<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Practice Before Theory · TheFocus.AI Labs</title><description>Notes, working essays, and features on building intelligent organizations — from TheFocus.AI Labs.</description><link>https://labs.thefocus.ai/</link><language>en-us</language><item><title>Practice leads to Theory</title><link>https://labs.thefocus.ai/dispatch/practice-leads-to-theory/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/practice-leads-to-theory/</guid><description>Grown not built, discovered not developed</description><pubDate>Mon, 16 Nov 2026 13:00:00 GMT</pubDate></item><item><title>How AI in November 2026</title><link>https://labs.thefocus.ai/dispatch/how-ai-november-2026/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/how-ai-november-2026/</guid><description>Draft. Off the laptop into cloud orbs, three people to follow on harness and craft, and domain-specific harnesses over model cards.</description><pubDate>Wed, 11 Nov 2026 00:00:00 GMT</pubDate></item><item><title>Where A2A Begins and Ends</title><link>https://labs.thefocus.ai/dispatch/where-a2a-begins-and-ends/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/where-a2a-begins-and-ends/</guid><description>A2A hit v1.0 in April, and MCP&apos;s extension catalog made the two protocols look alike on paper. The actual boundary is stance: compose a transparent workbench, or delegate to an opaque peer.</description><pubDate>Tue, 04 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Agents Get a UI</title><link>https://labs.thefocus.ai/dispatch/agents-get-a-ui/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/agents-get-a-ui/</guid><description>MCP was the USB port for agents. The 2026-07-28 revision gives that port a screen, with host-mediated widgets in the chat, plus extensions for tasks, auth, and whatever comes next.</description><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate></item><item><title>mattpocock/skills v1.1: coding with alignment surfaces</title><link>https://labs.thefocus.ai/dispatch/mattpocock-skills-v1-1/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/mattpocock-skills-v1-1/</guid><description>The v1.1 release is useful because it turns agent coding into a loop we can share: align, spec, ticket, build, verify — with Wayfinder for work too foggy for one session.</description><pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Introducing Labs</title><link>https://labs.thefocus.ai/dispatch/relaunching-labs/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/relaunching-labs/</guid><description>There&apos;s so much to talk about that we need a better home for it — quarterly issues, clear lanes, and a place to look back without drowning in the archive.</description><pubDate>Sun, 19 Jul 2026 00:00:00 GMT</pubDate></item><item><title>What Surprised Us at the World&apos;s Fair</title><link>https://labs.thefocus.ai/dispatch/aie-worlds-fair-2026/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/aie-worlds-fair-2026/</guid><description>We read all 92 talk transcripts from the AI Engineer World&apos;s Fair 2026. The main report: what genuinely surprised us — with clips.</description><pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How AI in May 2026</title><link>https://labs.thefocus.ai/dispatch/how-ai-may-2026/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/how-ai-may-2026/</guid><description>Five months after the last update, almost every choice has shifted. Multi-model is the default, open weights showed up, the harness is open, and the coding agent is now a native part of the software process.</description><pubDate>Fri, 22 May 2026 00:00:00 GMT</pubDate></item><item><title>Neural harness</title><link>https://labs.thefocus.ai/dispatch/neural-harness/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/neural-harness/</guid><description>I&apos;m on my second Claude Max plan.  Are we going to go for three? Tokens are the bill for running a new native unit of computing. The harness is to neural nets what the compiler is to source code.</description><pubDate>Fri, 01 May 2026 00:00:00 GMT</pubDate></item><item><title>Laddering up from chatboxes to autonomy</title><link>https://labs.thefocus.ai/dispatch/laddering-up-from-chatboxes-to-autonomy/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/laddering-up-from-chatboxes-to-autonomy/</guid><description>Most companies want to go from scattered ChatGPT use directly to agents and autonomy. The middle layers — the ones where deployments either become real or die — get skipped in the planning.</description><pubDate>Tue, 14 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Building an Intelligent Organization</title><link>https://labs.thefocus.ai/dispatch/building-an-intelligent-organization/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/building-an-intelligent-organization/</guid><description>From AI pilots to production systems — how we help leadership move up the maturity curve with principal-led engagements.</description><pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Sraffa&apos;s Gesture, the Crack in the Crystal, and Why the Stochastic Parrot Still Bites</title><link>https://labs.thefocus.ai/dispatch/sraffas-gesture/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/sraffas-gesture/</guid><description>Wittgenstein&apos;s shift from the Tractatus to the Philosophical Investigations—triggered by Sraffa&apos;s Neapolitan gesture—reframes the stochastic parrot debate. The danger isn&apos;t that LLMs lack secret understanding. It&apos;s our willingness to treat fluent simulation as the real thing.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Agent Habitat</title><link>https://labs.thefocus.ai/dispatch/agent-habitat/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/agent-habitat/</guid><description>An agent isn&apos;t just automation with LLM calls. It carries state, accumulates memory, and makes bounded decisions under uncertainty — and a git repo is where all of that lives.</description><pubDate>Thu, 05 Feb 2026 00:00:00 GMT</pubDate></item><item><title>The Data Flywheel Pattern</title><link>https://labs.thefocus.ai/dispatch/data-flywheel-pattern/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/data-flywheel-pattern/</guid><description>Build applications by dropping in data and letting AI handle parsing, structuring, and synthesis. Three case studies.</description><pubDate>Thu, 22 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Claude Code, not Code</title><link>https://labs.thefocus.ai/dispatch/claude-code-non-coding/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/claude-code-non-coding/</guid><description>The real power of Claude Code isn&apos;t writing software—it&apos;s orchestrating skills for research, newsletters, browser automation, and turning one-off requests into repeatable workflows.</description><pubDate>Wed, 14 Jan 2026 00:00:00 GMT</pubDate></item><item><title>How AI in January 2026</title><link>https://labs.thefocus.ai/dispatch/how-ai-january-2026/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/how-ai-january-2026/</guid><description>We&apos;re at the beginning of infinity. In geological time this is all happening in an instant — and 2026 might be the best year to be alive.</description><pubDate>Sat, 03 Jan 2026 00:00:00 GMT</pubDate></item><item><title>&quot;You&apos;re absolutely right&quot; and other AI warning signs</title><link>https://labs.thefocus.ai/dispatch/you-are-absolutely-right/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/you-are-absolutely-right/</guid><description>When your AI assistant starts agreeing with everything, you&apos;ve hit the dumb zone. Practical techniques for managing context windows and keeping AI useful.</description><pubDate>Tue, 16 Dec 2025 00:00:00 GMT</pubDate></item><item><title>AI tools fail loudly where humans failed quietly</title><link>https://labs.thefocus.ai/dispatch/good-for-human-good-for-ai/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/good-for-human-good-for-ai/</guid><description>AI coding tools don&apos;t work well in messy codebases. The fix is doing what should have been done all along - and that&apos;s good for everyone.</description><pubDate>Wed, 10 Dec 2025 00:00:00 GMT</pubDate></item><item><title>AI Engineering Summit 2025: Bash-Pilled and Building for Everyone</title><link>https://labs.thefocus.ai/dispatch/2025-11-22-ai-engineering-summit-takeaways/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/2025-11-22-ai-engineering-summit-takeaways/</guid><description>The models got smart. The tools got simple. The circle of who builds is expanding.</description><pubDate>Sat, 22 Nov 2025 00:00:00 GMT</pubDate></item><item><title>gpt5 is smarter than you are</title><link>https://labs.thefocus.ai/dispatch/gpt5/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/gpt5/</guid><description>gpt5 can choose to be so smart it&apos;s almost impossible to judge.  Lets see how it does on some unanswerable questions and if it can totally replace google.</description><pubDate>Thu, 04 Sep 2025 00:00:00 GMT</pubDate></item><item><title>gpt-5 and gpt-oss</title><link>https://labs.thefocus.ai/dispatch/gpt5-and-gpt-oss/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/gpt5-and-gpt-oss/</guid><description>OpenAI’s GPT-5 launch stole headlines, but GPT-OSS quietly made local AI a lot more practical. This post covers what’s new, how to run it with Ollama or LM Studio, and why context size can change your results.</description><pubDate>Wed, 13 Aug 2025 00:00:00 GMT</pubDate></item><item><title>Technical Debt and the ROI Threshold</title><link>https://labs.thefocus.ai/dispatch/technical-debt-and-the-roi-threshhold/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/technical-debt-and-the-roi-threshhold/</guid><description>With agents now able to read and refactor code, the future cost of messy code -- and the current costs of unwritten code -- is shrinking.  Code is more disposable and experimentation more rewarding.</description><pubDate>Thu, 03 Jul 2025 00:00:00 GMT</pubDate></item><item><title>Don&apos;t be passive aggressive with your agents</title><link>https://labs.thefocus.ai/dispatch/dont-be-passive-aggressive/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/dont-be-passive-aggressive/</guid><description>Treat your coding agents as adaptable collaborators—communicate clearly, value efficiency over endurance, match tools to your workflow, skip unnecessary formality, rethink technical debt, and document your development rules for best results.</description><pubDate>Wed, 25 Jun 2025 00:00:00 GMT</pubDate></item><item><title>Feature Development on the go</title><link>https://labs.thefocus.ai/dispatch/feature-development-on-the-go/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/feature-development-on-the-go/</guid><description>What happens when you challenge Google Jules, OpenAI Codex, and Cursor to build a PWA—using just your phone? Find out which agent delivered.</description><pubDate>Sun, 08 Jun 2025 00:00:00 GMT</pubDate></item><item><title>Geo-affordance</title><link>https://labs.thefocus.ai/dispatch/geo-affordance/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/geo-affordance/</guid><description>Imagine having Sherlock Holmes’ legendary eye for detail—AI now makes that possible for all of us. Is this AI changing us?  It will alter our expectations and the risks of everyday digital life.</description><pubDate>Mon, 02 Jun 2025 00:00:00 GMT</pubDate></item><item><title>Report from Microsoft Build 2025</title><link>https://labs.thefocus.ai/dispatch/microsoft-build-2025/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/microsoft-build-2025/</guid><description>Microsoft is betting big on an open, agent-powered web—where protocols like MCP, A2A, and NLWeb redefine how AI and services interact. The real opportunity in AI isn’t just smarter models, but the “capability overhang” waiting to be unlocked by better reasoning and open standards.</description><pubDate>Wed, 21 May 2025 00:00:00 GMT</pubDate></item><item><title>On Demos and Demons</title><link>https://labs.thefocus.ai/dispatch/on-demos-and-demons/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/on-demos-and-demons/</guid><pubDate>Mon, 19 May 2025 00:00:00 GMT</pubDate></item><item><title>Thoughts on gemini</title><link>https://labs.thefocus.ai/dispatch/thoughts-on-gemini/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/thoughts-on-gemini/</guid><description>Despite popular narratives about Google lagging in AI, their Gemini models reveal engineering excellence that&apos;s hard to ignore when you strip away the conservative product decisions and UI polish. From the lightweight yet powerful Gemma 3 to the multimodal capabilities of Gemini 2.5, Google&apos;s models demonstrate a level of speed, precision, and fundamental understanding that suggests they&apos;re not playing catch-up—they&apos;re just being cautious.</description><pubDate>Fri, 04 Apr 2025 00:00:00 GMT</pubDate></item><item><title>Coding with a memory system</title><link>https://labs.thefocus.ai/dispatch/coding-with-a-memory-system/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/coding-with-a-memory-system/</guid><pubDate>Sun, 30 Mar 2025 00:00:00 GMT</pubDate></item><item><title>Moral Vibe Check</title><link>https://labs.thefocus.ai/dispatch/moral-vibe-check/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/moral-vibe-check/</guid><description>Technical correctness and meaningful insight: well-formatted, detailed AI responses can mask a fundamental lack of understanding—a &quot;raving lunatic&quot; hidden behind impressive form.  Maybe P-doom is less about malice and more of making us intellectually poorer by substituting form for substance, facts for understanding, and technical accuracy for wisdom.</description><pubDate>Mon, 24 Mar 2025 00:00:00 GMT</pubDate></item><item><title>Agentic YOLO with Warp, Cursor, and Claude</title><link>https://labs.thefocus.ai/dispatch/agentic-yolo-with-warp-cursor-and-claude/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/agentic-yolo-with-warp-cursor-and-claude/</guid><description>What happens when you let AI help you think through and build your ideas, with minimal supervision and maximum trust? What does it mean to be a programmer?  Are we closer or further from thought-stuff?</description><pubDate>Fri, 07 Mar 2025 00:00:00 GMT</pubDate></item><item><title>Clipboards are eating the world</title><link>https://labs.thefocus.ai/dispatch/clipboards-are-eating-the-world/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/clipboards-are-eating-the-world/</guid><description>The untold story of how your computer&apos;s clipboard sees itself as the essential bridge between humans and AI tools in the creative process. Through its eyes, we witness the journey of how digital projects come together through countless transfers between different AI services.</description><pubDate>Tue, 25 Feb 2025 00:00:00 GMT</pubDate></item><item><title>The New Touch Interface</title><link>https://labs.thefocus.ai/dispatch/the-new-touch-interface/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/the-new-touch-interface/</guid><description>The real killer apps of smartphones weren&apos;t the early games but became things like group chats and video calls that fundamentally changed how we communicate. Similarly, while we&apos;re currently amazed by AI&apos;s capabilities, we&apos;re still discovering how these tools will meaningfully integrate into our lives.</description><pubDate>Tue, 11 Feb 2025 00:00:00 GMT</pubDate></item><item><title>Tools for thinking.  Everyday AI.</title><link>https://labs.thefocus.ai/dispatch/tools-for-thinking/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/tools-for-thinking/</guid><description>From building nuclear fusors to probing Vatican AI doctrine, this exploration reveals how AI tools are reshaping our daily intellectual work in surprisingly practical ways. Through examples of interfacing with databases, analyzing legal documents, and diving into deep research rabbit holes, we see how AI assistants are becoming intuitive research companions that expand our ability to quickly understand and synthesize complex information.</description><pubDate>Thu, 30 Jan 2025 00:00:00 GMT</pubDate></item><item><title>How I classify models</title><link>https://labs.thefocus.ai/dispatch/how-i-classify-models/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/how-i-classify-models/</guid><description>Small models are smart yet limited in knowledge; foundation models possess both deep understanding and extensive knowledge but lack structured problem-solving approaches. Educated models like DeepResearch excel by combining learned reasoning processes with large memory capacities, enabling them to adapt effectively to complex tasks while handling vast information instantaneously.</description><pubDate>Tue, 21 Jan 2025 00:00:00 GMT</pubDate></item><item><title>AI for research: DeepResearch a clear winner</title><link>https://labs.thefocus.ai/dispatch/ai-for-research-deepresearch-wins/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/ai-for-research-deepresearch-wins/</guid><description>Asking the tough questions: DeepResearch excels in depth and comprehensiveness, while o1, Sonnet 3.5, and DeepSeek with DeepThought provide comparable results for complex inquiries. Smaller models like phi4 and llama3.2 are deemed inadequate for intricate topics.</description><pubDate>Sun, 12 Jan 2025 00:00:00 GMT</pubDate></item><item><title>Learning on the go with NotebookLM</title><link>https://labs.thefocus.ai/dispatch/notebooklm-for-research/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/notebooklm-for-research/</guid><description>By utilizing NotebookLM, an AI model capable of generating audio summaries and interactive conversations, you can create customized podcasts on-the-go.  You can also join the conversation.</description><pubDate>Thu, 09 Jan 2025 00:00:00 GMT</pubDate></item><item><title>Making hard things easier</title><link>https://labs.thefocus.ai/dispatch/making-hard-things-easier/</link><guid isPermaLink="true">https://labs.thefocus.ai/dispatch/making-hard-things-easier/</guid><description>Explore how generative AI-based tools can revolutionize the way we work, making creative tasks more accessible and efficient for both novices and experts, while also highlighting the importance of critical thinking and creativity in the face of automation.</description><pubDate>Sun, 15 Dec 2024 00:00:00 GMT</pubDate></item></channel></rss>