Staff Research Engineer at @GitHubNext. But actually a designer. Writes about design, dev, & anthropology. Also on Bluesky 🦋 @maggieappleton.com
London, England
Joined April 2013
- Tweets5.4K
- Following1.6K
- Followers44.3K
- Likes9.3K
Maggie Appleton retweeted
Stageshow: a skill that helps your agent make better faux UI stills, animations, bento grids, and more.
npx skills add benjitaylor/skills --skill stageshow
Maggie Appleton retweeted
GitHub Agentic Workflows has graduated out of the lab and is now generally available! We're excited to see more projects and businesses leverage AW to automate the things that could not be automated before AI.
github.blog/changelog/2026-1…
Maggie Appleton retweeted
The Origin Story of Github Copilot:
In 2020, @GitHub had just acquired my startup, Semmle, and the CEO, @natfriedman, gave me free rein to find our next product.
At the time, I had a bee in my bonnet: GitHub had more data than anyone else about developer behavior, but it wasn’t using that data to build new products.
I started exploring how to change that.
In June 2020, I got early access to GPT-3 and saw its potential to write code, especially if trained on the code on GitHub. It was the obvious project to work on.
It could generate a little code on its own, but almost always got it wrong. So I gave the model a set of 50 programming puzzles, the kind I used to set at Oxford entrance interviews.
I asked the model to solve each puzzle 1,000 times, using automated tests to check it. Given enough attempts, it got almost all of them right. That's when I knew it would be able to code.
I assembled a small initial team of ~10 people to work on what became GitHub Copilot. The first two people who joined were co-founders of the project: @thewunderalbert and @alexgraveley
Fortunately key people at OpenAI shared our vision, and it was the perfect partnership at the perfect time with @sama, @gdb, @ilyasut, @DarioAmodei and Sam McCandlish (months before Anthropic was born!), @npew and several others.
OpenAI trained the model behind it, Codex, and we built the product around it. It ran inside VS Code and suggested lines of code and functions as you typed.
The VS Code team, led by @ErichGamma, moved mountains to give us exactly what we needed. The Azure AI team of Misha Bilenko also helped make it scalable.
When we launched the technical preview in June 2021, it hit 1.2 million users in 12 months. It was an instant hit with developers and helped write billions of lines of code.
It also left me with an uncomfortable thought. The models had learned to code from public source code, and public source code has a lot of vulnerabilities in it.
It was easier than ever to write vulnerable code, and developers were shipping it faster than ever.
But, I knew that if AI could write the code, it could find the holes in it too. It was imperative that defenders got it before attackers did.
In 2023, I left GitHub to build @Xbow to do exactly that. Since then, we've already helped our customers find and fix more than 14,000 zero-days and the work has only just begun.
The same team that started the AI coding revolution is now leading the charge on AI security.
Maggie Appleton retweeted
Missed the closing keynote at GitHub Universe? You can see @Mappletons from GitHub Next demoing Chopin, our exploration of multiplayer planning for the agentic era
youtu.be/Gh-hg7lwA0o?si=Ys5q…
Maggie Appleton retweeted
What Maggie showed with Chopin is definitely where things are going next for me personally. I'm kinda building this workflow manually myself, but this has been formalized in a way that makes it collaborative and less scrappy. Very impressed!
ALT Maggie Appleton, wearing a red top and black pants, presents on a large conference stage at GitHub Universe. A massive curved screen behind her displays a screenshot of Chopin, an AI-powered collaborative planning interface featuring a conversation sidebar, detailed text, and a hand-drawn diagram comparing design tradeoffs. Colorful green, blue, and purple squares decorate the surrounding screen. The industrial venue features exposed steel ceiling beams, overhead stage lighting, and purple accent lighting along the stage.
GitHub Universe day one done!
If you’re here, come by tomorrow to chat to all the @GitHubNext folks at the Speakeasy section. We’re in white lab coats.
Also demoing some stuff in the final keynote.
I know I've been prompting my agents correctly when they present interfaces at the grammar, noun, and verb level. Took a lot of skill crafting to get here but god it's refreshing to work at the correct abstraction level and not like "my brother in christ why is this a modal?"
Mildly performative but very directionally correct.
In the sense of having a focused environment to deeply engage with the questions and decisions that matter, and not being drowned in tool calls and other irrelevant implementation details.
Maggie Appleton retweeted
If you have a front door, and aren't decorating for Halloween, I assume you either are elderly and infirm, overwhelmed with young kids, are undergoing some immense personal tragedy that forces you to neglect day-to-day things, or you don't understand the purpose of life.
okay this is actually funny to do
though only covers what I’ve said to my personal chatgpt account, not work agents who are separate and have been exposed to all my flavours of stupid
Maggie Appleton retweeted
The "design engineer" archetype in intelligence era needs be someone much further-reaching on both ends.
Beyond DESIGN,
a keener social intuition, a rich visual + tonal vernacular, broadly read, a deep understanding of people. They need to be deeply-feeling themselves, and not Maslow's 'existential zombies.' They need an investigative & suspended disbelief, but also a discernment and sanity to prevent psychosis. Far beyond just buttons + sliders. Much closer to a novelist or anthropologist.
Beyond ENGINEER,
a deep-seated intuition of machine intelligence: how they traverse latent space, what they can / cannot do well. A scientific approach to prodding this 'grown-not-built' intelligence. Far beyond just CRUD apps. Practically: ability to fine-tune + benchmark models, among other skills, to bridge machine intelligence to the more design/humanistic.
FWIW: all this is very good for a field — software design — that has recently (and rightfully) become the butt of jokes, and seen as a very unserious discipline
The trouble with crystallising your thoughts into solid form like this is you spent so much time marinating in the material that when you’re done you’re like “okay this is old news and I have 5 new theories, this is so backwards and passé”
(jk obvs good I love it)
New talk! About the divided human & agent worlds, boundary objects, and building thicker interfaces
I've been exploring how to improve "planning", aka. deciding what agents should build, how you want it built, & making the whole team part of that process
maggieappleton.com/planning-…
Okay I do have to say riding in Waymos in SF is actually a peak experience. I love these things. Plays your own Spotify music while you cruise around marvelling at the amount of engineering packed into this thing. Wild and beautiful.
New talk! About the divided human & agent worlds, boundary objects, and building thicker interfaces
I've been exploring how to improve "planning", aka. deciding what agents should build, how you want it built, & making the whole team part of that process
maggieappleton.com/planning-…
Visual choices like shadows are obviously bad in a text CLI but lots of problems are easier to solve with bespoke visuals
For example, how you want to handle refactoring retry logic is an easier decision w/ a visual of call sites and how easy each one is to replace.
