Skip to main content
Documentation

Transform Investigations with AI-Powered Analysis

Aid4Mail Investigator and Enterprise editions integrate artificial intelligence, providing a fundamental change in how email analysis can be performed. As among the first digital forensics tools to integrate AI analysis of emails, including modern attachments, Aid4Mail sets a new standard for the industry—with the option to perform investigations entirely offline.

98%

Top accuracy (Claude Opus 4.5)

8,261

Tokens/sec (Gemini 2.5 Flash)

200+

Pre-Written Prompts

1

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

Automatically filtering emails with unparalleled accuracy, going far beyond simple keywords to understand meaning and context
Instantly classifying emails into relevant categories, streamlining your review process with unprecedented efficiency
Uncovering critical insights through automated summarization, translation, and information extraction
Dramatically accelerating your investigations by automating time-consuming manual reviews
Maintaining complete data privacy with local AI inference, keeping processing fully under your control

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. 1. Training Phase: Experts manually review 200–2,000+ documents as a “seed set”
  2. 2. Iterative Learning: System finds documents similar to seed set using statistical models
  3. 3. Feedback Loops: Additional rounds of manual review refine accuracy
  4. 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.

2

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.

3

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.

4

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.
5

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 ACCURATE

97.6%

accuracy

Context: 200K tokens
Input Cost: $5.00/M
Platforms: Bedrock, Vertex, Foundry

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 VALUE

97.6%

accuracy

Context: 2M tokens
Input Cost: $0.20/M
Platform: xAI API, Microsoft Foundry

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 CONTENDER

97.1%

accuracy

Context: 400K tokens
Input Cost: $1.75/M
Platform: OpenAI, Microsoft Foundry
5. Gemini 2.5 Flash
BEST ALL-ROUND

95%

accuracy

Context: 1M tokens
Input Cost: $0.30/M
Speed: up to 8,261 tokens/sec

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.

6

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.

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
7

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. 1

    Open Aid4Mail

    Launch the Aid4Mail application on your computer.

  2. 2

    Navigate to App Settings

    Access through the View menu or the left-side toolbar.

  3. 3

    Select the AI Tab

    Click on the AI tab to access API key configuration.

  4. 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.

Example: Responsive, Unresponsive, Review
Analyze

Summarization, translation, extraction. Specify the maximum output tokens.

Recommended: 500–2000 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 tokens200 KB
~1,000,000 tokens150 KB
200,000 tokens75 KB
128,000 tokens50 KB
32,000 tokens20 KB

7.3. Creating AI Tasks in Sessions

AI Filter Tasks

  1. 1. Go to the Settings tab on the Sessions screen
  2. 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. 1. Go to the Settings tab on the Sessions screen
  2. 2. Under Folder structure, select Use a template
  3. 3. In Folder structure template, insert {Classify}

AI Analysis Tasks

Available for PDF, HTML, CSV, TSV, XML, and JSON output.

  1. 1. Go to Settings tab, ensure target format is PDF, HTML, CSV, TSV, XML, or JSON
  2. 2. Above the configuration field, select Add
  3. 3. Add AI.Analyze (and optionally AI.Classify) to Selected Items
  4. 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.

8

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. 1. Go to Project Settings
  2. 2. Click on the AI tab
  3. 3. Find the Prompt field for your AI task
  4. 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
9

Troubleshooting & Best Practices

Maximize efficiency, reduce costs, and improve results with these proven strategies.

Recommended Workflow

1

Server-Side Pre-Filtering

Select appropriate date ranges, folders, and keywords. Download to local drive using EML format with MIH+ file names.

2

Local Post-Filtering

Further narrow your dataset with Aid4Mail’s local filters before AI processing.

3

Cloud Attachments (Optional)

Include cloud attachments only for relevant emails after post-acquisition filtering.

4

Enable Incremental Processing

Allow resumption from any interruption point without reprocessing completed work.

5

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).

Ready to Transform Your Email Investigations with AI?

Experience AI-powered email forensics with up to 99% classification accuracy. Process complex datasets faster with natural language prompts.