#human-computer-interaction
64 episodes
#5233: One Tap Beats Eight Links: Designing a Digital Business Card
Most digital cards fail in ten seconds. Here's the design that actually starts a conversation.
#5160: Bluetooth Peripherals on One Android Phone
How many Bluetooth devices can one Android phone juggle? The seven-device limit is a stack artifact — profiles matter more.
#5158: A Pulse Oximeter Said 97%. That Was the Problem.
A reassuring oxygen reading can hide a child in respiratory distress. Here's what home devices actually tell you — and what they can't.
#4813: The $70 Mouse That Changed Everything
How a $70 ergonomic mouse purchase reveals the quiet way we learn to trust AI.
#4700: Browser Agents: Three Paths to One Protocol
How screenshot watching, dev-tools extensions, and native MCP in Chrome are converging — and what wins.
#4691: The Machine Lane: When AI Agents Call Your Business
What if your business phone menu had a button for AI callers? The search for who's building it — and why nobody has.
#4586: Fixing Stale UI: The 4-Link Chain of Data Flow
Why does a number on screen stay frozen after an upload? We trace the 4-link chain from response to redraw — and where it breaks.
#4568: Building a Smarter Text Expansion Library
Move beyond addresses and signatures — build snippets that shape how you think, decide, and communicate on mobile.
#4469: The Missing Protocol for AI Software Development
No one has built a software development protocol designed for AI agents. Here's what that would require.
#4443: Terminal Navigation Beyond cd: Favorites, Recents & Agentic Workflows
Why cd isn't broken — our spatial memory is. A tour of zoxide, broot, and what's missing for power users.
#4374: How AI Agents Finally Made the Terminal Accessible
How Claude Code removes the memory tax that kept neurodivergent users from living in the terminal.
#4340: Building an AI Tutor That Teaches You to Code Without Writing It For You
How to build an AI tutor that assigns projects, reviews code, and remembers what you've learned — without writing your code for you.
#4289: Spreadsheets vs. SQL: Is the Grid Dying?
Airtable's AI agent just collapsed the usability gap. Does the spreadsheet still have a purpose?
#4179: Why Your Phone Number Link Is Costing You Customers
That non-clickable phone number on your site is quietly bleeding leads. Here’s the five-minute fix.
#4157: Prompt Engineering Is a Misnomer — Managing Ambiguity in AI
Why the best AI outputs come not from tighter prompts, but from knowing where to leave room for surprise.
#4122: Why No AR App for Infant CPR?
A parent at 2AM needs visuals, not a PDF from 2014. Why doesn't the app exist?
#3835: Slack's Accidental AI Agent Superpower
The tool that failed to kill email is now thriving as the notification backbone for AI agents. Here's why.
#3718: AI Babysitters Already Exist—What We Learned
Tens of thousands of Chinese families already use robot babysitters. What actually happened, and what's next?
#3221: Why Can't Your Partner Reach You? The Family Pager Problem
Smartphones have no reliable urgent notification channel for families. Here's why — and what might fix it.
#3198: Why Architects Still Use 1963 Pens
Why architects still use isographic pens and parallel rules in 2026 — and what that teaches us about thinking through our hands.
#2592: The Market That Never Went Away
From IBM terminals to Stream Decks — how macro keyboards evolved under the radar for decades.
#2577: Fixing Hidden UI Bugs on Real Devices
Tools and strategies to catch layout failures across devices before users abandon your app.
#2567: Beyond Pixels: Controlling Apps Without Vision
How MCP agents can use accessibility APIs and COM to control Windows and macOS apps at the protocol level.
#2558: Should You Say Please to AI?
The surprising cost, technical tradeoffs, and ethical dilemmas of saying "please" to chatbots.