Designing with intelligence

Building a brand-aware AI assistant at Workable

Every company wants consistency. Every designer wants autonomy. And every slide deck wants to sabotage both.

Branded slide deck flirting with last minute changes

At some point in Workable Brand Design, we got tired of rebuilding the same layouts, reapplying color codes, rewriting intros, and hearing:

“Can you just brand this real quick?”

So we built something. Not a new Figma design system. Not a folder of templates. A custom GPT assistant.

Was this just a fancy wiki of our brand guidelines?

Even though our ambitious project started really quickly, using ChatGPT builder, it proved to be quite a lot more than a novelty project.

Preview of Workable Brand Assistant v.1.0

We trained our “Brand assistant” to understand our brand guidelines, voice, tone, hierarchy, pacing. We fed it logos, color palettes, icon libraries. We walked it through the logic of our design system: when to use a quote block, when not to center-align a paragraph, what a “callout” actually is.

The result? An assistant that applies brand logic, understands layout, voice, and structure. It wasn’t magical, just methodical. It could find information and resources about everything brand related and present it in an understandable manner to anyone that wanted help branding their projects. Apart from explaining our brand guidelines on demand, it could also suggest copy that was aligned with our tone of voice. But that felt like the easy part, ChatGPT is fairly good with text already.

So, we challenged ourselves. If it could do that… could it actually design? Could it maybe use real content in our Google Slides template and actually respect it?

Version 1: The Frankenbuild

We started scrappy. Using Make.com and a webhook in our ChatGPT build, we duct-taped together a system that worked! Any Workable employee could kickstart their Workable branded deck and get help filling it with relevant copy and images.

GPT webhook action and part of make.com blueprint

The happy user journey went like this:

1. User asks for help creating a deck
2. Assistant asks for more info on the presentation
3. User inputs the required info
4. Assistant mocks up the structured slides content, choosing graphics from a pool of images whenever needed and asks for approval
5. User asks for changes or approves presentation content
6. Assistant asks for permission to run the automation through make.com
7. User approves connection
8. Assistant confirms deck creation and informs user will receive it in their inbox.
9. User clicks inbox link and accesses the branded deck

[embed]Workable Brand Assistant built with ChatGPT and make.com in action

But it still was a pain for us designers to debug and a pain to use, too. The workflow was unstable, depended on a lot of services and required users to change environments to get their deck.

So we rebuilt.

The agent arrives

We migrated the assistant to n8n, turning it into an actual AI agent. We built it with conditional logic in mind, creating our own MCP server, smartly delegating tasks based on user input.

Instead of cobbling steps together, we created a system that can adapt. The assistant now handles both branded guidance and real-time generation of presentations without sending anyone to a different platform.

n8n AI agent and Brand MCP Server

The new happy path looked like this: User prompt → GPT logic → Deck logic → Google Slides export → Inline link

This helped us achieve:

• Faster performance (Selected an LLM that fit the specific need)
• Modular logic (The deck generator became a callable tool)
• Better debugging (n8n logging and error descriptions, even agent self-debugging were heaven sent)
• Better analytics (ability to log requests)
• Tool consolidation (no more multiple tool juggling)
• Better UX (Inline presentation link within chat)
• Ability to host anywhere (can build our own UI)

That last one, sent us vibe coding a custom UI for our Brand assistant, to make it even more… branded. We used Framer’s workshop to build it as a code component, and overlaid it onto our upcoming brand site. And it wasn’t just a simulated chat prototype. It was fully functional, linked to our assistant and complete with type animations and formatted answers.

[embed]Workable Brand assistant built in n8n with a Framer wrapper in action

Going beyond decks

Once the new workflow was stable enough, we felt invincible. We wanted to use the same AI agent for other tasks, like accessing our Figma design system and component libraries to export custom images based on templates. Why not make it intelligently pick an Instagram post layout based on user input and export it within our Brand assistant?

Figma MCP into the n8n workflow

So, we started experimenting with Figma’s new MCP to export components from Figma by triggering it inside the chat.

This allowed us to:

• Export design assets on request, not just fill in our servers with duplicate or obsolete assets
• Extend support to use cases like HR onboarding decks, sales enablement, and quick marketing kits

We got as far as exporting components. Injecting custom text is still a work in progress.

Agentic AI, minus the hype

The buzzword here is “agentic AI” for systems that act with embedded purpose instead of just responding.

This isn’t about automation for its own sake. It’s about giving the assistant enough context to operate as if it understands the system it’s working in.

You can say: “Here’s a product update.”

And it will return: “Here’s a branded deck with the right structure, tone, and formatting that makes sense.”

Not because it’s guessing, but because it’s been taught how to think in brand patterns.

A direction, not a product

Everyone wants to talk about what AI can do. But we’re more interested in what it can understand and how that changes the shape of creative work.

Right now, the assistant builds branded decks and gives guidance. That’s helpful. But how it behaves? That’s the interesting part.

This is a shift from static templates to living brand systems, ones that remember, adapt, and carry intention across teams.

Imagine:

• Helping teams stay on brand without micromanagement
• Cross-functional teams getting tone and voice guidance in the moment
• Surfacing design logic contextually, not buried in a PDF

This isn’t AI replacing designers. It’s AI keeping the annoying stuff from breaking the good stuff.

Internal reception: quiet, useful, and (almost) invisible

When we shared it internally, the sky didn’t part. No viral threads. No standing ovations. Just a few nods and a few “can it also…?” messages. Some early adopters were discouraged by early bugs. Some others asked if they could build something like that for their own teams, finding the value behind the geekiness.

It’s not perfect. But neither is any real creative system. Templates alone aren’t scalable. Design systems don’t teach themselves. And teams are tired of opening a 92-page brand PDF to figure out if their quote block is legal.

What matters is building tools that understand your brand deeply enough to reduce the noise, so your focus can go where it actually matters. This assistant filled a gap most design systems don’t even acknowledge. The quiet, daily collapse of consistency.

And that alone was worth building.

I trained an AI to follow my brand guidelines. Now it’s asking me to revise my tone. Fair.