Product designer and builder.
Nashville, TN
Joined April 2007
- Tweets981
- Following1.1K
- Followers1.3K
- Likes10.3K
This presentation by @lil_dill had me at Korean BBQ. Well worth the watch.
youtube.com/watch?v=GLvFTMtw…
Learned about Whimsical last night while watching @ridd_design interview @pablostanley (who has a nice honest take on the state of design today).
Seems like a great product for those of us that do a mix of product management and design work.
whimsical.com/
This had me at:
Three features.
None of them useful.
froppi is free this week
a frog that lives on your mac desktop. climbs, falls, eats flies, naps. does nothing useful
free till nov 7
apps.apple.com/us/app/froppi…
Geoff Alday retweeted
A wild scrolling experience exploring what the job of the Human (designer) is in the era of AI.
human-md.ai is worth a scroll and may even have you laughing at times.
Geoff Alday retweeted
Every week, there's a new THING to talk about.
AI, workflows, tools, job hunting, the state of something or other... and that's great. I love keeping up with all of it.
But sometimes, I want to talk about balance.
And I want to hear from you how you're dealing with it.
About how you're balancing the obligations of paying bills while creating work that means something to you.
About how you manage family with work. Company mandates with your team's health.
What is working for you?
Next Thursday, @ridd_design and I are dedicating an episode to this. To people and the reality of what all of this costs (and affords).
We'd love to hear from you. Please consider it.
Geoff Alday retweeted
Building a couple different apps right now. A few things that are really fun and different:
• New input methods! It used to be UI was only type, click, upload file, etc. Now "hold a button to explain what you want" is a thing. Or "show to the camera."
• New cogs in the backend! Basically LLMs are magical cogs we can insert into backend processes to enable new things to happen.
• Cover more creative ground! Every time I'm scratching my head I can ask for multiple takes on this one thing and get new ideas.
And the best part -- the hard parts are still hard! It's all about how to integrate these new things together into a workflow that actually solves problems!
Geoff Alday retweeted
Every design system I keep has a visual version I look at and a markdown version my agents read.
If I need to change a token I'm just gonna type it.
Two predictions based on convos:
1. Designers are gonna end up with their own personal design system and pull the refined components into every AI project
2. Design teams are going to hire design engineers to enable XFN partners to achieve the quality bar with their agents
I want to hear from you:
If you're on a bigger team, DM me what you're actually doing and seeing for Thursday's Dive Radio live stream.
@ridd_design and I are going deep on how design systems are evolving at 1PM Pacific.
Short video that explains and shows off this little Mac desktop toy I made.
youtube.com/watch?v=NlfideF4…
Made a little Mac desktop toy: Plink Break 🎯 Shoot pixel-art holes in your desktop, or knock down carnival targets. Looking for feedback and bugs!
Free for macOS 15+: github.com/geoffalday/plink-…
'... we don't need to gatekeep what "design" is ...' 💯
I want to be snarky so badly.
But instead I'll say - could it possibly be that both sides definition of design is too narrow and myopic for this very wild world we're in.
AND just maybe we don't need to gatekeep what "design" is because some are uncomfortable with a process that doesn't involve a canvas?
Geoff Alday retweeted
A solo dev spent a year writing a Direct3D 12 engine from scratch so the CRT would be physics, not a shader
- You are the King's Surveyor lost far from home
- Map a valley & study what its makers left behind
- Use your torchlight wisely to get home
Game is The King's Surveyor.
Made a desktop toy yesterday. Have a few ideas about where to take this. Curious about other ideas though.
Color me impressed. AI one-shots can be really good with the right context.
This week, I wrapped the design for a new greenfield project. We’re building it with AI-DLC, a development process from AWS that gives structure to how AI fits into the development lifecycle.
Next up: requirements for Inception, the first phase of AI-DLC. I started with a colleague’s template and filled in about half from my own knowledge of the project. Then, in Cursor, I pointed Opus 5.5 (High) at it with this prompt:
“Would like to create a copy of this doc [redacted].md and populate with relevant information from this vision doc [redacted].pdf. I also have the designs for this new product in Figma on this page: [redacted]”
Cue the mechanical whirring sounds I like to imagine. Minutes later, in one shot, the requirements doc was populated accurately.
But it wasn’t magic. I’d spent real time organizing the Figma file, naming every screen by its place in the information architecture, its purpose and state, and its intended user. When every prompt has a price tag, good context isn’t a nice-to-have. It’s the cheapest optimization you’ll ever make.
Anyway, the robots are ready when you are. Your “Frame 427 copy 3” might not be.