Operational trust for AI agents

Updated: September 21, 2026

Operational trust is the term used throughout this documentation to describe a set of related capabilities that give you a live, signal-driven view of how well your deployed AI agents are performing in production. It is not a named feature in the Collibra interface, but a concept that brings together AI monitoring, the agent Quality tab, and the Agents dashboard.

The foundation of operational trust is AI monitoring. Collibra reads monitoring signals, such as quality evaluations and token consumption, directly from the AI platform each agent is integrated through, and surfaces those signals across the product. Governance signals, such as assessments, lifecycle status, and documentation completeness, reflect what you know about an agent. Operational signals reflect what the agent is actually doing: how often its responses pass quality checks, and how much it consumes in token resources. What is collected, and how a pass or fail result is determined, differs by AI integration; go to AI monitoring for AI agents for the breakdown.

Important These capabilities are currently available for agents integrated via the Databricks AI integration, the AWS Bedrock AI integration, the Gemini Enterprise Agent Platform integration, and the Azure AI Foundry integration. Support for additional AI platforms is planned for future releases.

Enabling the feature

Operational trust must be enabled before any of these signals appear. In Settings, under AI Command Center, switch on Operational trust for AI agents. For complete steps, go to Set up AI Command Center.

How operational trust works

Each AI integration has its own mechanism for collecting operational trust signals from its AI platform, on its own monitoring schedule. The Quality tab shows these signals wherever it appears: on the AI Agent asset page and on each of its AI Agent Version asset pages. For the mechanism specific to each integration, go to AI monitoring for AI agents.

Note Operational trust data requires the AI platform to have monitoring data available for the agent, for example, agent interaction trace data in Databricks, or CloudWatch invocation metrics for the agent alias in AWS Bedrock. If this data is not available, no operational trust data appears in Collibra for that agent.

Signals collected

Collibra collects two types of operational trust signals. What each signal is derived from depends on the AI integration:

Monitor pass rates. Collibra records the result, pass or fail, of each monitoring check performed against an agent, and computes a pass rate from those results. Pass rates are computed and surfaced as daily and 7-day aggregate values. What counts as a pass or fail check, how many AI Monitor assets are linked to an agent, and how often current-day metrics update, depends on the AI integration. For details, go to AI monitoring for AI agents.
Token consumption. Prompt and completion token counts aggregated from agent interactions. How often current-day metrics update depends on the AI integration.

AI Monitor assets

In Collibra, an AI Monitor asset represents a monitoring source for an agent, such as an LLM judge configured in Databricks or a monitored agent alias in AWS Bedrock. AI Monitor assets are created automatically when the integration syncs; you do not create them manually.

A single AI Agent can have multiple AI Monitor assets linked to it, one for each judge or alias that monitors the agent's responses, depending on the integration. For complete information about AI Monitor assets, go to AI monitoring for AI agents.

Where operational trust data surfaces

Operational trust data appears in three places in AI Command Center.

Surface	What it shows
AI Trust Score, the Operational Health theme	The 7-day average monitor pass rate across all AI Monitor assets linked to the AI Agent Version asset. If no monitoring data is available for this AI agent version for the past 7 days, this theme is excluded from the Trust Score entirely. For complete information, go to AI Trust Score: contributing factors.
Agent Quality tab	A tab on AI Agent and AI Agent Version asset pages showing per-monitor daily pass rate trend lines. Use this view to track an individual agent's quality over time and compare performance across monitors.
Agents dashboard	A fleet-wide operational dashboard that shows AI Monitor pass rate trends and token consumption across all monitored agents in your environment. Use this view to identify which agents or monitors need attention. In the AI monitors table, click a monitor name to see which AI Agent Versions are evaluated by that monitor and how each is performing. From there, click an agent version to navigate to its asset page and Quality tab for detailed trend lines.

Surface

What it shows

AI Trust Score, the Operational Health theme

The 7-day average monitor pass rate across all AI Monitor assets linked to the AI Agent Version asset. If no monitoring data is available for this AI agent version for the past 7 days, this theme is excluded from the Trust Score entirely. For complete information, go to AI Trust Score: contributing factors.

Agent Quality tab

A tab on AI Agent and AI Agent Version asset pages showing per-monitor daily pass rate trend lines. Use this view to track an individual agent's quality over time and compare performance across monitors.

Agents dashboard

A fleet-wide operational dashboard that shows AI Monitor pass rate trends and token consumption across all monitored agents in your environment. Use this view to identify which agents or monitors need attention.

In the AI monitors table, click a monitor name to see which AI Agent Versions are evaluated by that monitor and how each is performing. From there, click an agent version to navigate to its asset page and Quality tab for detailed trend lines.

Note Operational trust metrics are stored in a time-series optimized format to power the Quality tab, Agents dashboard, and trust score features. They are not accessible through the standard Collibra platform APIs.