Purpose

Purpose

Can a tiny control deck measurably speed up interface design—and become a bridge to agentic work?

Can a tiny control deck measurably speed up interface design—and become a bridge to agentic work?

Purpose

Can a tiny control deck measurably speed up interface design—and become a bridge to agentic work?

A two-week comparison in Figma became a broader lesson about designing better interfaces for human—and agentic—work.

A two-week comparison in Figma became a broader lesson about designing better interfaces for human—and agentic—work.

Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur?

Aisha’s question made me realize that my first automation secret was not really about AI. It was about reducing the distance between an idea and an action. The Work Louder Micro became a compact physical interface for the commands I use constantly, so the software could disappear and the design decision could stay in focus.

One small deck, three generations of automation.

I learned that lesson in 2023–24 while working in Figma. My layout put pencil and component controls at the top; alignment and distribution across the middle; select and comment at the bottom. A black knob handled content scrolling, while the vertical wheel adjusted integer values such as type size. The arrangement mirrored the way I actually designed.

Grey placeholder 01 — replace with article artwork.

Aisha’s question made me realize that my first automation secret was not really about AI. It was about reducing the distance between an idea and an action. The Work Louder Micro became a compact physical interface for the commands I use constantly, so the software could disappear and the design decision could stay in focus.

One small deck, three generations of automation.

Grey placeholder 02 — replace with article artwork.

Aisha asked how I combine AI and design. My first secret starts with the Work Louder Micro.

Aisha’s question

Grey placeholder 03 — replace with article artwork.

Using the Micro with Figma in 2023–24 showed me how much time small, repeated actions consume.

Daily practice

Grey placeholder 04 — replace with article artwork.

I mapped drawing, alignment, selection, comments, scrolling, and number adjustments to one compact Figma control surface.

Figma shortcuts

Distribution of daily completion time, comparing design work without and with the control deck.

On matched design days, average completion time fell from 4.00 to 3.65 hours: 21 minutes saved daily.

Measured gains

Normalized task completion over active design time, comparing work without and with the control deck.

The same tasks finished sooner, with fewer interruptions and less cursor travel. The completion curve confirmed it.

Less friction

Drag to explore →

Once I saw the time compound, I looked for the next recurring time sink. My personal website was collecting dust because it was hard to update, so I built a Framer layout for the Micro and turned publishing steps into dedicated controls. I even made custom keycaps, including a tiny yellow duck. When the Work Louder and OpenAI collaboration was announced, the idea clicked into its next form: physical controls could initiate, steer, and review agentic design work while keeping a human in the loop.

Estimated daily time savings by control: vertical wheel, alignment, black knob, tool modes, and distribution, totaling 21 minutes per day.

To test whether the speed was real, I held the interface workload constant across two five-day blocks. The comparison moved average completion time from 4.00 hours without the Micro to 3.65 hours with it. That is 21 minutes saved per day—an 8.75% reduction—with the same amount of design work completed. Extended across the same schedule, that becomes 1.75 hours per week, about 7.6 hours per month, and roughly 91 hours per year—more than eleven eight-hour workdays.

Work Louder Micro — the programmable control deck used in this workflow.

01

Figma — the interface design environment used for the matched-workload comparison.

02

Hinckley et al. (2014), “Touch-Level Model (TLM): Evolving KLM-GOMS for Touchscreen and Mobile Devices,” CHI 2014.

03

Loop

The design-forward AI newsletter.

Keeping humans in the loop.

Open Menu

Can a tiny control deck measurably speed up interface design—and become a bridge to agentic work?

A two-week comparison in Figma became a broader lesson about designing better interfaces for human—and agentic—work.

A two-week comparison in Figma became a broader lesson about designing better interfaces for human—and agentic—work.

Work Louder Micro — the programmable control deck used in this workflow.

01

Figma — the interface design environment used for the matched-workload comparison.

02

Hinckley et al. (2014), “Touch-Level Model (TLM): Evolving KLM-GOMS for Touchscreen and Mobile Devices,” CHI 2014.

03

I learned that lesson in 2023–24 while working in Figma. My layout put pencil and component controls at the top; alignment and distribution across the middle; select and comment at the bottom. A black knob handled content scrolling, while the vertical wheel adjusted integer values such as type size. The arrangement mirrored the way I actually designed.

Grey placeholder 01 — replace with article artwork.
Grey placeholder 01 — replace with article artwork.
Loop

The design-forward AI newsletter.

Keeping humans in the loop.

Grey placeholder 01 — replace with article artwork.
Grey placeholder 01 — replace with article artwork.

I learned that lesson in 2023–24 while working in Figma. My layout put pencil and component controls at the top; alignment and distribution across the middle; select and comment at the bottom. A black knob handled content scrolling, while the vertical wheel adjusted integer values such as type size. The arrangement mirrored the way I actually designed.

Grey placeholder 04 — replace with article artwork.

Figma shortcuts

I mapped drawing, alignment, selection, comments, scrolling, and number adjustments to one compact Figma control surface.

Distribution of daily completion time, comparing design work without and with the control deck.

Measured gains

On matched design days, average completion time fell from 4.00 to 3.65 hours: 21 minutes saved daily.

Normalized task completion over active design time, comparing work without and with the control deck.

Less friction

The same tasks finished sooner, with fewer interruptions and less cursor travel. The completion curve confirmed it.

Grey placeholder 03 — replace with article artwork.

Daily practice

Using the Micro with Figma in 2023–24 showed me how much time small, repeated actions consume.

To test whether the speed was real, I held the interface workload constant across two five-day blocks. The comparison moved average completion time from 4.00 hours without the Micro to 3.65 hours with it. That is 21 minutes saved per day—an 8.75% reduction—with the same amount of design work completed. Extended across the same schedule, that becomes 1.75 hours per week, about 7.6 hours per month, and roughly 91 hours per year—more than eleven eight-hour workdays.

Estimated daily time savings by control: vertical wheel, alignment, black knob, tool modes, and distribution, totaling 21 minutes per day.
Estimated daily time savings by control: vertical wheel, alignment, black knob, tool modes, and distribution, totaling 21 minutes per day.

Once I saw the time compound, I looked for the next recurring time sink. My personal website was collecting dust because it was hard to update, so I built a Framer layout for the Micro and turned publishing steps into dedicated controls. I even made custom keycaps, including a tiny yellow duck. When the Work Louder and OpenAI collaboration was announced, the idea clicked into its next form: physical controls could initiate, steer, and review agentic design work while keeping a human in the loop.

Figma — the interface design environment used for the matched-workload comparison.

02

Hinckley et al. (2014), “Touch-Level Model (TLM): Evolving KLM-GOMS for Touchscreen and Mobile Devices,” CHI 2014.

03

Work Louder Micro — the programmable control deck used in this workflow.

01

Work Louder Micro — the programmable control deck used in this workflow.

01

The design-forward AI newsletter.

Keeping humans in
the loop.

Loop

Aisha’s question made me realize that my first automation secret was not really about AI. It was about reducing the distance between an idea and an action. The Work Louder Micro became a compact physical interface for the commands I use constantly, so the software could disappear and the design decision could stay in focus.

One small deck, three generations of automation.

One small deck, three generations of automation.

Aisha’s question made me realize that my first automation secret was not really about AI. It was about reducing the distance between an idea and an action. The Work Louder Micro became a compact physical interface for the commands I use constantly, so the software could disappear and the design decision could stay in focus.

Grey placeholder 04 — replace with article artwork.

Figma shortcuts

I mapped drawing, alignment, selection, comments, scrolling, and number adjustments to one compact Figma control surface.

Distribution of daily completion time, comparing design work without and with the control deck.

Measured gains

On matched design days, average completion time fell from 4.00 to 3.65 hours: 21 minutes saved daily.

Normalized task completion over active design time, comparing work without and with the control deck.

Less friction

The same tasks finished sooner, with fewer interruptions and less cursor travel. The completion curve confirmed it.

Grey placeholder 03 — replace with article artwork.

Daily practice

Using the Micro with Figma in 2023–24 showed me how much time small, repeated actions consume.

To test whether the speed was real, I held the interface workload constant across two five-day blocks. The comparison moved average completion time from 4.00 hours without the Micro to 3.65 hours with it. That is 21 minutes saved per day—an 8.75% reduction—with the same amount of design work completed. Extended across the same schedule, that becomes 1.75 hours per week, about 7.6 hours per month, and roughly 91 hours per year—more than eleven eight-hour workdays.

Estimated daily time savings by control: vertical wheel, alignment, black knob, tool modes, and distribution, totaling 21 minutes per day.
Estimated daily time savings by control: vertical wheel, alignment, black knob, tool modes, and distribution, totaling 21 minutes per day.

Once I saw the time compound, I looked for the next recurring time sink. My personal website was collecting dust because it was hard to update, so I built a Framer layout for the Micro and turned publishing steps into dedicated controls. I even made custom keycaps, including a tiny yellow duck. When the Work Louder and OpenAI collaboration was announced, the idea clicked into its next form: physical controls could initiate, steer, and review agentic design work while keeping a human in the loop.

Open Menu