Operations

The Operations section of AI Governance is the central management hub for all AI assets running in your organization. It provides inventory, moderation, prompt, and model governance across five tabs: AI Assistants Inventory, AI Workers Inventory, Moderation, Prompt Library, and Model Groups.

Who Uses This Section

Role	How They Use It
Platform Administrator	Manage all AI assistants and workers across the organization. Create and assign Model Groups to standardize model usage.
CISO / Security Officer	Audit which assistants are deployed, which models they use, and which profiles have access. Enforce model policy via Model Groups.
AI Product Owner	Maintain the Prompt Library as a reusable asset. Configure moderation rulesets to control AI output quality.
Compliance Officer	Verify that all deployed assistants are bound to approved Model Groups. Review moderation logs for flagged interactions.
CTO / Technical Lead	Use Model Groups to centrally control model selection across all assistants without editing each one individually.

AI Assistants Inventory

A searchable catalog of all AI Assistants deployed in the workarea.

Each assistant card displays:

Name and workarea — assistant name and the workspace it belongs to
Models — the AI models currently bound to the assistant (Not detected if no model is configured)
Tools — the tools enabled on the assistant (e.g. LLM Generative AI, AI Data Graphing)
Profiles with Access — the user profiles that have access to interact with this assistant (e.g. Super Users)

Use the search bar to filter assistants by name. Use the external link icon on each card to open the assistant directly in AI App Studio.

AI Workers Inventory

A searchable catalog of all AI Workers deployed in the workarea.

AI Workers are background AI processes that operate outside of direct user interaction. This tab provides the same search and inventory capability as AI Assistants Inventory, scoped to workers.

Moderation

Moderation allows you to define rulesets that govern AI output quality and compliance. It is divided into two panels:

Moderation Rules Set
A table of all configured rulesets showing: Ruleset name, Count of Rules, Created / Updated date. Use + Add Ruleset to create a new ruleset.

Moderation Logs
A searchable log of all moderation events. Columns include: Log Id, Timestamp, Flagged, Ruleset, Severity, Reviewer, Action Taken. Use the search bar to find specific events by keyword.

Creating a Moderation Ruleset

Click + Add Ruleset
Enter a Ruleset Title
Set the Status (default: ACTIVE)
Under Rules, click + Add Rule to add individual rules
For each rule, enter the rule context in the Rule Context tab — a free-text field describing what the rule enforces
Add as many rules as needed using + Add Rule
Click Save

Each rule is numbered sequentially (#1, #2, ...). Rules can be deleted individually using the × button.

Prompt Library

A centralized repository of reusable prompt templates available across the organization.

The table displays: Title, Created By, Created date, and edit/delete actions.

Managing Prompts

To create a prompt: Use the add action (+ button if available) or edit an existing entry.

To edit a prompt:

Click the pencil icon on the prompt row
Update the Prompt Title
Edit the prompt content in the rich text editor — supports Bold, Italic, Strikethrough, Heading, Code, Quote, Bullet list, Numbered list, Link, and formatting controls (undo/redo/clear)
The editor shows live line and word counts at the bottom
Click Save

Prompts stored here can be referenced from AI Assistants and other tools across the platform, reducing duplication and ensuring consistency in system-level instructions.

Model Groups

Model Groups are curated sets of AI models that can be bound to any AI tool in the platform. Instead of configuring a single model per assistant or tool, a Model Group defines an ordered list of models — the first model in the list is the primary (default), and the remaining models form the automatic fallback chain.

Curated sets of AI models. Bind a group to an assistant's model selector; the user then picks one model from the group per chat session. Order matters; the first model is the primary / default.

This enables centralized model governance: update the group once and the change propagates to every assistant and tool bound to it — without editing each one individually.

Model Group Table

The table displays all configured groups with the following columns:

Column	Description
Group	Group name, purpose badge (CHAT / SQL), description, and short ID
Models	The ordered list of models in the group (⭐ marks the primary)
Status	ACTIVE or INACTIVE
Created	Creator email and creation timestamp
Updated	Last update timestamp

Use the search bar to filter groups by name. Use the pencil icon to edit a group or the × icon to delete it.

Creating a Model Group

Click the + button in the top-right corner of the Model Groups tab.

Field	Description
Group Name	A descriptive name for the group (e.g. Powerful, Balanced, Cost-saver)
Description	What this group is for — shown as a subtitle in the table and in tool selectors
Status	ACTIVE (available for binding) or INACTIVE (hidden from selectors)
Scope	Which tools this group is available to. Apply to all (any tool) = available to any tool, all active models offered. A specific scope (SQL, Vision, etc.) limits the group to matching tools and offers only capability-matching models
Models	Select models one at a time using the dropdown. Drag rows using the ⠿ handle to reorder — the top model is the primary / default and the order defines the fallback chain

Click Save when done.

How Fallback Works

When a tool is bound to a Model Group and the primary model fails or is unavailable, the platform automatically walks the group in priority order — attempting each model in sequence until one succeeds. The single model configured above the group selector serves as the final fallback if all group members are exhausted.

This means a single Model Group configuration provides both user-selectable model choice and automatic resilience without any additional setup.

Scope Reference

Scope	Tools Available To
Apply to all (any tool)	All tools across App Studio and Reasoning Flows
CHAT	Conversational tools (LLM Generative AI, AI Moderator, Search Internet, etc.)
SQL	Query generation tools (Generative Query — GenerativeQ selector)

Binding a Model Group to a Tool

Once a group is created, bind it in any supported tool:

Open the tool in AI App Studio or Reasoning Flows
In the Model Configuration section, change the Model selector from Single Model to Model Group
A second dropdown appears — search or select the group
Save the assistant or flow

The group is now active for that tool. Any changes made to the group in Operations propagate automatically.

AI Governance — AI Governance section overview
Overview — aggregate metrics and provider health dashboard
Aerie — AI Agents — real-time AI operations view