How Axonius Leverages AI with AI Technical Agent - EA

Axonius AI Technical Agent is a productivity and support capability designed to act as an in-product technical assistant. It helps users analyze data, find answers across UIs, and draft precise action parameters directly within the platform dashboard. To ensure safety and regulatory compliance, the AI Technical agent operates strictly as a productivity tool. It provides technical guidance but is restricted from performing unsupervised automated decision-making or executing actions independently.

Customers’ Control, Accessibility, and Settings

Activation Options & Functional Impact: The AI Technical Agent is enabled through an in-product Opt-In UX by the Customer Administrators. If the feature is turned off, the agent's user interface is completely removed from view.

Deployment and AI models: The AI Technical Agent relies on Amazon Bedrock and is available only to SaaS customer instances.

Data Handling

To deliver actionable insights, the AI Technical Agent requires access to tenant data; masking, pseudonymizing, or fully de-identifying this information would restrict the product's core utility. Customer data is continuously maintained within a logically isolated environment unique to each instance. Axonius strictly prohibits the pooling, combining, or cross-tenant aggregation of customer data. To ensure high speed performance, the underlying infrastructure hosts processing services in geographic regions chosen for proximity and data routing speed.

Training and Optimization

The AI Technical Agent does not use customer or user-provided data to train or retrain the global models. Instance-level fine-tuning is a core requirement of the AI Technical Agent; all resulting fine-tuned models and associated data are strictly isolated per tenant. The AI Technical Agent automatically learns from customer data to optimize results exclusively for each specific customer organization.

Transparency, Explainability, and Human Oversight

The AI Technical Agent interface includes a persistent footer that clearly disclaims the automated interaction. From this footer, a "[Learn More]" link directs users to additional details on the Axonius documentation site. To ensure seamless escalation, an obvious path to a human agent is positioned immediately adjacent to the chat input field, providing direct entry to the Axonius Support Portal. The system functions entirely under a supervised operational model and avoids unsupervised automated decision-making. The AI Technical Agent merely drafts parameters; users must actively evaluate the output and manually click a verification button (e.g., "Search", "Apply", "Run", or "Save") to run it. Explicit prompts will always appear to secure user confirmation before any data-modifying activity is finalized.

Accuracy, Reliability, Security and Integrity

The AI models build their knowledge base using customer data, as validated by Axonius’ adapters. This localized anchoring fundamentally insulates them from external threat actors and malicious outside manipulation. Users can initiate a new chat session at any time, which completely clears the local context and prevents conversational history from bleeding into the new interaction. Additionally, Administrators have the ability to globally disable persistent memory/history between chat sessions.

Multi-layered security and operational guardrails are actively applied across the data pipeline to verify structural integrity. Additionally, we maintain an active multi-tiered Quality Assurance (QA) process. This includes: Reliability is managed through a scheduled monitoring lifecycle. Following the deployment of this AI-driven feature, we conduct periodic performance and accuracy assessments. This iterative process is designed to refine model outputs and align them with evolving security landscapes.

Retention

Interaction history is retained (post-contract termination) for a standard rolling window of 30 days to assist with debugging and context, after which it is automatically deleted.