Now in Open Beta!

Mandisa Foster · July 2026 · 5 min read

We've been working on something that changes the way you work in Boards entirely.

Today we're introducing the Raspberry AI Agent, an autonomous creative partner that lives directly on your board. It can do anything you can do in Boards: generating images, chaining modules, running multi-step workflows, without any of the manual effort. You describe the end result. The Agent figures out the rest.

Expand your creative time

Your Agent can handle as many parts of the workflow that require massive scale, repetitive processes, ideation to the MAX, so you have time to expand your creativity.

No technical knowledge required

• You don't need to know which modules to use or how to sequence them
• You don't need to construct a single prompt
• Just describe the end result in plain language and the Agent chains the right modules together and writes optimized prompts behind the scenes

Automate the manual work

• Recoloring a product across 12 palette variations
• Running a sketch-to-on-body pipeline across multiple poses
• Applying a print to a full set of model shots
• Tasks that used to require your hands on every step can now be kicked off with a single description

Do multiple things at once

• Start your color variation workflow, kick off your sketch-to-on-body pipeline, and begin a print recolor batch 
• Every task runs in the background while you move on to something else entirely
• All outputs land on your board as they complete, ready to review when you are

‍

What That Looks Like in Practice

Open any board, open the Agent panel from the toolbar, and describe your goal in plain language. Not a technical prompt.

"Create on-body renders of these 6 sketches in 3 poses each, editorial style."

"Run a 12-color palette variation across these 4 base designs."

"Take this sketch to a full on-body pipeline across multiple poses."

The Agent confirms its plan, then starts working. And here's the part that changes everything: you don't have to watch it. Close the board, go to a meeting, go to bed. The Agent keeps running. Your outputs will be waiting when you come back.

‍

Run Up Multiple Tasks at Once

You're not limited to one workflow at a time. Each user can run Agent tasks concurrently in parallel.

Kick off your color variation workflow. Start your sketch-to-on-body pipeline. Begin a print recolor batch. All three running simultaneously while you keep working on something else entirely.

What used to take a full day of sequential work now happens in the background while you move on. The history dropdown shows you the status of everything at a glance: what's generating, what's ready to review, and what's waiting on your input.

‍

Your Whole Team, Running Agents Together

On a shared board, every collaborator can bring their own Agent. Multiple Agents from different users can work on the same board simultaneously — each running independent tasks, all outputs landing in the shared space.

Your entire team running parallel Agent workflows on the same board at the same time. That's what's possible now.

The Agent Gets Smarter the More You Use It

This is where it gets genuinely exciting for early adopters.

The Agent learns. Over time it builds a picture of how you work: your preferred render styles and finishes, how you like to sequence workflows, the kinds of outputs you approve versus refine. It learns your personal shorthand and gets faster and more accurate the more you use it.

At the organization level, it goes further. The Agent learns your brand's aesthetic and visual language, your signature color systems, your recurring workflow patterns, and what "good" looks like for your team's output standards. Over time it stops feeling like a generic tool and starts feeling like one that was built specifically for how your organization creates.

‍

Where This Is Heading

The Agent today is powerful. But it's also the foundation for something much bigger.

Imagine the Agent reviewing your collection and surfacing something like: "Cerulean is trending for F/W 27 but it's not represented in your collection today, want me to add a cerulean variation for you to review?" Trend awareness, gap analysis, and generation are all initiated by the Agent, not a brief.

Or imagine shortening the handoff to merchandising entirely: describe the callouts you want in a single prompt, and the Agent pulls from your materials database, builds the tech pack, and creates editable callouts ready for export. 

The teams using the Agent today are the ones shaping what those capabilities look like. And the ones whose workflows and brand knowledge it will already understand when those features arrive.

‍

Try It Free! All generations in Open Beta 

Agent is free to use during Open Beta, so your team can experiment with real workflows, run batch tasks, and help shape the product before general availability. Pricing will be introduced at GA, and details will be shared before billing begins. 

Try the Agent in Boards

Don't have a Pro or Enterprise account yet? Start a free trial on our pricing page.‍

Start Your Free Trial

‍

FAQ

Is Agent free?

‍Agent is free to use during open beta. Pricing will be introduced when Agent becomes generally available, and we’ll share details before billing begins.

‍Will I be charged during open beta?

‍No. Agent processing is free during open beta. If your workspace is already on the new pricing model, standard generation pricing may apply for agent-created outputs depending on your plan.

‍What happens at GA?

‍At GA, Agent usage will move to paid pricing. We’ll provide advance notice and clear usage details before billing starts. A notification will go out at least 2 weeks in advance of GA for teams to make any changes needed.

One More Thing: Meet Your Berry

When you use the agent for the first time, you'll be assigned one of 10 berry personalities, a small, expressive companion that reacts to what you're doing as you work. Purely fun, zero effect on your outputs. If you're a Jammy when you really feel like a Bramble, head to agent settings and swap anytime.