Weekly memos from the front of AI engineering — dispatches, measurements, and bench recipes, bound into quarterly issues.https://labs.thefocus.ai/en-ushttps://labs.thefocus.ai/dispatch/aie-worlds-fair-2026/https://labs.thefocus.ai/dispatch/aie-worlds-fair-2026/We read all 92 talk transcripts from the AI Engineer World's Fair 2026. The main report: what genuinely surprised us — with clips — plus six deep dives into the themes that mattered.Sun, 12 Jul 2026 00:00:00 GMThttps://labs.thefocus.ai/recipes/site-trailers-with-webreel/https://labs.thefocus.ai/recipes/site-trailers-with-webreel/We added the webreel skill to Claude Code, then made a site trailer by describing shots — recording, camera moves, cuts, and a Suno soundtrack — one prompt at a time. Every prompt from the session, verbatim.Thu, 09 Jul 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/mattpocock-skills-v1-1/https://labs.thefocus.ai/dispatch/mattpocock-skills-v1-1/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.Tue, 07 Jul 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/how-ai-may-2026/https://labs.thefocus.ai/dispatch/how-ai-may-2026/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.Fri, 22 May 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/local-providers-which-open-model/https://labs.thefocus.ai/dispatch/local-providers-which-open-model/We tested 7 model families across 3 runtimes on a 64 GB Mac. gemma-4-26b-a4b hits 95% in 4 minutes with thinking off. The runtime barely matters — but thinking mode changes everything.Tue, 12 May 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/neural-harness/https://labs.thefocus.ai/dispatch/neural-harness/I'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.Fri, 01 May 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/miami-report/https://labs.thefocus.ai/dispatch/miami-report/Conference update from AI Engineer Miami, April 2026. Day One was patterns breaking; Day Two was three populations — people, companies, and agents — learning agency at the same moment. Published as a full bound edition.Sat, 25 Apr 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/laddering-up-from-chatboxes-to-autonomy/https://labs.thefocus.ai/dispatch/laddering-up-from-chatboxes-to-autonomy/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.Tue, 14 Apr 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/building-an-intelligent-organization/https://labs.thefocus.ai/dispatch/building-an-intelligent-organization/From AI pilots to production systems — how we help leadership move up the maturity curve with principal-led engagements.Sat, 11 Apr 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/gemma-4-umwelten-showdown/https://labs.thefocus.ai/dispatch/gemma-4-umwelten-showdown/We benchmarked Gemma 4 (e2b, default, 26B MoE, 31B dense) through Ollama against 50+ hosted and local models on reasoning, knowledge, instruction, coding, and TezLab MCP tool use—same Umwelten harness as our other showdowns. Here’s where the new line shines, where frontier models still pull ahead, and how the biggest Gemma handles real EV data tools.Sat, 04 Apr 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/same-weights-different-results/https://labs.thefocus.ai/dispatch/same-weights-different-results/We ran the same Nemotron model on four providers and got wildly different results. MCP tool use ranged from 1/6 to 6/6. Speed varied 16x. The weights are identical. The results are not.Tue, 24 Mar 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/mcp-tool-eval-mercury-umwelten/https://labs.thefocus.ai/dispatch/mcp-tool-eval-mercury-umwelten/We ran 39 models against real Rivian driving data via MCP tools. Inception's Mercury-2 delivered a perfect 15/15 in 8.6 seconds. Here's the standout model, the ELO narrative rankings, and how the same Umwelten setup powers both chat and evals.Sun, 15 Mar 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/sraffas-gesture/https://labs.thefocus.ai/dispatch/sraffas-gesture/Wittgenstein's shift from the Tractatus to the Philosophical Investigations—triggered by Sraffa's Neapolitan gesture—reframes the stochastic parrot debate. The danger isn't that LLMs lack secret understanding. It's our willingness to treat fluent simulation as the real thing.Thu, 12 Mar 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/the-car-wash-test/https://labs.thefocus.ai/dispatch/the-car-wash-test/We asked 131 AI models a simple question — should I walk or drive to the car wash? 76% got it wrong. Simple gotcha questions reveal more about model reasoning than any benchmark leaderboard.Sun, 01 Mar 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/agent-habitat/https://labs.thefocus.ai/dispatch/agent-habitat/An agent isn'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.Thu, 05 Feb 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/data-flywheel-pattern/https://labs.thefocus.ai/dispatch/data-flywheel-pattern/Build applications by dropping in data and letting AI handle parsing, structuring, and synthesis. Three case studies.Thu, 22 Jan 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/claude-code-non-coding/https://labs.thefocus.ai/dispatch/claude-code-non-coding/The real power of Claude Code isn't writing software—it's orchestrating skills for research, newsletters, browser automation, and turning one-off requests into repeatable workflows.Wed, 14 Jan 2026 00:00:00 GMThttps://labs.thefocus.ai/dispatch/how-ai-january-2026/https://labs.thefocus.ai/dispatch/how-ai-january-2026/We'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.Sat, 03 Jan 2026 00:00:00 GMThttps://courses.thefocus.ai/build-ai-coding-agent/https://courses.thefocus.ai/build-ai-coding-agent/A step-by-step tutorial for building an AI coding assistant from scratch. Bootstrap it with an existing agent, then use it to improve itself.Wed, 17 Dec 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/you-are-absolutely-right/https://labs.thefocus.ai/dispatch/you-are-absolutely-right/When your AI assistant starts agreeing with everything, you've hit the dumb zone. Practical techniques for managing context windows and keeping AI useful.Tue, 16 Dec 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/good-for-human-good-for-ai/https://labs.thefocus.ai/dispatch/good-for-human-good-for-ai/AI coding tools don't work well in messy codebases. The fix is doing what should have been done all along - and that's good for everyone.Wed, 10 Dec 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/smallest-coding-agent/https://labs.thefocus.ai/recipes/smallest-coding-agent/A complete agentic coding loop in 25 lines of Bun. No frameworks, no dependencies, just bash and a model.Fri, 05 Dec 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/2025-11-22-ai-engineering-summit-takeaways/https://labs.thefocus.ai/dispatch/2025-11-22-ai-engineering-summit-takeaways/The models got smart. The tools got simple. The circle of who builds is expanding.Sat, 22 Nov 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/ai-engineering-code-summit-2025/https://labs.thefocus.ai/dispatch/ai-engineering-code-summit-2025/A comprehensive analysis of the state of AI engineering tools, frameworks, and best practices from the November 2025 Code Summit. Exploring cutting-edge developments in AI-assisted development, infrastructure, and production deployment strategies.Thu, 20 Nov 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/repomix-redux/https://labs.thefocus.ai/recipes/repomix-redux/How to use repomix to package your entire codebase into a single file for LLM context, with tips for managing token counts and mise integration.Mon, 08 Sep 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/gpt5/https://labs.thefocus.ai/dispatch/gpt5/gpt5 can choose to be so smart it's almost impossible to judge. Lets see how it does on some unanswerable questions and if it can totally replace google.Thu, 04 Sep 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/context7-mcp/https://labs.thefocus.ai/recipes/context7-mcp/Learn how to integrate Context7 MCP server to get up-to-date code documentation for LLMs and AI code editors, enabling real-time access to the latest library and framework documentation.Mon, 01 Sep 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/playwright-mcp/https://labs.thefocus.ai/recipes/playwright-mcp/Learn how to integrate Playwright MCP server to enable AI coding agents to interact with web browsers, take screenshots, and validate designs with high fidelity for accurate web development and testing.Mon, 01 Sep 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/single-file-swift-code/https://labs.thefocus.ai/dispatch/single-file-swift-code/swift files can be run directly without compiling and without XCode, making it easy to create native UI elements and access all of macOS's APIs. Once you see Swift as a scripting language rather than just an app language, you start wondering what other capabilities are hiding in plain sight.Fri, 22 Aug 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/local-models-typescript/https://labs.thefocus.ai/dispatch/local-models-typescript/Small, local AI models deliver surprisingly effective results for everyday tasks. Also llama3.2 is surprisingly fast and gpt-oss is surprisingly good.Wed, 20 Aug 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/gpt5-and-gpt-oss/https://labs.thefocus.ai/dispatch/gpt5-and-gpt-oss/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.Wed, 13 Aug 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/dagger-and-container-use/https://labs.thefocus.ai/recipes/dagger-and-container-use/Unlock the power of isolated development with Dagger and Container Use—no more worrying about missing dependencies or system conflicts.Tue, 08 Jul 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/technical-debt-and-the-roi-threshhold/https://labs.thefocus.ai/dispatch/technical-debt-and-the-roi-threshhold/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.Thu, 03 Jul 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/use-cursor-in-slack/https://labs.thefocus.ai/recipes/use-cursor-in-slack/Learn how to integrate Cursor with Slack for seamless code review and collaboration, including setup tips and workflow enhancements.Mon, 30 Jun 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/dont-be-passive-aggressive/https://labs.thefocus.ai/dispatch/dont-be-passive-aggressive/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.Wed, 25 Jun 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/june-2025-coding-agents-report/https://labs.thefocus.ai/dispatch/june-2025-coding-agents-report/A comprehensive analysis of 15 leading AI coding agents in 2025. We break down the strengths, weaknesses, and surprises from top tools, with clear winners for pros, tinkerers, and casual users alike.Sun, 15 Jun 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/feature-development-on-the-go/https://labs.thefocus.ai/dispatch/feature-development-on-the-go/What happens when you challenge Google Jules, OpenAI Codex, and Cursor to build a PWA—using just your phone? Find out which agent delivered.Sun, 08 Jun 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/geo-affordance/https://labs.thefocus.ai/dispatch/geo-affordance/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.Mon, 02 Jun 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/content-finder/https://labs.thefocus.ai/recipes/content-finder/Ever had a movie stuck on the tip of your tongue or wanted more like your family's favorite? Explore how AI-powered content discovery can help you make your next pick.Wed, 28 May 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/geolocation-prompt/https://labs.thefocus.ai/recipes/geolocation-prompt/This post introduces a prompt for high-precision, image-based geolocation analysis, guiding AI to deduce where a photo was taken using expertise in visual, cultural, and environmental cues. The prompt provides a step-by-step framework for analyzing images and generating confident, reasoned location guesses—even suggesting what extra information would help if uncertain.Wed, 28 May 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/microsoft-build-2025/https://labs.thefocus.ai/dispatch/microsoft-build-2025/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.Wed, 21 May 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/on-demos-and-demons/https://labs.thefocus.ai/dispatch/on-demos-and-demons/Mon, 19 May 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/iterating-designs-with-chatgpt4o/https://labs.thefocus.ai/recipes/iterating-designs-with-chatgpt4o/Discover how to leverage Chrome's hidden command palette and ChatGPT to transform your website screenshots into sophisticated wireframes. Learn a clever workflow that combines Chrome's full-page screenshot capability with ChatGPT's AI-powered design suggestions to create professional 16:9 ratio mockups for your next project.Mon, 07 Apr 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/thoughts-on-gemini/https://labs.thefocus.ai/dispatch/thoughts-on-gemini/Despite popular narratives about Google lagging in AI, their Gemini models reveal engineering excellence that'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's models demonstrate a level of speed, precision, and fundamental understanding that suggests they're not playing catch-up—they're just being cautious.Fri, 04 Apr 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/llm-for-quick-prototyping/https://labs.thefocus.ai/recipes/llm-for-quick-prototyping/Transform your workflow with a command-line tool that brings AI capabilities directly to your terminal, no complex setup required. See how to parse websites, analyze transcripts, and extract meaningful data using the llm CLI with popular models like Gemini and Claude.Thu, 03 Apr 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/lift-and-shift/https://labs.thefocus.ai/recipes/lift-and-shift/Master the art of learning from existing projects by using this structured approach to extracting and documenting requirements and insights. With simple command-line tools and clear documentation practices, you'll be able to turn any existing implementation into a wealth of reusable knowledge.Wed, 02 Apr 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/using-claude-to-write-midjourney-prompts/https://labs.thefocus.ai/recipes/using-claude-to-write-midjourney-prompts/Transform your written content into compelling visual concepts by using Claude as an intelligent intermediary for Midjourney prompt creation. See how combining prompt libraries with AI analysis can help you explore multiple creative directions before settling on the perfect visual representation.Mon, 31 Mar 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/coding-with-a-memory-system/https://labs.thefocus.ai/dispatch/coding-with-a-memory-system/Sun, 30 Mar 2025 00:00:00 GMThttps://labs.thefocus.ai/dispatch/using-structured-output/https://labs.thefocus.ai/dispatch/using-structured-output/Transforms chatting from simple text generators into powerful data processing engines, enabling extraction of organized information from PDFs, audio files, and more. Here are some practical techniques for building, including audio analysis, pdf data extraction and conversation state management, showcasing how constraint-driven outputs can power rich user experiences.Sun, 30 Mar 2025 00:00:00 GMThttps://labs.thefocus.ai/recipes/always-tdd/https://labs.thefocus.ai/recipes/always-tdd/Sat, 29 Mar 2025 00:00:00 GMT