Quest Data Modeler AI FAQs

This topic provides a high-level overview of Quest Data Modeler (QDM) AI capabilities, followed by frequently asked questions about platform architecture, data usage, security, privacy, and compliance.

Overview by Category

The following table summarizes how QDM AI capabilities are structured and governed.

Category

What QDM Delivers

AI Platform

AI capabilities powered by Azure OpenAI (GPT‑5.1), hosted on Microsoft Azure.

Modeling Capabilities

AI-assisted generation and modification of logical and physical data models, including entities, attributes, and relationships.

Data Processing Scope

Processes only the data required for data modeling workflows, including user prompts, limited model context, and execution metadata.

Data Storage

Persists conversation data, execution records, and model snapshots to support multi-turn interactions and rollback.

Privacy Protection

Doesn't use your data for AI training, advertising, or profiling, and supports user-initiated deletion.

Security Controls

Protects AI services with authentication, authorization, encryption in transit, and infrastructure-level encryption at rest.

Data Isolation

Enforces strict per-user and per-catalog access, so your data isn't visible to other users or tenants.

Compliance Support

Aligns with GDPR, CCPA, and Microsoft's Data Protection Addendum (DPA) through data minimization and isolation.

Governance and Auditability

Logs AI interactions and execution records to support audits, troubleshooting, and compliance reviews.

Operational Safeguards

 Applies validation, approval workflows, rate limiting, and rollback mechanisms to reduce AI-related risks.

Service Limitations

Applies rate limits and scope restrictions, and requires online connectivity and human review of outputs.

Quest Data Modeler AI - Security, Privacy, and Compliance Frequently Asked Questions (FAQs)

AI Platform and Usage

QDM uses Azure OpenAI (GPT‑5.1) for AI-powered features.

The AI model is hosted on Microsoft Azure through the Azure OpenAI Service.

AI usage is governed by the Microsoft Azure OpenAI Service terms and the Quest Software product terms.

Data Processing

QDM processes the following data:

  • User prompt (natural language input)

  • Conversation history (multi-turn context)

  • Data model context

  • Execution plan context

  • File inputs (Text, CSV, Excel, JSON)

  • System prompts (role definitions and safety instructions)

  • Session metadata used for routing and correlation

Data is processed only for:

  • Data model generation and modification

  • Requirement validation

  • Intent classification

  • Conversational assistance

  • Execution summarization

  • Maintaining conversation context

QDM doesn't use your data for advertising or profiling.

All processing occurs within Microsoft Azure infrastructure:

Service Purpose
Azure OpenAI Service LLM inference
Azure Kubernetes Service Application services
Azure-managed databases Storage

Data Storage and Retention

Yes. QDM stores your input in a PostgreSQL database as part of the multi-turn conversation architecture. Stored data includes:

  • User messages

  • Assistant responses

  • Conversation history

  • Agent execution records

  • Data model snapshots

Retention Policy: Data persists until explicitly deleted by the user, such as by deleting a chat session.

No. There is currently no separate feedback mechanism that collects additional data.

Data Privacy

No. QDM doesn't use your data to train or fine-tune AI models. Azure OpenAI also doesn't use customer data for training.

No. QDM enforces per-user isolation and per-catalog access control.

Yes. Your data is encrypted both in transit and at rest.

State Protection
In transit HTTPS communication with Azure OpenAI, HTTP Strict Transport Security (HSTS), and TLS encryption through the API Gateway
At rest Azure-managed encryption across the underlying storage services

Security Controls

QDM secures all AI services with JWT-based authentication and user login through QDM.

QDM protects data in transit with HTTPS, TLS encryption, and HTTP Strict Transport Security (HSTS).

QDM secures data at rest with Azure-managed encryption for:

  • PostgreSQL conversation and model data

  • Redis for rate-limiting state

QDM applies the following security measures:

  • API key and JWT authentication

  • Role-based access control (RBAC)

  • Rate limiting

  • HSTS enforcement

  • Input validation

  • System prompt safety rules

Governance and Compliance

Yes. Azure OpenAI complies with Microsoft’s Data Protection Addendum (DPA), supporting GDPR and related privacy regulations.

Yes. QDM logs AI interactions and execution records for monitoring, auditing, and compliance.

Yes. QDM collects per-request usage metrics, which are logged locally and stored in the database for monitoring and analysis. These metrics support:

  • Performance monitoring

  • System reliability

  • Operational insights

Operational Safeguards

QDM includes the following safeguards:

  • Prompt validation and input checks

  • Human-in-the-loop approval workflows

  • Execution validation and retry mechanisms

  • Rate limiting

  • Snapshot-based rollback

Review AI outputs before you use them. The system supports validation, retries, and rollback to help ensure reliability.

Service Limitations

  • Rate and token limits apply

  • An internet connection is required

  • File type support is limited

  • AI outputs might require manual review

  • Scope is limited to data modeling tasks

No. AI features require an active internet connection.

Yes. You can disable AI in one of these ways:

  • Remove or stop the AI-service microservice

  • Configure the API Gateway to block AI-service endpoints

Network Requirements

The Azure OpenAI endpoint is required: https://dm-ai-api.openai.azure.com

Additional Questions

No. QDM uses session data only to maintain conversation context, not to train or improve the model.

Yes. QDM logs all AI interactions for monitoring, security, and compliance.