Pigment AI

We’re introducing a single, unified AI experience at Pigment. Instead of assistants, users now have powerful AI Agents in one place: the AI Chats. They are your specialized digital workforce, accepting natural language prompts in over 50 languages. Everything you could do before is still possible—and the Agents go much further.

The Modeler Agent helps you build, talking through your goals, whether simple or complex, and creating Blocks, formulas, Views and Boards accordingly.

The Analyst Agent is even more powerful, chatting with Members, pulling trends, insights and conclusions from your data and helping you design repeatable, schedulable Missions.

The Custom Agent lets you combine bespoke company knowledge with Pigment's powerful AI capabilities, navigating Boards and analyzing data more effectively.

And the Documentation Agent replaces the Documentation Assistant, accepting user help queries about the platform and issuing short summaries and links to Pigment’s Knowledge Base.

Pigment AI features that you used to use, the Data Assistant and Insights, have been replaced by the new, more powerful version of the Analyst Agent. The previous interface and shortcut have been replaced too.

Other features powered by Pigment AI remain unchanged:

• Predictions generates customized forecasts automatically for inclusion in your model. See Machine Learning Forecasting for more information.

• The MCP Server allows external AI systems to connect to Pigment’s features and data sources in a controlled, secure, and structured way. See MCP Server for more information.

• Explain the formula, found by the formula bar, opens the Documentation Agent with the current formula pre-loaded. For more information, see Other Pigment AI features.

• The Navigation Assistant responds to prompts like “Show me reports on key account health”, finding reports and dashboards from any Application in the Workspace. For more information, see Other Pigment AI features.

🎓 Pigment Academy

• For detailed insights, examples and use cases on Pigment’s AI features, explore the Pigment AI Learning Path.

• For a video in English or French on best practices when setting up for AI, see Getting your models ready for Pigment AI. Just make your language selection in the player!

Set up Pigment AI

Follow these steps to set Pigment AI up for your Application.

1. Request activation
   The Workspace Administrator, Security Administrator or the Primary Owner must submit a Support ticket here requesting activation. In your ticket, under AI Feature Request, specify your choice of the below:

   • “Modeler Agent, + Analyst, Custom & Documentation Agents”

   • “Analyst Agent, + Custom & Documentation Agents”

   • “Documentation Agent”

   • “MCP Server”

   • “Predictions” using Machine Learning Forecasting

   ℹ️ Note

   MCP Server activation is included when you choose any of the above.

2. Grant Members access using dedicated permissions
   Two new permissions allow you to manage which Members have access to the Agents:

• Access AI Agents

  • grants access to:

    • Modeler Agent (also requires Configure Blocks)

    • Analyst Agent

    • Custom Agent

    • Documentation Agent

• Configure AI Agents

  • grants permission to:

    • persist and automate analyses via Missions

    • create and configure Custom Agents

By default, all Members with Define Application Security are automatically granted Configure AI Agents.

For more information on updating Permissions, see About Roles, Permissions, and Access Rights.

The table below sets out the permissions needed by AI features:

This means that:

• Anyone with Access AI Agents can use any AI Agent that your Application supports, except for the Modeler Agent.

• Anyone with Configure Blocks and Access AI Agents can use the Modeler Agent. To take Modeler Agent access away from a Member, you need to remove their Configure Blocks permission.

• If at Workspace-level the Modeler and Analyst Agents are activated, you can not give access to the Modeler Agent without also giving access to the Analyst Agent.

As a rule, the Agents inherit permissions and data access rights from the user interacting with them, ensuring that they can only view data and perform actions the user is authorized for.

Update Roles as needed

Follow these steps to update Roles needing access:

1. In your Application, select the three dots at the bottom of the sidebar and then Roles, permissions & access.

2. The main pane opens on Overview. Select the next tab over: Roles.

3. Hover the mouse over the Roles needing access. Select the blue pencil icon that pops up to Edit Role. In the dialog that appears, under Permissions, open the drop-downs as appropriate, toggling On the permissions according to the grid below.

4. Save.

ℹ️ Note

By default, all Roles have Access AI Agents and Admin Roles have Configure AI Agents. For more information, see About Roles, Permissions, and Access Rights.

AI data access

The AI data access setting allows you to prevent the MCP Server, the Analyst Agent, and the Custom Agent from querying data in a particular Metric.

Once activated, the MCP Server, the Analyst Agent, and the Custom Agent have access to all an Application’s Metrics by default. You may want to hide certain Metrics from the MCP Server, the Analyst Agent, and the Custom Agent, for example if they contain sensitive data.

Change the setting

You need two permissions to operate this setting: Configure AI Agents and Configure Blocks. There are two ways to adjust it:

1. To change the setting for just one Metric, open its settings and scroll down in the General tab to AI data access. For more information, see Block settings for Metrics.

2. To bulk update this setting:

   1. In your Application, open the Blocks folder in the left sidebar, and select All Blocks.

   2. From the five tabs All types, Transactions, Dimensions, Metrics and Tables, select Metrics.

   3. (Optional) In the row below, open the AI drop-down on the far right, selecting Filter if it is not displayed. Choose from:

      1. Can access Metric’s data

      2. Cannot access Metric’s data

   4. Select the checkbox to the left of Name in the main pane. The bulk action toolbar appears.

   5. Make your selection of Metrics to toggle, using their checkboxes.

   6. Select Toggle AI data access from the bulk action toolbar.

Types of actions affected

Turning off access strictly impacts Metric data querying, and does not prevent the following types of actions:

• Block structure modifications

• Block configuration edits

• Adding or editing Views

• Any non-data actions

This setting does not affect the Modeler Agent.