Building agent memory that survives between sessions
Two practical approaches to the same insight: memory is a design problem, not a tooling problem.
Category: Ai
All CategoriesActually, people love to work hard
When effort stems from purpose, agency, and trust, rather than oversight.
The building block economy
How "building blocks" thrive by letting AI and niche users handle the customization.
My picture of the present in AI
A scenario forecast, but for the present (which is already uncertain) rather than the future.
AI fatigue is real and nobody talks about it
You’re using AI to be more productive. So why are you more exhausted than ever? The paradox every engineer needs to confront.
Bernie vs. Claude
Speaking to Anthropic’s AI agent Claude about AI collecting massive amounts of personal data and how that violates our privacy rights.
Craft is untouchable
AI doesn’t threaten craft—the temptation to skip iteration does.
The machines are fine. I’m worried about us.
On AI agents, grunt work, and the part of science that isn’t replaceable.
Designers finally have a say in the product they design
AI didn’t teach designers to code. It gave them back the decisions that were always theirs.
AI Interaction Atlas
Comprehensive reference for designing AI experiences. 100+ patterns, visual examples, and reusable components.
AI prototyping tools: why control matters as much as speedSponsored
Most AI tools optimize for speed. ProtoPie AI is built for validation. Here’s why that matters for design teams working at a professional level.
The beginning of programming as we’ll know it
Is the human role of “computer programmer” coming to an end? Will the AI bots one day do all the programming for us?
What if AI just makes us work harder?
More multitasking. AI introduced a new rhythm in which workers managed several active threads at once.
The ground is shaking: Why designers must flip the script on AI
Something has shifted in the way the design field operates, and we haven’t yet found the words or identified the exact schema for it.
A mirror test for LLMs
In which we propose a new measure of LLM self-awareness but ultimately decide they fall short.
Your ticket is a prompt
The instinct to break work into atomic tickets was right for human teams. For agents, it reproduces the same fragmentation disease at machine speed.
The first 40 months of the AI era
Accumulated thoughts and ideas about AI since the launch of ChatGPT in November 2022.
Why are executives enamored with AI but ICs aren’t?
Executives have always had to deal with non-determinism, while individual contributors are evaluated by their execution on deterministic tasks.
AI agents could make free software matter again
Free software once mattered deeply, but faded when SaaS made those freedoms feel irrelevant.