Derek Briggs

Their words

It's really important to me that folks are not using AI to do 10 times more work. It's important to me that it's making them 10 times better.

Their words

I'm a big believer that we need to stop treating today's LLMs the way that we treated yesterday's LLMs because it's just really good at doing what you want without asking too much of it.

Their words

Because I am a big believer that, like, the most important piece of context that you have is your codebase. And if you just let it continue to evolve itself and sling things in there from various different models doing various different things, I think that you're going to get into a world of hurt eventually.

Their words

I think people need to be ruthless around knowing and being confident that the solutions that they're designing and shipping are meeting the goals that they set out to achieve. If you're shipping something without any sort of data around its success, I don't understand how you'll be able to know if what you did was the right thing for the company or not.

Their words

I think that that role is still maybe the most important role out there right now. Somebody who can truly bring the vision to life from a code perspective

Their words

I think companies are wasting their time if they're trying to hire tons of these people to be responsible for all these areas when you can very horizontally deploy them through Markdown files.

Their words

I think it's incredibly critically important to deploy taste and craft and quality and knowledge around what tools we need to use and what strategies we need to use to achieve the level of quality we're looking for. We need to document those in just simple markdown files of how I'm approaching this, what I'm doing, and here's the outcome. So that those skills can then just be deployed through our skill packages throughout our designers and our engineers to where greatness accidentally happens.

Their words

But right now in this era, I think designers even more should really own what the quality of output is rather than relying on their agents to, to determine what the quality is.

Their words

I think that designers need to spend some more time on the artboard at times. I think that there's a lot of prompting happening that just results in what an agent will do for you.

Their words

Agents are capable of doing what they've learned to do, and innovation happens in what has never happened before. So it's very difficult, and my personal opinion is it's very difficult to innovate in design with AI, being that it's only ever going to present what has happened before when we're trying to figure out what's going to happen in the future.

Their words

You might not be able to say what looks different, but you can see that it looks different. And I think the key factor is what makes a good designer a great designer is being able to tell you what the difference is.

Their words

I think teams can invest too quickly in design systems, both in Figma and in code. There are a lot of early decisions that get made that are easy to either overthink or over-optimize. And the way that we have approached it is kind of designing for what we need at that time. Reusing that design or component a few times before codifying it, especially in code.

Their words

I have a big issue with deadlines. Setting a deadline is going to either allow the person to stretch out that amount of work over that period of time or have to eventually de-scope the project to be able to meet that arbitrary deadline.

Their words

I say all the time that the users never see the Figma files. Like, your design quality and your design capabilities of your team is only as good as the UI engineers that are implementing it.