Very cool! Can I recommend improving the semantics/accessibility of the HTML? Would be nice to encourage good practice.
Very cool! Can I recommend improving the semantics/accessibility of the HTML? Would be nice to encourage good practice.
What if teams could comment and compare vibe coded interactive prototypes, and the comment stored the state of the prototype when the comment was made?
Demoπ
Properly educating the next generation of developers is one of the biggest challenges for our industry today.
Is your org teaching junior devs? What do you think is working? What isnβt?
I've seen multiple companies recently adopting a "teaching hospital" approach for their developers. New developers are "interns" (not juniors) and a developer educator (i.e. in-house mentor) is a position in the company.
The industry needs *more* of this approach.
Blog post: tonyalicea.dev/blog/trace-d...
GitHub: github.com/anthonypalic...
I'm pleased to present Trace, a markdown-based declarative modeling approach to spec writing for LLM consumption.
It's designed both for experienced devs and to give new devs a focus on *what* to learn (thinking in systems) in the age of AI.
Blog post and GitHub repo: π
You can teach an LLM the technique, and use it to iterate on your prototypes (Figma, vibe-coded, etc.).
Read the book free here: dontimitate.dev/normalui
Let me know what you think!
I'm making my book Normal UI free to read online! The book is the result of decades of UX work and thousands of usability tests.
It's a simple technique that any designer or developer can learn that improves the usability of software applications. π
AI canβt replace humans period. You need humans to educate. But I think computers and AI can be an engaging canvas for good instructors to build learning experiences around.
Having students sit and just βlearnβ from chatting with AI is foolish though.
An AI computer chip with a graduation cap. Next to it says "The Future of Self-Paced Online Education by Tony Alicea".
What is the future of self-paced education in the age of AI? I've been experimenting with designing LLM-based learning experiences from the ground up, and wrote up my thinking on what I'm calling a Learning Surface.π
PMs who vibe code their PRDs into prototypes should be clear that it is an expression of "what" not "how". A communication tool.
PM-generated prototypes should not become an excuse to skip the work of UX designers. That's a danger, and one mature teams do well to avoid.
Status: recording this week a series of lectures on Agent Skills.
They will be added free to my AI-Assisted Dev course and also be released as a short standalone course on Udemy.
If you arenβt writing and using Skills for your agent, you should be.
Saying code generation removes the need for software engineers is like saying self-driving cars remove the need for roads.
Don't create AI slop. Find the points in your creative process that LLMs can optimize.
Keep your voice, your thoughts, your reasoning, your unique perspective. Give AI your boilerplate, your point-and-click, your drudgery, your tedium.
Beat AI slop with efficient quality.
I'm a fan of Figma and FigJam and have courses on them. You can Figma for getting your design system together.
But these days your team should be spending more time vibe coding throwaway interactive prototypes, getting real research data and iterating rather than pushing pixels.
I now have a course for this! www.pluralsight.com/courses/intr...
I'm so excited to announce a brand new course on
@pluralsight.bsky.social, Introduction to MCP!
This isn't a coding course, but a conceptual one, ensuring you understand what MCP actually is and how it works, so you can use it to your best advantage. π
Yawning emoji with the text "Dev to Lead to Architect: Losing the Joy of Coding".
New podcast episode just dropped! In the age of LLMs some devs are losing the joy of coding. How can you motivate yourself and your team while using LLM generation?
No release of any new LLM model will change the fact that you need to understand what you're doing as a developer.
Your dev team should be standardizing on Skills, not just for providing tooling to an AI, but to package domain knowledge.
An artifact from the requirements process should be a Skill for the business the software is supporting, and it should be shared with the entire dev team.
I'm a unicorn. I do full-stack dev *and* deep UX / design / usability work.
AI blurs the UX / dev line. Designers who learn some coding can supercharge their vibe coded prototypes. Devs who learn a bit of UX design can build better apps.
Should you learn to be an AI unicorn?
I am quietly looking for a position in UX or DevRel/DevEx to add the value of my 25 years as a full-stack dev, bestselling dev educator, UX designer and researcher, and conference speaker.
If you know of a good fit, feel free to DM me.
It's the last couple of days to get my new AI-assisted development course at early-access price. New modules are dropping soon and the course will be finished up in February.
It's something different - a core mental model that we use to build good practices.
Remember that AI doesnβt feel the pain of past architectural choices. But you will.