Context Window | Recommended Size Limit |
|---|---|
| 2,097,152 tokens | 200 KB |
| ~1,000,000 tokens | 150 KB |
| 200,000 tokens | 75 KB |
| 128,000 tokens | 50 KB |
| 32,000 tokens | 20 KB |
7.3. Creating AI Tasks in Sessions
AI Filter Tasks
- 1. Go to the Settings tab on the Sessions screen
- 2. Under Filter, select “Enable AI filtering”
When to use: AI filtering is powerful but incurs costs. Use it when you need to analyze meaning or context—not for simple date ranges, participants, or keyword matching where standard Aid4Mail queries are faster and free.
AI Classification Tasks
- 1. Go to the Settings tab on the Sessions screen
- 2. Under Folder structure, select Use a template
- 3. In Folder structure template, insert
{Classify}
AI Analysis Tasks
Available for PDF, HTML, CSV, TSV, XML, and JSON output.
- 1. Go to Settings tab, ensure target format is PDF, HTML, CSV, TSV, XML, or JSON
- 2. Above the configuration field, select Add
- 3. Add AI.Analyze (and optionally AI.Classify) to Selected Items
- 4. Include other relevant fields (Subject, From, To, Date) and Save
7.4. Running Your Session
You’re Ready to Process
Click Run to start processing. Aid4Mail sends the relevant data to your chosen AI provider(s) and applies the results according to your configuration.
Pro Tip: Enable Incremental Processing
- • Turn on “Automatically record each email to allow incremental processing” in Source settings
- • If interrupted, use “Incremental processing” to resume from where you left off
- • Saves time and costs by avoiding reprocessing of completed emails
7.5. Common Errors Explained
Invalid JSON response / Failed to extract response from schema
The AI API returned data in an unexpected format. Usually a temporary server-side issue. Wait and try again.
HTTP 400: Bad Request
Email data exceeds the AI model’s processing limit. Consider a model with a larger context window or reduce attachment text size limits.
HTTP 403: Forbidden
Credit balance depleted or AI provider doesn’t support your region. Consider a different provider.
HTTP 429: Too Many Requests
Rate or token quota exceeded. Aid4Mail retries automatically with appropriate backoff. For large jobs, reduce concurrency or use enterprise platforms.
HTTP 500/502/503: Server Errors
Temporary server issues or high demand at the AI provider. Wait a few minutes and retry.
Pre-Written Prompt Library
Aid4Mail includes a library of over 200 pre-written prompts organized by task (Filter, Classify, Analyze) and theme, helping you get started quickly with proven templates.
Accessing Pre-Written Prompts
- 1. Go to Project Settings
- 2. Click on the AI tab
- 3. Find the Prompt field for your AI task
- 4. Click Open above the Prompt field
Windows Security Note
If pre-written prompts don’t appear when you click Open, Windows’ “Controlled folder access” protection may be blocking the installation. Check the AI Prompts subfolder in your Aid4Mail program folder.
Digital Forensics
32 specialized themes
- • Cybercrime & financial fraud
- • Crypto fraud & human trafficking
- • Cybersecurity threats
- • State-sponsored espionage
eDiscovery
20 litigation themes
- • Antitrust & IP theft
- • Harassment & insider threats
- • M&A due diligence
- • Whistleblower investigations
FOIA/Public Records
14 government themes
- • Environmental impact
- • Government misconduct
- • Surveillance practices
- • Lobbying influence
Why Use Pre-Written Prompts?
- • Time Savings: Don’t start from scratch
- • Best Practices: Follow proven AI interaction guidelines
- • Targeted Scenarios: Quickly find prompts relevant to your tasks
Customization Is Key
- • Review: Make sure the prompt’s logic matches your goals
- • Customize: Refine prompts to suit your specific project
- • Test: Verify and test on a small sample after customizing
Troubleshooting & Best Practices
Maximize efficiency, reduce costs, and improve results with these proven strategies.
Recommended Workflow
Server-Side Pre-Filtering
Select appropriate date ranges, folders, and keywords. Download to local drive using EML format with MIH+ file names.
Local Post-Filtering
Further narrow your dataset with Aid4Mail’s local filters before AI processing.
Cloud Attachments (Optional)
Include cloud attachments only for relevant emails after post-acquisition filtering.
Enable Incremental Processing
Allow resumption from any interruption point without reprocessing completed work.
Test and Refine
Test prompts with small samples before processing large datasets to verify results and estimate costs.
Troubleshooting Tips
API Key Errors
Make sure your API key is correct and active, with sufficient credits.
Prompt Errors
Use “Verify” to check for invalid prompts before processing.
Rate Limits
Monitor your provider’s rate limits. Consider enterprise platforms for large jobs.
Processing Speed
Speed varies by time of day. Aim for times when the API is less busy.
Context Window Limits
Use a model with a larger context window if needed. Avoid including attachment data with small context windows.
Output Errors
If output isn’t as expected, review your content configuration (Analyze) or folder structure (Classify).
Legal Considerations
Sending data to AI providers raises important privacy and data protection considerations, especially for sensitive investigations.
Disclaimer
This information is general guidance only and not legal advice. You must consult legal professionals to ensure compliance with applicable laws and regulations.
Key Principles (Regardless of Location)
- Data Minimization: Only process the minimum personal data required
- Purpose Limitation: Use processed data only for defined investigation purposes
- Data Security: Protect data under your control
- Data Retention: Delete or anonymize data when no longer needed
- Chain of Custody: Maintain a clear chain of custody
- Accuracy: Ensure data is accurate
GDPR Considerations (Europe)
- • Establish a GDPR-compliant lawful basis (legitimate interests or legal obligation)
- • Ensure Data Processing Agreement (DPA) in place with AI provider
- • Use EEA-hosted models when possible (Mistral AI, Azure, Vertex, Bedrock with EU config)
- • Document transfer mechanisms (EU SCCs or UK Addendum)
US Considerations
- • Review applicable federal and state laws (HIPAA, COPPA, CCPA/CPRA)
- • Consider Section 702 of FISA implications
- • Understand Stored Communications Act (SCA) obligations
- • Document compliance measures thoroughly
Recommendations for All Users
- Minimize Data: Use Aid4Mail filtering to limit what is sent to AI providers
- Consult Legal Counsel: Always verify your approach with privacy and forensics experts
- Document Everything: Record your legal basis, data transfer mechanisms, and risk assessments
- Review Provider Terms: Check your AI provider’s terms of service and privacy policies
- Stay Updated: Data protection laws frequently evolve