Reimagining AI interactions in Pigment

Over the past few weeks, the AI experience in Pigment has evolved significantly.

The introduction of the Modeler Agent marked an important milestone for us, but it was also part of a broader shift in the way users interact with the AI functionality within Pigment.

We’re building a conversational, customizable AI experience embedded directly into planning workflows.

If you’ve been using Pigment recently, you may have already seen this taking shape through:

• A more conversational Analyst experience
• The introduction of Custom Agents
• A unified way to access AI across the platform

Taken together, these changes mark a shift toward working with AI more like a collaborator in your day-to-day work.

From prompts to conversations: Now you can talk to the Analyst Agent

The Analyst now supports a more conversational way of working, that eliminates the need for the user to do prompt engineering.

Additionally, the Analyst now understands your context. it’s aware of the Board you’re on and the data you’re looking at. That means you can start an analysis directly from any data point, without needing to explain your setup.

As you interact, the Analyst turns your conversation into structured analyses in the background, so you can focus on the question, not how to formulate it.

Once you’ve explored and reached the outcome you need, you can ask the Analyst to turn it into a report and set it up to run automatically at the cadence you choose. What started as a conversation becomes a repeatable workflow, without ever needing to write a complex prompt.

We’ve also expanded the Analyst’s capabilities, including support for code execution, enabling more advanced and flexible analyses when needed.

The result is a much more direct path from question to result.

Custom agents: Trained on your own organization’s context

Pigment’s home-grown agents are great. But the platform itself is built around flexibility, and we wanted to bring more of that to our AI experience.

Custom Agents extend Pigment’s AI by allowing organizations to specialize agents for their business.

We can’t wait to see what customers do with these.

How it works

With Custom Agents, organizations can define how an agent behaves, what knowledge it uses, which capabilities it can access, and where it is available inside Pigment.

This makes it possible to deploy agents that are aligned with company-specific processes, reflecting each organization’s definitions, methodologies and ways of working.

Custom Agents combine Pigment’s existing agent expertise with customer-specific instructions and knowledge, so AI reflects each team’s terminology, KPIs, and workflows, directly inside the applications they use every day.

How can I use it?

There are infinite use cases for custom agents - the limit is your imagination. But maybe you could start with:

FP&A analyst agent
Helps finance teams analyze performance, explain variances, and prepare insights for business reviews.

Workforce analyst agent
Helps HR and People teams analyze headcount data, track workforce KPIs, and model the impact of hiring or attrition scenarios.

Supply chain analyst agent
This creates an agent that helps supply chain and operations teams monitor inventory levels, analyze demand forecasts, and identify risks across the supply network.

View more details on how to set one of these up in the Pigment Knowledge Base entry.

We think Custom Agents will be particularly helpful for accelerating onboarding and adoption - new users can now get guided, contextual help directly inside Applications, reducing training effort and support dependency.

And you can also use them to ensure consistency across users and teams - embed institutional knowledge, definitions, and processes in your agents to ensure everyone works from the same playbook.

A more intuitive AI experience

AI is now accessible from a single, unified space within Pigment, making it easier to start a conversation and access agents.

No need to search for features or switch contexts. Whether you’re exploring data or building a new model, there’s a consistent entry point that supports how people naturally work: start with a question, then navigate toward answers.

What next?

All of the features in this article are now available in Pigment, and they mark an important step in the journey towards our vision for the AI experience in Pigment - seamless and continuous interaction with a helpful, personalized agentic workforce.

To learn more about how Pigment’s AI functionality can help your team, join one of our live tours.