2026-10-20 22:00:00
The Ask LukeW feature on my website has been answering people's questions about digital product design for over three years. How well it answers depends on the content available to it. So in addition to improving content retrieval recently, I've also improved content indexing: a key part of making personal AI work.
Before any of my articles, presentations, or files can be used to answer people's questions, they need to be cleaned up and turned into a format that makes semantic search possible. This happens through a content ingestion pipeline, which I had to kick off manually for every piece of new content.
Now the system automatically checks for anything new or changed each hour. Audio, video, PDFs, and images it finds get queued, processed in the background, and added to the corpus. How that happens depends on the types of content.
Audio and video files get transcribed into text spelling out what was said and who said it. The service doing this recognizes my voice so it can consistently label me in each transcript. An AI model then reads the transcript and generates a title, summary, list of topics, and date if it can find one in the text. Each transcript gets split into distinct passages so an answer can reference the exact moment in a talk where I said something, and you can jump straight to it in the embeddable video and audio players.
PDF files get read by a vision model that not only extracts all the text but also describes charts and diagrams in words. Since many of my presentation slides are visual, this process matters a lot. Each PDF page is individually saved so answers can show slides inline resulting in less walls of text.
Of course, images help with that as well, so an AI model analyzes each new image added, describes what's in it, and uses my captions as additional context if the image appears in a blog post.
That's all well and good, but I'm not writing that many articles and definitely not giving enough talks to keep content recent and relevant. Thankfully, there's Twitter (X now) and I've posted there nearly 20,000 times since 2008. Damn, I need hobbies.
Despite the volume, none of those tweets were available to Ask LukeW. Now when I post, X notifies our server which pulls in the full post or deletes it if I had a half-baked idea that I removed. Older posts were added through a one-time import though I skipped replies to other people, reposts, and anything linking to lukew.com (that content was already there).
For each post, shortened links are expanded so the text reads naturally, and quoted posts are included for context. Any photo, video, or GIF also gets described by an AI model.
So why does all this matter? Making content ingestion automatic, especially Twitter/X posts as they happen, allowed me to start the Ask LukeW experience with an answer vs. requiring a question. Which addresses one of the most challenging bits of AI products: knowing what they can do. Plus Ask LukeW answers are now better because they have more content to draw from. So that's cool.
2026-10-17 22:00:00
Several years ago I read Jeff Hawkins’s A Thousand Brains, which dug into his theories on how our brain works. In it he argued intelligence comes from thousands of cortical columns that each learn their own model of the world and then vote to reach agreement. Then AI engulfed the tech world, and along the way I kept finding myself thinking about Jeff's theory.
How Jeff described our brains and how today’s AI models are built seem to have a lot of parallels. Specifically, a common set of building blocks for intelligence. How so?
Hawkins estimates the part of the brain that handles seeing, hearing, language, and thinking contains about 150,000 cortical columns. Each of these columns effectively runs the same program on nearly identical biology. But they differ in what they're connected to (eyes, ears, fingertips). Each column learns things by combining what it senses with where it senses it.
For example, you learn the shape of a coffee cup in the dark when you touch the rim here and the handle there. Hawkins claims the same process works for everything we learn, even math. In addition, cortical columns work together by sharing their guesses until they agree on what’s there. That’s why you recognize the cup faster by grabbing it with your whole hand.
The Transformers architecture behind many of today’s AI models is also built from a repeated block. It handles text, images, audio, and video once they’re broken into tokens. Each token carries a “what” (the word “cup”) and a “where” (third token in the sentence). An attention mechanism lets each token look at the others and work out how the pieces fit. It's kind of like the brain's voting between columns. Many tokens share information to settle on one interpretation.
During training, language models improve by predicting what comes next and adjusting after wrong guesses. This seems to mirror how Hawkins says the brain learns from surprise. But while Transformers learn most of what they know during training, cortical columns keep rewiring themselves as they experience the world. AI researchers are working on models that keep learning after deployment too.
So in both our brains and AI, intelligence may come from one building block, repeated many times and shaped by experience. Of course, that's at a high level and lots of details differ. But the similarities do make me think about intelligence of both types differently.
2026-10-09 22:00:00
After seeing lots of posts over the years arguing that design has become homogenized, I decided to pull together historical and modern designs for a few different product categories: TVs, phones, cars, etc. You don't have to squint to see the pattern... but why?
Do we eventually reach a final form? Does everything just trend toward average as mediocrity seeps in? Is it driven by what's possible or cost-effective in the supply chain? Or does everybody just copy everybody else? Here's the reasons I see people argue most often.
Once a product's purpose becomes clear, design can get out of the way. A TV is for watching a picture, so the ideal TV is mostly picture. Same for smartphones, cash registers, etc.
The more mature a technology, the more it competes on price and specs. Standing out is risky and expensive so less companies do it. The ones that do tend to be smaller so they have less resources and reach, making it hard to go beyond niche markets.
Nature does it too. Crustaceans keep independently evolving into crab-like shapes: a pattern we call carcinisation. Someone suggested the consumer product version should be called "crabitalism".
Aerodynamics, thermals, and materials push cars and planes toward the same shapes. Constraints do the same. Planes are designed around airports, and cars around safety standards. Change the job (an F1 car, a fighter jet) and the design changes with it.
Software is even more susceptible. Every app is already being chat-ified (video below) even though we're only a few years out from ChatGPT's release. Hardware convergence often took decades.
On that note, AI hardware is currently a bunch of experiments: pins, glasses, earbuds, and even pendants. We'll see which of them (if any) make it into the right-hand column, but for now it's a design playground.
2026-10-05 22:00:00
In today's AI-powered software, you manage agents, they manage more agents, and those agents manage even more agents. Chat threads break with that scale. We need to know what agents are planning, what they've already done, and how best to steer them. In other words we need different ways of seeing things.
When most people think about staying on top of agent activity, they jump to management views: an inbox like those found in Slack and email; a dashboard like those found in monitoring apps. Effectively these answer the question "what are my agents doing right now?"
I took a look at inboxes, Kanban boards, task lists, dashboards, and calendars in a post last year about agent management interface patterns. But while these kinds of agent views currently get all the attention, more specific and dynamic views may actually be more useful.
That's why in Intent, our large scale agent coordination tool for developers, we've built in multiple ways to see what's going on. Intent lets you create any number of documents (we call them notes) when working on a task, so you can have the specific views you need when you need them. A few examples:
Agents can draw architecture maps, flowcharts, sequence diagrams, and state machines inside notes and chats so you know what they are planning to do, and how, before spending the tokens.
Stepped walk-throughs move you through a diagram one stage at a time, each with a short explanation and the relevant parts highlighted. This not only makes plans easier to follow but also helps you quickly understand the current state of things. Boxes that reference files or notes open them when you click so can go deeper if needed.
Agents can take before and after screenshots of their UI changes and place them side by side in a note letting you judge results without reading any code. These notes can update with each change or stick around as a historical record. Agents in Intent can also pin a screenshot to show progress at a glance.
A app or website's design system can also be viewed as a note: colors, type styles, spacing, corner rounding, animation timings, and components with their variants, all in one place. Keeping a view like this open while you work makes "which padding?" one glance away. Agents read the same notes, so their UI work lines up with your references.
Of course, lots of views aren't much help if you can't set them up in a way that's useful. Every panel in Intent can hold a stack of agents, notes, files, terminals, and browser tabs. Drag things between panels, drop one on an edge to split off a new panel, and zoom any panel to full screen if you need focus.
Yes, chat still has a place for kicking off, moving along, and redirecting work. But as agents keep multiplying, a configurable workspace of useful views goes a long way toward steerings thing toward the outcomes you want.
2026-10-01 22:00:00
For as long as I've been working on design systems (20+ years, oof!), I've seen the same pattern play out... design teams invest a lot of time in creating a system, then struggle to keep it up to date as the actual product evolves. Inevitably the design system ends up describing a product that no longer exists.
The most common way to address this was to throw more resources at the problem: design system teams and/or centralized design reviews. But now, AI agents give design systems a different path forward. When agents write most of the code, the design system can become part of what I've called the AI steering layer: the context that keeps every website update aligned with brand, design, and development guidelines. Put simply, a design system for agents is a steering layer for a site's design and front-end code.
With AI agents, anyone on a team can update a website. Marketing adds landing pages, engineering adds docs, a PM tweaks the pricing page. Each of their agents will happily implement its own tone and voice, colors, spacing, etc. unless something steers them toward a unified whole.
That's the case for collaborative steering. A design lead and front-end lead define the grid, fonts, colors, spacing, and components once, and everyone's agents are "snapped to" it. The team keeps shipping and the site keeps its integrity. So what does that look like in practice? Here are a few examples from our recent projects.
On the Intent website, an AGENTS.md file tells AI agents to reuse the theme classes and CSS variables in the site's global stylesheet instead of duplicating color, typography, or grid values. That stylesheet defines colors, fonts, type sizes, the responsive grid, and light and dark themes as design tokens (named values the whole site shares). A design system page shows it all as live examples agents can inspect.
When someone asks an agent to add a new button, it reuses the existing Button component and its styling, which also adapts to dark mode automatically. And no human has to look anything up.
Intent's design system started from Figma specs that were automatically translated into code using a Figma MCP connection. After that, the code itself became the source of truth and was updated with a new body font, responsive layouts, dark mode, and more as the site evolved. We've even had agents write changes back to the original Figma files. But since the code is the source of truth, that hasn't been necessary in practice.
Sol and Aria's websites follow the same approach (links go to their design system pages), each with design tokens, agent instructions, and a design system page that stays current because it's built from the same code as the site.
Design teams have spent years trying to get people to actually read their design system documentation. Agents read it every single time.
2026-09-24 22:00:00
The software profession has spent years designing, developing, and shipping tools. Tools that, when learned, give people the power to create reports, videos, programs, and much more. But the pervasiveness of tools may have implanted the wrong instinct in our heads in a world of AI. Tool first, outcome second can now (and perhaps should) be flipped on its head.
Loads of AI use today is building a lot more of the tools we're used to, but much faster. With today's capabilities, though, we can actually skip the tools and jump straight to the outcomes they enable. A tool was always just a means to an end. If AI can get you to the end directly, why stop at the tool?
As usual, a concrete example helps. Two years ago, we built an AI-powered newsroom called Exposit. The system would find, aggregate, and report on global news. Behind the scenes AI agents would do the curating, writing, and editing that you'd find in a physical news room.
So it's not surprising that we presented the end result like a news site: headlines, articles, categories, etc. People could search, scroll, or navigate to find the news they were interested in. In other words, we built a news tool. Like all the other news sites out there, just run by AI.
As we continued to iterate on the product, we added a feature that allowed people to ask about a specific topic or news story and we'd compile a personalized report for them based on the latest news, related events, people, locations, and more. Really quickly this feature became the dominant way people used the site.
I've come to refer to this approach as just-in-time content: generated in real-time, for a specific person, with a specific need, at a specific moment. Instead of writing something once and hoping it fits everyone who comes along, you build a corpus that can be recombined endlessly and produce a timely, relevant answer on demand.
From the personalized report on Exposit, people could go deeper into articles, topics, entities, sources, and more. In other words, they started from the outcome: here's the news that you asked for. And if they wanted to, later engaged with the tool(s). Outcome first, tool second.
I do a similar thing on the Ask LukeW feature of this Website. Originally people had to ask a question before they got anything. Now each day I grab my most recent tweets, articles, and files and compile a "what's Luke thinking about now" answer automatically, so people get something to read without needing to ask anything. It's a small change, but it aligns with that larger theme: skip the tools and make the outcome. In this case, starting with an answer instead of requiring a question.
Now I ask myself (and pester others with): are you building another tool, or are you delivering the outcome the tool was supposed to produce? I've found just asking that question inspires new ways of solving problems.
