# Matthew Blode — Full corpus > Melbourne product leader and AI engineer at Linktree. Two startups, two exits (Fingertip, VenueSafe). Forbes 30 Under 30, zero-to-one specialist. This document is the complete public content of matthewblode.com in one file, intended for long-context agent ingestion. --- # About Matthew Blode > Melbourne product leader and AI engineer at Linktree. Two startups, two exits (Fingertip, VenueSafe). Forbes 30 Under 30, zero-to-one specialist. AI at Linktree. Co-founder of Fingertip and VenueSafe. Forbes 30 Under 30. Melbourne-based product leader and engineer. ## Quick facts - **6 months** — VenueSafe went from idea to acquisition by me&u in six months. - **15M+ users** — Helped scale me&u's mobile ordering platform to 15M+ users globally after VenueSafe was acquired. - **100+ countries** — Fingertip supported small businesses globally before its acquisition by Linktree. - **Zero to one** — My specialty is building the early product, engineering, and AI systems that get new ventures moving. Two startups, two exits. I am a Melbourne-based product leader and engineer focused on going zero to one. I co-founded VenueSafe during COVID and took it from idea to acquisition by me&u (formerly Mr Yum) in six months. I stayed on for two years, helped scale me&u to 15M+ users globally, and supported the US expansion from Austin, Texas. After that I co-founded Fingertip with Olly Hoffman and the founders of Catch and Menulog. We scaled to tens of thousands of small businesses across 100+ countries before Fingertip was acquired by Linktree. Today I'm on AI at Linktree, building AI-powered experiences for creators and small businesses. On the side, I build under Blode, my product studio for apps, developer tools, and open-source libraries like Blode UI, Blode Icons, and AllMD. ## Experience ### 2025 - Present — Linktree *AI Engineer* · [Linktree](https://linktr.ee) Building AI agents and assistants that help creators grow and manage their Linktree. - Building AI agents and product experiences for 90M+ Linktree users. ### 2023 - 2025 — Fingertip *Co-founder & CTO* · [Fingertip](https://fingertip.com) Co-founded Fingertip with Olly Hoffman, Gabby Leibovich, and Hezi Leibovich to help small businesses run more of their business online. - Scaled to tens of thousands of small businesses across 100+ countries. - Built product and engineering across website creation, bookings, payments, and invoicing. - Fingertip was acquired by Linktree in 2025. ### 2022 - 2023 — me&u *Senior Software Engineer* · [me&u](https://www.meandu.com/) Joined me&u (formerly Mr Yum) after the VenueSafe acquisition and helped scale the platform to 15M+ users globally. - Helped scale me&u's platform to 15M+ users. - Moved to Austin, Texas to support US market expansion. ### 2020 - 2021 — VenueSafe *Co-founder & CTO* · [VenueSafe](https://venuesafe.netlify.app/) Built a COVID contact tracing platform for Australian venues and hospitality businesses. - Went from idea to acquisition by me&u in six months. - Built and shipped the product during the peak urgency of COVID operations. ### 2019 - 2020 — Light Creative *Front-end Web Developer* · [Light Creative](https://www.lightcreative.com.au) Built React frontends for enterprise clients across e-commerce and corporate platforms. - Delivered fast, responsive interfaces for high-traffic web applications. ### 2016 - 2019 — S. Group *Web Developer* · [S. Group](http://www.sgroup.com.au) Built websites and web applications for corporate clients across marketing and internal tools. - Shipped projects across multiple concurrent client engagements. ## Community & advisory ### Startmate *Accelerator Mentor* · [Startmate](https://www.startmate.com.au) Mentoring startups in Australia's leading accelerator and supporting the next generation of founders. ### OpenAI *Codex Ambassador* · [OpenAI](https://openai.com) Supporting local developer communities through community sessions, feedback, and hands-on learnings. ### Airtree *Explorer* · [Airtree](https://www.airtree.vc) Part of Airtree's operator community connecting experienced builders with early-stage founders. ### VCMC *Co-founder* · [VCMC](https://vcmc.ai) Co-founded the Vibe Coding Micro Community with Luca Bonelli and Ryan Hendler to bring AI-native builders together. ## FAQ ### What does Matthew Blode do? Matthew is on AI at Linktree, working across product and frontend to build AI-powered creator experiences. ### What has Matthew Blode built? He co-founded VenueSafe during COVID and took it from idea to acquisition by me&u in six months. He then helped scale me&u to 15M+ users globally. After that, he co-founded Fingertip with the founders of Catch and Menulog, scaling to tens of thousands of small businesses across 100+ countries before Fingertip was acquired by Linktree. ### What is Blode? Blode is Matthew's product studio. It ships apps, developer tools, open-source libraries, and design experiments like Blode UI, Blode Icons, and AllMD, at blode.co. - [blode.co](https://blode.co) ### Is Matthew Blode available for speaking or mentoring? Yes. Matthew speaks at meetups, panels, and builder events on topics like zero-to-one product building, AI-assisted engineering, and shipping fast. He also mentors through Startmate and co-founded VCMC, a builder community in Melbourne. ### Where can I find Matthew Blode online? You can find Matthew on LinkedIn, GitHub, X, Raycast, CodePen, and on this site where he publishes his projects and resume. - [LinkedIn](https://www.linkedin.com/in/matthewblode/) - [GitHub](https://github.com/mblode) - [X](https://x.com/mattblode) - [Raycast](https://www.raycast.com/mblode) - [CodePen](https://codepen.io/mblode) - [projects](https://matthewblode.com/projects) - [resume](https://matthewblode.com/resume.pdf) --- # How I get shit done > Nine things I’ve learned about shipping, as an engineer and technical founder, across two startup exits and 90M+ users at Linktree. The tools come last. *“You don’t win by being right. You win by finding out faster.”* ## 01. Ship fast or die > *Going faster means removing what’s slowing you down.* Instead of asking how to ship faster, ask what’s slowing you down and get rid of it: blocked tasks, too many meetings, fuzzy ownership, PR reviews. Find the 10% that gives you 90% of the value, and get it in front of real people. Nobody knows what works up front, so the quickest way to find out is to put it in someone’s hands. ## 02. Bias towards action > *Even a failed first attempt teaches you what to build next.* Now that building is cheap, throwing code away costs nothing. Your first version is just a guess, so try not to get attached and keep iterating. ## 03. Own it, then hand over the keys > *If something’s broken and you can fix it, just fix it and push.* Try to kill off “that’s not my job” wherever it shows up. One person should own a feature the whole way through, across design, engineering, and product, and if you can’t yet say what “done” looks like, sort that out first. Ownership doesn’t scale by doing more yourself, it scales by giving someone real authority and the accountability to go with it. Give them both at once, because authority with no accountability gets messy and accountability with no real say isn’t fair on anyone. ## 04. Build lots, keep it simple > *Get it simple enough that it clicks in your head.* Solve your own problem, give the tool away, and show people how you did it. For each project, find the little crux of the problem and get it as simple as you can, until it clicks. Once it clicks, it’s like a ball rolling downhill. ## 05. Risk scales with blast radius > *How much you can break decides how carefully you ship.* An early MVP can ship fast and loose: push to main, get it in front of users. A platform with 90M+ people on it earns feature flags, staged rollouts, and proper review. The scariest code, anything touching money, tax, or permissions, earns stronger tests even when AI wrote it. CI going green doesn’t mean the product works. ## 06. Stay at the frontier > *Pick the role that scares you slightly more than it excites you.* Put yourself where you’ll learn the fastest, and keep learning the newest thing. Speed is a skill, and you only build it under pressure, when real people need a real answer and the deadline isn’t moving. ## 07. You can sense carelessness > *People never see your code, but they can feel when it was made carelessly.* It’s the sum of all the small details that people pick up on, even the ones they’d never consciously notice. So generate fast, then go and sand down the rough edges, and keep sanding. The thing that still sets you apart is knowing what’s good, choosing it, and standing behind it. ## 08. Get in the room > *A model can write any code, but it can’t be in the room, and that part doesn’t go away.* Play the long game and optimise for opportunities. Do the talks, build in public, help people when there’s nothing in it for you. You can’t plan luck, but you can give it more ways to find you. ## 09. Getting things done > *A slightly obnoxious belief that any problem can be solved does more for a team than any plan.* Don’t carry everything in your head: put it in a system you trust so you can be fully present on the one thing in front of you. When AI can write anything, your edge is the stuff it can’t do: taste, ownership, being in the room. --- # Speaking & talks > Talks and sessions by Matthew Blode on zero-to-one product building, AI-assisted engineering, and shipping fast. ## Topics - Zero-to-one product building - AI-assisted engineering - Product taste and craft - Startup execution speed - Developer tooling - Community-led learning ## Talks ### Writing 90% of my code with AI *Agents After Dark* · June 2026 · Podcast Writing most of my code with AI and shipping it safely to millions of Linktree users: plan mode, layered agent and human review, feature flags, and evals. - The hallucinated dependency that reached prod, and the review system that catches the next one. - [Watch](https://youtu.be/jUI-E4K942w) - [Listen](https://open.spotify.com/show/033v9bTcSbsxFsxQmPnz52) ### Care made easy *Claude Community Australia* · May 2026 · Melbourne The tools I've built over two years to ship fast without cutting corners. - Live demo of the full Blode Stack. - [Slides](https://stack.blode.co) - [Recording](https://www.loom.com/share/023aaf07218d4c938b6a5ce4428fc0f2) ### Unblocking Yourself with AI *Linktree* · May 2026 · Melbourne How we run AI tools across a 10 year old codebase and 200+ engineers. 20 parallel agent branches, PRs that land overnight. - From zero adoption to 20 concurrent agent branches in production. - [Slides / link](https://ai-usage.blode.co) ### You can sense carelessness *Next.js Melbourne meetup* · February 2026 · BuildPass, Melbourne Users notice when you cut corners, even when they never see the code. Why the invisible details still shape how a product feels. - ~50 developers and product builders at Next.js Melbourne. - [Slides / link](https://nextjs-preso.blode.co) - [Event page](https://luma.com/t5jle3hj) ### Ship fast or die *Startmate mentor session* · January 2026 · Melbourne A working session for the latest Startmate cohort. Claude Code workflows, what actually slows early teams down, and when going slower is faster. - Part of an ongoing mentorship with Startmate. - Claude Code, velocity killers, and knowing when to slow down. - [Slides / link](https://app.chroniclehq.com/share/8460b971-930c-4f97-b0bb-7f6e1b683693/561d15f0-33df-446a-b89b-b36438ad31fb/intro) ### You don't have to make AI slop *Melbourne builder meetup* · January 2026 · Melbourne AI makes it easy to ship faster. It also makes it easy to ship worse. The habits that keep the bar high when you're building with AI every day. - The gap between using AI and producing AI-quality output. - Practical habits for keeping quality high. - [Slides / link](https://app.chroniclehq.com/share/dbb62bb8-d1bb-4ee4-b24e-77c900a2ca31/0ac5a633-f636-410a-85b0-ba02540e3e94/intro) ### Building at different scales *The Outlook panel* · July 2025 · Melbourne What changes when you go from three people to Atlassian scale? Panel with Tarra van Amerongen and Trudi Boatwright. - How execution changes at every stage while the mission stays the same. - [Video](https://www.linkedin.com/posts/matthewblode_want-to-know-what-customers-want-tarra-activity-7363744098853273601-2l43?utm_source=share&utm_medium=member_ios&rcm=ACoAABPvOgMBrrRnmj7eHPWPIcoGwwpj2HiQRKg) --- # Press & mentions > Public features, awards, and third-party mentions of Matthew Blode. ## Recognition - [Meet the Aussies on the 2025 Forbes 30 Under 30 Asia list](https://www.forbes.com.au/news/30-under-30/meet-the-aussies-on-the-2025-forbes-30-under-30-asia-list/) — *Forbes Australia*. Recognition tied to the 2025 Forbes 30 Under 30 Asia list. - [Matthew Blode](https://pauseawards.com/winners/matthew-blode/) — *Pause Awards*. Public winner profile describing Matthew as CTO and co-founder of Fingertip. ## Features - [Fingertip](https://www.forbes.com/profile/fingertip/) — *Forbes*. Forbes company profile for Fingertip, describing the business co-founded by Matthew Blode and Oliver Hoffman. - [Linktree acquires emerging Melbourne-based competitor Fingertip](https://www.businessnewsaustralia.com/articles/linktree-acquires-emerging-melbourne-based-competitor-fingertip.html) — *Business News Australia*. Acquisition coverage describing Linktree's acquisition of Fingertip and the founders joining Linktree. - [Matthew Blode - One Page Website Award](https://onepagelove.com/matthew-blode) — *One Page Love*. Feature page for Matthew Blode's one-page portfolio site. --- # The Blode Stack > Software Matthew Blode has built — design foundations, developer tools, and platform tools. It all ships under [Blode](https://blode.co), Matthew Blode's product studio. ## 1. Design foundations A typeface, icon set, and component library that work together. Keeps your UI consistent out of the box. - [Glide](https://glide.blode.co) — Variable font family crafted for UI. · [GitHub](https://github.com/mblode/glide) - [Blode Icons](https://icons.blode.co) — 3,000+ beautiful icons. Lucide compatible. · [GitHub](https://github.com/mblode/blode-icons) - [Blode UI](https://ui.blode.co) — The shadcn/ui registry with good taste. · [GitHub](https://github.com/mblode/blode-ui) - [Style Capture](https://style-capture.blode.co) — Point at any UI. Let your agent rebuild it. · [GitHub](https://github.com/mblode/style-capture) ## 2. Developer tools Tools and agents for coding, converting content, and testing changes. - [Agent Skills](https://github.com/mblode/agent-skills) — All I know about building products, turned into agent skills. - [AllMD](https://allmd.blode.co) — Turn the whole universe into markdown. · [GitHub](https://github.com/mblode/allmd) - [Commandment](https://commandment.blode.co) — Voice to text, instantly. Just press a shortcut and speak. BYO OpenAI API key. · [GitHub](https://github.com/mblode/commandment) - [DiffHub](https://diffhub.blode.co) — Local diff viewer for cmux. · [GitHub](https://github.com/mblode/diffhub) - [Rubber Duck](https://rubber-duck.blode.co) — Voice coding agent. Talk through code to understand the problem. · [GitHub](https://github.com/mblode/rubber-duck) ## 3. Platform tools Shared infrastructure so you don’t have to build it yourself. - [Blode.md](https://blode.md) — Documentation platform. Write markdown, get a published docs site. · [GitHub](https://github.com/mblode/blodemd) - [Strata Sync](https://stratasync.dev) — Apps that just work. Inspired by Linear’s sync engine. Open-source. Total tools: 11. --- # All projects > A reverse-chronological list of every project Matthew Blode has built — products, open source, side projects, client work, and presentations. ## 2026 - [Agent Skills](https://github.com/mblode/agent-skills) — *Open source*. A minimal set of agent skills for high-quality UI and frontend work - [AllMD](https://allmd.blode.co) — *Open source*. Convert web pages, YouTube videos, PDFs, Google Docs, and more to markdown - [Blode Icons](https://icons.blode.co) — *Open source*. Icon library for design engineers - [Blode UI](https://ui.blode.co) — *Open source*. UI component library for design engineers - [Blode.md](https://blode.md) — *Open source*. Documentation framework for the whole stack - [Canvas Kit](https://canvas.blode.co) — *Open source*. Infinite-canvas shadcn registry with pan, zoom, drag and folder cards - [Captain](https://captain.blode.md) — *Open source*. Captain a fleet of cmux worktrees from one Claude Code session - [Care](https://care.blode.co) — *Presentation*. Care made easy: encoding taste and care into code - [Commandment](https://commandment.blode.co) — *Open source*. Open-source voice dictation for macOS, bring your own OpenAI API key - [Convene](https://convene.blode.co) — *Open source*. Open-source meeting transcription for macOS - [Course](https://course.blode.co) — *Side project*. A free interactive course on obsessive web design detail - [DiffHub](https://diffhub.blode.co/) — *Open source*. Local git diff viewer - [Done Bear](https://donebear.com) — *Product*. Calm, local-first task manager for focused people and teams - [Glide](https://glide.blode.co) — *Open source*. Variable font family crafted for UI - [HN](https://hn.blode.co) — *Side project*. A fast, modern Hacker News client - [Reel](https://reel.blode.co) — *Open source*. Turn browser feedback recordings into structured artifacts for coding agents - [Rubber Duck](https://rubber-duck.blode.co) — *Open source*. Open-source voice coding companion for macOS - [Shareful.ai](https://shareful.ai) — *Product*. Share and discover coding solutions - [Ship fast or die](https://app.chroniclehq.com/share/8460b971-930c-4f97-b0bb-7f6e1b683693/561d15f0-33df-446a-b89b-b36438ad31fb/intro) — *Presentation*. If AI writes the code, how come you’re still moving slowly? - [Spotlight Testing](https://github.com/mblode/spotlight-testing) — *Open source*. See your code changes in a running dev server instantly - [Static to Variable](https://variable.blode.co) — *Open source*. Turn a family of static fonts into one variable font - [Strata Sync](https://stratasync.dev) — *Open source*. Sync that works offline - [Style Capture](https://style-capture.blode.co) — *Side project*. Capture CSS from any website element and convert to Tailwind classes - [Tiller](https://tiller.blode.co) — *Side project*. Interactive guide to learning how to sail a dinghy - [Unblocking yourself with AI](https://ai-usage.blode.co/) — *Presentation*. How Matthew Blode and Mrudula Vysyaraju use Claude Code, Codex, and Devin - [You can sense carelessness](https://nextjs-preso.blode.co) — *Presentation*. Behind-the-scenes of Fingertip’s product engineering - [You don’t have to make AI slop](https://app.chroniclehq.com/share/dbb62bb8-d1bb-4ee4-b24e-77c900a2ca31/0ac5a633-f636-410a-85b0-ba02540e3e94/intro) — *Presentation*. Building quality products with AI tools ## 2025 - [Beautiful QR Code](https://beautiful-qr-code.blode.co) — *Side project*. Generate beautiful, customizable QR codes in JavaScript - [Brighter](https://github.com/mblode/brighter) — *Open source*. macOS brightness utility - [Claude Code Search](https://github.com/mblode/claude-code-search) — *Open source*. Search through your Claude Code conversation history - [Colour Mixer](https://color-mixer.blode.co) — *Side project*. Pigment-based colour mixing playground - [Days Off Git](https://days-off-git.blode.co) — *Side project*. Inspect and visualize GitHub commit patterns - [Dither Asteroids](https://dither.blode.co) — *Side project*. Asteroids game with blue noise dithering - [DnD Grid](https://dnd-grid.com) — *Open source*. Draggable and resizable grid layout for React - [FX](https://fx.blode.co) — *Side project*. Blue noise dithering, ASCII, and LED art for images and video - [Linktree](https://linktr.ee) — *Product*. Link-in-bio platform for creators - [Matt’s Experiments](https://experiments.blode.co) — *Side project*. A collection of UI experiments - [Moon Simulator](https://moon.blode.co) — *Side project*. Interactive moon phase simulator - [New Portfolio Site](https://matthewblode.com) — *Side project*. Personal portfolio redesign - [Nicebreak](https://nicebreak.blode.co) — *Product*. AI ice breakers for Google Meet - [QRUX](https://qrux.app) — *Product*. Create and manage QR codes - [React Vello](https://react-vello.blode.co) — *Open source*. Blazing fast React renderer powered by Vello - [Resumai](https://resumai.studio) — *Product*. AI-powered resume editor - [VCMC](https://vcmc.ai) — *Product*. Vibe Coding Micro Community: a WhatsApp group bringing AI-native builders together ## 2024 - [Raycast CyberChef](https://github.com/mblode/raycast-cyberchef) — *Open source*. CyberChef operations in Raycast - [Touchwood Cabinetry](https://touchwood.com.au) — *Client*. Award-winning custom kitchens and cabinetry ## 2023 - [Blue Noise TypeScript](https://github.com/mblode/blue-noise-typescript) — *Open source*. Blue noise dithering algorithm in TypeScript - [Fingertip.com](https://matthewblode.com/case-studies/fingertip) — *Exit*. AI-powered platform helping SMBs run their entire business ## 2022 - [Raycast Google Search](https://github.com/mblode/raycast-google-search) — *Open source*. Google search extension for Raycast - [Raycast Quick Event](https://github.com/mblode/raycast-quick-event) — *Open source*. Create calendar events with natural language in Raycast ## 2021 - [Blue Noise Rust](https://github.com/mblode/blue-noise-rust) — *Open source*. Black and white image dithering using blue noise - [me&u](https://meandu.com) — *Product*. Mobile ordering platform for hospitality ## 2020 - [Egg Freezing](https://eggfreezing.org.au) — *Client*. Fertility preservation decision-making resource - [Fertility Choices](https://fertilitychoices.com.au) — *Client*. Fertility preservation guidance for cancer patients - [Light Creative](https://lightcreative.com.au) — *Client*. Strategic brand storytelling and design agency - [PANDA](https://www.panda.org.au) — *Client*. Mental health support for expecting and new parents - [VenueSafe](https://matthewblode.com/case-studies/venuesafe) — *Exit*. COVID contact tracing platform serving 1M+ Australians ## 2019 - [Bishops](https://bishops.com.au) — *Client*. Launceston barristers and solicitors - [Blue Derby](https://www.ridebluederby.com.au) — *Client*. Tasmania’s mountain bike trails destination - [Change Overnight](https://changeovernight.co) — *Client*. Charitable hotel in Launceston, Tasmania - [Crunchlab](https://crunchlab.com.au) — *Client*. Cloud-based accounting automation for businesses - [Freedom Centre](https://freedomcenter.in) — *Client*. Education and job skills programs in India - [Michael Christofas](https://michaelchristofas.com.au) — *Design*. Corporate, events, and portraiture photographer - [Nectaar](https://nectaar.com.au) — *Client*. Melbourne residential and commercial interior design - [OPERA](https://opera.eclc.org.au) — *Client*. Community program combating ageism - [Plastex](https://www.plastexmatting.com) — *Client*. Industrial and commercial matting manufacturer - [Rae & Partners](https://raepartners.com.au) — *Client*. Tasmanian full-service law firm - [TRAM](https://tram.org.au) — *Client*. University of Melbourne research impact accelerator - [VSCode Pretty Formatter](https://marketplace.visualstudio.com/items?itemName=mblode.pretty-formatter) — *Open source*. VS Code extension to format files using Pretty Diff - [VSCode Zotero](https://marketplace.visualstudio.com/items?itemName=mblode.zotero) — *Open source*. Zotero Better BibTeX citations for VS Code ## 2018 - [Anstie Constructions](https://www.anstieconstructions.com.au) — *Client*. Tasmanian commercial and institutional builder - [Arise Acres](https://web.archive.org/web/20250416043844/https://ariseacres.com.au/) — *Client*. Property development website - [Creative Brimbank](https://creativebrimbank.com.au) — *Client*. Arts and cultural programs for Brimbank community - [Deus Ex Machina](https://shop.au.deuscustoms.com) — *Client*. Motorcycle and surf culture lifestyle brand - [Heathdale Christian College](https://www.heathdale.vic.edu.au) — *Client*. Christian school from Kinder to Year 12 - [IPD Consulting](https://ipdconsulting.com.au) — *Client*. Tasmanian engineering and project management consulting - [Jeremy Blode Photography](https://jeremyblode.com) — *Design*. Melbourne and Mornington Peninsula wedding photographer - [Klapsis](https://web.archive.org/web/20260311164037/https://klapsis.com.au/) — *Client*. Building and construction project management - [Lord of the Fries](https://www.lordofthefries.com.au) — *Client*. Plant-based fast food restaurant chain - [Our Cradle](https://ourcradle.com.au) — *Client*. Luxury accommodation at Tasmania’s Cradle Mountain - [Polar Guides](https://polarguides.org) — *Client*. Professional guiding standards for polar environments - [Shift Property Styling](https://www.shiftpropertystyling.com.au) — *Client*. Property styling mobile app - [Sprout Forms Tables](https://github.com/mblode/sprout-forms-tables) — *Open source*. Custom tables field for Sprout Forms on Craft 3 - [VSCode Twig Language 2](https://marketplace.visualstudio.com/items?itemName=mblode.twig-language-2) — *Open source*. VS Code extension with snippets, syntax highlighting, and formatting for Twig - [Your Tea](https://int.yourtea.com) — *Client*. Traditional Chinese Medicine herbal tea blends ## 2017 - [Little Designer Club](https://web.archive.org/web/20200425005856/https://littledesignerclub.com/) — *Client*. Kids craft and design subscription box - [SVG Placeholder](https://github.com/mblode/svgplaceholder) — *Open source*. Invisible SVG placeholder plugin for lazy loading in Craft CMS - [Verbb](https://verbb.io) — *Product*. Craft CMS plugin marketplace - [VSCode Twig Language](https://marketplace.visualstudio.com/items?itemName=mblode.twig-language) — *Open source*. VS Code extension with snippets and syntax highlighting for Twig ## 2016 - [Expense Check](https://www.expensecheck.com.au) — *Product*. Automated bill switching and expense reduction - [Grav Theme Medium](https://github.com/mblode/grav-theme-medium) — *Open source*. Medium-inspired theme for Grav CMS ## 2015 - [Burger](https://codepen.io/mblode/pen/qEGWwB) — *Open source*. The minimal hamburger menu with fullscreen navigation - [Hayley Lauren Design](https://hayleylaurendesign.com) — *Design*. Graphic design portfolio website - [Marx](https://mblode.github.io/marx/) — *Open source*. The classless CSS reset (perfect for Communists) --- # Case studies > Zero-to-one products, startup exits, and the systems Matthew Blode built behind them. ## [Fingertip](https://matthewblode.com/case-studies/fingertip) *Co-founder & CTO · 2023-2025 · Linktree* Fingertip scaled to tens of thousands of small businesses across 100+ countries, earned Forbes 30 Under 30 Asia recognition, and was acquired by Linktree in 2025. - **100+ countries** — Small-business footprint - **Tens of thousands** — SMBs supported - **2025** — Acquired by Linktree - **30+ repos** — Product ecosystem ## [VenueSafe](https://matthewblode.com/case-studies/venuesafe) *Co-founder & CTO · 2020-2021 · me&u / Mr Yum* VenueSafe served more than 1M Australians during the COVID response and went from idea to acquisition by me&u in six months. - **1M+** — Australians served - **6 months** — Idea to acquisition - **2021** — Acquired by me&u - **3 repos** — Product stack --- # Fingertip case study > How Matthew Blode co-founded and built Fingertip, an AI-powered platform for small businesses, before its acquisition by Linktree. *Co-founder & CTO · 2023-2025 · Linktree* Published May 18th, 2026 Fingertip scaled to tens of thousands of small businesses across 100+ countries, earned Forbes 30 Under 30 Asia recognition, and was acquired by Linktree in 2025. ## Metrics - **100+ countries** — Small-business footprint - **Tens of thousands** — SMBs supported - **2025** — Acquired by Linktree - **30+ repos** — Product ecosystem ## Context Fingertip started with a narrow but painful problem: service businesses needed something more useful than a link-in-bio page and less heavy than a traditional website builder. The product became an AI-powered business platform for websites, bookings, payments, invoicing, QR codes, and e-commerce, designed so a small business owner could run it from a phone. ## What I Built As co-founder and CTO, I built the core TypeScript platform across the public page runtime, creator editor, theme system, AI page generation, booking engine, invoicing, payments, QR codes, Apple Wallet support, and deployment infrastructure. The architecture grew into a 30+ repo ecosystem with a Next.js creator frontend, Fastify backend, Prisma/PostgreSQL data model, Redis/BullMQ workers, Connect RPC contracts, Stripe, Nylas, and a shared design system. ## Outcome Fingertip reached tens of thousands of small businesses across more than 100 countries before being acquired by Linktree in 2025. The team, including co-founders Olly Hoffman and Matthew Blode, joined Linktree to keep shaping LinkApps and small-business workflows for Linktree's global creator community. ## FAQ ### What was Fingertip? Fingertip was an AI-powered platform that helped small businesses create pages, take bookings, accept payments, send invoices, and run more of their business online. ### Who acquired Fingertip? Fingertip was acquired by Linktree in 2025, and the team joined Linktree to work on creator and small-business tools. ### What was Matthew Blode's role at Fingertip? Matthew Blode was co-founder and CTO, responsible for the core product and engineering platform. ## Sources - [Fingertip joins Linktree](https://www.businessnewsaustralia.com/articles/linktree-acquires-emerging-melbourne-based-competitor-fingertip.html) - [Forbes profile](https://www.forbes.com/profile/fingertip/) - [Business News Australia coverage](https://www.businessnewsaustralia.com/articles/linktree-acquires-emerging-melbourne-based-competitor-fingertip.html) --- # VenueSafe case study > How Matthew Blode co-founded and built VenueSafe, a COVID contact-tracing platform that served more than 1M Australians and was acquired by me&u. *Co-founder & CTO · 2020-2021 · me&u / Mr Yum* Published May 18th, 2026 VenueSafe served more than 1M Australians during the COVID response and went from idea to acquisition by me&u in six months. ## Metrics - **1M+** — Australians served - **6 months** — Idea to acquisition - **2021** — Acquired by me&u - **3 repos** — Product stack ## Context VenueSafe was built during the 2020 COVID response, when venues needed a practical way to collect visitor details, support contact tracing, and stay operational under urgent public-health constraints. The product had to be fast, reliable, and understandable for venue operators and customers who had no patience for software friction. ## What I Built As co-founder and CTO, I built the product across a Craft/Vue marketing site, Express and MariaDB backend, React client, Stripe billing, analytics dashboards, and operational tooling. The work was intentionally pragmatic: ship the useful version quickly, keep the flow simple for venues, and handle the operational edge cases that emerged as the platform scaled. ## Outcome VenueSafe served more than 1M Australians and was acquired by me&u, then operating as Mr Yum, within six months of the idea. After the acquisition, I joined me&u as a senior software engineer, helped scale the platform to 15M+ users globally, and supported the US expansion from Austin, Texas. ## FAQ ### What was VenueSafe? VenueSafe was a COVID contact-tracing platform for Australian venues and hospitality businesses. ### Who acquired VenueSafe? VenueSafe was acquired by me&u, formerly Mr Yum, after going from idea to acquisition in six months. ### What happened after the acquisition? Matthew Blode joined me&u as a senior software engineer, helped scale the platform to 15M+ users globally, and supported the US expansion from Austin, Texas. ## Sources - [VenueSafe archive](https://venuesafe.netlify.app/) - [About Matthew Blode](https://matthewblode.com/about) - [All projects](https://matthewblode.com/projects) --- # Blog # AI can code but it can't design > AI agents write production code but can't see visual design. Why that limits them, whether AI will replace designers, and what comes next. *AI-assisted engineering* Published Jan 30th, 2026 We use Claude Code hard for frontend work, but it's a blind collaborator. It writes JSX, Tailwind, and animation configs fluently, yet has never seen the output of its own code. It can't tell if the result is beautiful or balanced. Based on conversations from early 2026 about AI coding agents, design tools, and bridging the gap between terminal-based AI and visual editing. ## The gap is perceptual, not technical Code generation is text-to-text. LLMs are built for that. Design is spatial and aesthetic, and they have no native sense of it. The difference between a good interface and a mediocre one is almost never in the code. It's [the spacing, the type scale, the visual rhythm](/blog/you-dont-have-to-make-ai-slop): things users feel but can't name. I made a font for my wife's interior design studio. Weighing the curve of a letterform, feeling whether the kerning breathes, is illegible to an LLM. The agent can set your font-family. It can't tell you why one typeface carries more warmth than another. ## Visual craft still needs human judgment When I built Shareful, I drew the logo myself: an abstract share arrow. The AI did most of the building. The logo was mine. Anything it generated would have been generic. Visual craft needs judgment that comes from seeing thousands of things and forming opinions about them. An LLM has read descriptions of beauty. It has never seen any. ## The floor moved for code, not design AI raised the floor for coding. In design it has barely moved. A junior developer with Claude Code ships production-quality code. A junior designer with AI tools still produces junior design. Turns out the bottleneck was never the typing. It's the seeing. The next leap is giving agents eyes: the ability to evaluate their own output, understand spatial relationships, form aesthetic opinions. Until then, design stays human work. ## Related - [You don't have to make AI slop](https://matthewblode.com/blog/you-dont-have-to-make-ai-slop) - [The Blode Stack](https://matthewblode.com/stack) --- # Build the tool you're too cheap to pay for > When building takes hours instead of months, build-versus-buy flips. Why you should build your own tools now that AI makes implementation nearly free. *AI-assisted engineering* Published May 25th, 2026 I wanted WisprFlow but did not want to pay for it, so I built Commandment, an open-source alternative with a BYO API key, in a night. Then allmd, to turn any URL into markdown. Then HackerTok. Same impulse each time: too cheap to subscribe, fast enough to build. Based on side projects shipped between late 2025 and early 2026 including Commandment, allmd, and HackerTok. ## The impulse I use [voice-to-text](/blog/voice-is-the-next-interface) all day. WisprFlow is good, and it costs money every month. So I built Commandment: open-source, bring your own OpenAI key, runs locally. Built it in one night. Exactly the tool I wanted, at fractions of a cent per use instead of a fee forever. ## The pattern repeats Then I needed web pages, PDFs, videos, and audio as clean markdown, to feed into AI context without copy-pasting. So I built allmd in about four hours. Turn the whole universe into a skill: that is the tagline. Then I wanted a better Hacker News client, with login, comments, upvoting, submitting posts. HackerTok happened the same way, Claude Code doing the heavy lifting while I steered. 308 GitHub repos now. Plenty are dead experiments. Every one tested an assumption or scratched an itch nothing else was scratching. ## The calculus has flipped Do not reinvent the wheel, the old wisdom says. That assumed the wheel took months and cost far more than a ten-dollar subscription. Not anymore. Ten dollars a month is $120 a year, $600 over five years, for a tool you do not own, cannot modify, and might see shut down or repriced any time. The alternative is four hours of an evening and a tool you control. **The subscription is a tax on your own inaction:** you pay because building felt too hard, and it does not anymore. ## The hidden advantage of owning it The real benefit is understanding. When you build it, you fix breaks in minutes, add the features you want, adapt when the upstream API changes. No waiting on someone else's roadmap. Commandment does what I need because I built it for my use case. No onboarding flow, no pricing page, no team dashboard. ## When not to build Some tools are hard: database engines, payment processors, auth with compliance requirements. You should not build Stripe. The test I use: can you ship it before the free trial expires? If yes, build it. If no, the subscription is probably earning its keep. Most developer tools and utilities fall on the build side now, and the threshold keeps moving as AI gets faster. ## The real point This is not about being cheap. The cost of building software dropped to hours. Turns out "do not reinvent the wheel" was never advice about wheels, it was advice about cost, and the cost fell out. ## Related - [Side projects](https://matthewblode.com/side-projects) - [About Matthew Blode](https://matthewblode.com/about) --- # Delete everything and start over > When rebuilding from zero beats debugging, deletion stops being waste and becomes editing. Treat the first version as research, then throw it away. *Shipping & execution* Published Apr 20th, 2026 Shareful.ai had repos for a Mac app, iOS app, Chrome and Safari extensions, a frontend, and a monolith database. Weeks of work. I deleted it all and rebuilt from scratch in one night with Claude Code Max 20x. Live before morning. Based on the shareful.ai rebuild in February 2026. ## Weeks of work, deleted in a night Shareful.ai was a Mac app, an iOS app, Chrome and Safari extensions, a frontend, and a monolith database. Weeks of work, and it had got tangled enough that I'd stopped being able to move in it. So I deleted all of it and started again from an empty folder. One night, Claude Code Max 20x. Live before morning. The second version was better in every way, and not because I got smarter at 2am. The first time I was guessing at what the product needed. The second time I knew. The old code carried every assumption I'd made. The new code carried only what I'd learned. The first build wasn't wasted. It was research. ## Deletion is editing Deleting a codebase used to mean losing weeks, so you held on and debugged. Now it means losing hours. **When [building is fast](/blog/ship-fast-or-die), deleting is just editing.** Hold onto broken code out of sunk cost and you're the one being irrational. ## Related - [Side projects](https://matthewblode.com/side-projects) - [About Matthew Blode](https://matthewblode.com/about) --- # Forcing normies into the terminal > Why Claude Code and the best AI agents live in the terminal, the most agent-friendly interface we have, and why that locks most people out. *AI-assisted engineering* Published Apr 2nd, 2026 They are just forcing normies into the terminal. That is my read on current AI coding tools: Claude Code, Codex CLI, all of it. Capable tools locked behind decades of Unix knowledge. The command line is the most agent-friendly interface we have, but most people cannot use it. Based on observations about AI coding tool accessibility from early 2026. ## The tribal knowledge problem You need to know what a PATH is. What a shell is. Why a command works in bash but not zsh. That is tribal knowledge, not skill. I set up Claude Code on my phone with Tailscale and Termius. Build from the couch, merge from bed. Getting there meant knowing Tailscale, SSH, terminal emulators, persistent sessions. Five years of nerd knowledge compressed into a weekend project, and none of it accessible. ## The arc back to plain text The internet went from plain text HTML with hyperlinks to bloated React SPAs, and now it is circling back to plain text markdown with hyperlinks. Dev tools are on the same arc, abstraction peeling away. The terminal is text in, text out, exactly what LLMs are built for. No DOM, no pixels, just streams of text both ways. ## The missing product v0 and Lovable got something right: people need visual feedback. But does anyone still start on v0 or Lovable, or is everyone on Claude Code from day one? Someone needs to build the bridge. **A terminal not made for nerds.** A real command line for people who have never typed `ls` in their lives. Not another IDE plugin, not another chat wrapper. Nobody is building it yet. ## Related - [The crafty context trick](https://matthewblode.com/blog/the-crafty-context-trick) - [The Blode Stack](https://matthewblode.com/stack) --- # From builder to angel > After two exits, joining Airtree's Explorer cohort flipped the table. Investors over-index on the founder, and seeing that made me a better builder. *Founding & investing* Published Jun 14th, 2026 I joined Airtree's Explorer cohort to see building from the other side of the table. Evaluating other founders' zero-to-one stories showed me things about my own I could not see from inside them. Based on joining the Airtree Explorer Cohort 10 in early 2026. ## Switching seats I joined Airtree's Explorer cohort in early 2026, a cohort of about 25 operators learning to angel invest: deal sourcing, due diligence, adding value beyond the cheque. Most of my career has been on the other side. Building, pitching, convincing someone to believe in the thing I was making. [VenueSafe went to me&u, Fingertip to Linktree](/blog/your-career-compounds), and there was a Forbes 30 Under 30 in there too. None of it prepared me for what happened when I stopped pitching and started listening to other founders pitch me. ## The gap between the pitch and the work Inside a startup you remember the chaos. A migration that almost killed a launch. An 11pm argument about the pricing page. Pivots nobody outside ever saw. Evaluate someone else's startup and none of that is there. You get a deck, some metrics, and a tidy story about getting from nothing to something. Sorting the signal from the narrative is harder than it sounds. You only feel the size of the gap once you're the one doing it. ## They pitch product, you watch the founder Founders spend the pitch on product: features, roadmap, architecture, what makes them different. I did the same for years. I thought that was the thing being evaluated. It mostly isn't. I kept catching myself watching the person instead. Can they survive eighteen months of things going wrong? Recruit, make hard calls fast, hold their nerve or change their mind at the right time? The product will change. The founder is the constant. Which meant a lot of the time I'd spent polishing features in my own pitches was time I could have spent showing judgement. ## Which parts were skill, which were timing From zero to one you remember making the best call you could with bad information, again and again, until something stuck. From the inside, product-market fit felt like barely keeping up with demand. Watching it from the outside, it reads as a clean line up and to the right. So you start asking which parts of your own story were skill and which were timing. The honest answer is more timing than I'd like to admit. ## Turns out it taught me nothing about investing Turns out the useful thing wasn't the investing. It was hearing how a founder's story lands on someone who wasn't there for the chaos. Once you've heard that, you tell your own more plainly, and the calls you make while building get a little sharper. Switch seats, even for a bit. The view changes what you notice when you sit back down. ## Related - [About Matthew Blode](https://matthewblode.com/about) - [VenueSafe case study](https://matthewblode.com/case-studies/venuesafe) - [Fingertip case study](https://matthewblode.com/case-studies/fingertip) - [Speaking](https://matthewblode.com/speaking) --- # High performing keyboards > The best keyboard for coding is the most underrated developer tool: mechanical switches, programmable layers, and split ergonomics. *AI-assisted engineering* Published Dec 26th, 2025 I type tens of thousands of words a week into Claude Code. When your workflow is prompt, review, iterate, the keyboard is the bottleneck you never think about. Here is my setup, and why the physical layer deserves the same attention as the software. Based on the developer hardware and workflow setup used throughout 2025-2026. ## The physical layer of your developer OS The software layer gets all the attention: agents, snippets, shortcuts. None of it matters if the hardware you touch ten hours a day is an afterthought. Most developers will spend weeks configuring Neovim and never once question the keyboard under their fingers. It carries every line of code, every prompt, every commit. ## Why keyboard performance matters when you code with AI The AI coding loop changed typing. Prompts, diffs, context docs, commits: the ratio of prose to syntax flipped. You type more words a day than you did writing pure code. [Voice might replace typing eventually](/blog/voice-is-the-next-interface). Until it does, the keyboard is the channel between thought and shipped product, and a fast one cuts friction you feel across a ten-hour session. ## What makes a keyboard high performing Not a buying guide. What actually matters: Low latency. Keypress to character should be imperceptible. Wired, or high-polling-rate wireless. Tactile feedback. Switches that confirm at the actuation point teach your fingers the threshold, so they stop wasting force. Programmable layers. Layers for navigation, symbols, macros. Same idea as Raycast snippets: compress multi-step actions into muscle memory. Split ergonomics. Arms rest at shoulder width instead of hunching inward for eight hours. Less strain, fewer breaks. ## The setup I use A Kinesis Advantage. Concave key wells curved to the length of each finger, columns instead of the staggered offset we inherited from 1878 typewriters, and thumb clusters that move the modifiers onto my strongest digits. Mechanical tactile switches chosen for actuation not sound, fully programmable, with a nav layer that keeps my hands on home row instead of reaching for arrow keys. Each choice saves fractions of a second. Over hundreds of sessions those become hours. Same idea as [shipping fast](/blog/ship-fast-or-die): the drag is often in the last place you look. ## Keyboard shortcuts are a design decision [Keyboard shortcuts for power users](/blog/you-dont-have-to-make-ai-slop) signal you thought about how people use your product. Same applies to your own tools. When I hit three keys and my full Claude Code prompt expands, that is a tactile switch at the right force, a firmware layer routing the input, an OS shortcut firing the expansion, an app executing the result. Most people optimise that top layer and ignore everything below it. ## The compound returns of physical tools A keyboard you use 2,000 hours a year is infrastructure. Your keyboard is either speeding you up or slowing you down, and most people have never tested which. ## Related - [The Blode Stack](https://matthewblode.com/stack) - [Side projects](https://matthewblode.com/side-projects) --- # Seventy people in a group chat > How VCMC grew from 3 people in a WhatsApp group to 70+ members, and the product thinking behind it. *Product & craft* Published Mar 26th, 2026 Luca Bonelli started a WhatsApp group and pulled Ryan Hendler and me in as co-founders. We wanted to share how we actually build day to day, not track AI headlines. It grew to 70 people and thousands of messages. Then Greg Brockman tweeted about us. Based on the growth of the Vibe Coding Micro Community (VCMC) from 2025-2026. ## Community is a product Most communities die because nobody treats them like one. Spin up a Slack, invite 200 people, watch engagement flatline in two weeks. VCMC had a constraint instead of a plan. Luca started a WhatsApp group and pulled Ryan and me in. We wanted somewhere to share what actually worked in our builds. Not AI news, not fundraising takes, not AGI timelines. Workflows, prompts, tools, failures, shortcuts. The stuff that saves you three hours on a Tuesday. Share what works, not what sounds impressive, and the signal stays high. ## The cold start problem Nobody wants to post in an empty room, or be first to share something vulnerable in front of strangers. So we were the first three users, and we used the product relentlessly. Real builds, real questions, real failures, every day. New people landed in a live conversation between builders who weren't performing, so it felt safe to contribute. One shares a prompt that halved their deploy time, another a Claude Code workflow that broke their staging. Both valuable because both are true. It grew to 70 people and thousands of messages with no marketing. We capped membership at 100. Every invite was personal: someone we had worked with, met at an event, or whose work we respected. ## People in a room The real test was the meetup. Our "Shipping with AI" event drew around 56 people, over a 50-person cap. Founders, operators, and engineers, most of them already active in the group. Then Greg Brockman tweeted about us, and the thing clearly had its own gravity. Meetups are a feature, not the product. The daily chat builds the trust. The event is where it shows up in person. ## Engagement loops, not announcements Communities also die when they turn into announcement channels. Someone posts a link, nobody responds, and soon the only people posting treat the group as distribution. We designed against that: conversations, not broadcasts. Share a workflow and three people say how they'd do it differently. Hit a wall and two offer to pair within the hour. That loop is the retention mechanic. People come back because their contribution matters and they get something useful back. ## Build the brand before you need it We built [vcmc.ai](https://vcmc.ai) with a proper brand page "in case the New York Times picks up on this group." Sounds like a joke, but it was serious product thinking. Website, visual identity, positioning, all of it existed before the Greg Brockman moment. When attention arrived, we had somewhere to point people, and looked like we'd been doing this for years, not months. ## What I learned Community building is [product building](/blog/you-can-sense-carelessness) with a different input: people and conversations instead of code and design. Same principles. Solve the cold start, design the loop, curate ruthlessly, ship and iterate. The group chat is still the core product. No algorithms, no feeds, no content strategy. Just builders talking to builders, and that turned out to be enough. ## Related - [About Matthew Blode](https://matthewblode.com/about) - [Speaking](https://matthewblode.com/speaking) --- # Ship fast or die > You do not win by being right, you win by finding out faster. On team shape, AI feedback loops, and shipping at 80 percent. *Shipping & execution* Published Jun 28th, 2026 Two startups, two acquisitions, one lesson: speed is a small team's biggest advantage. Not reckless. Think to 80 percent, ship, watch, and close the loop. Based on my January 2026 Startmate mentor session on Claude Code and shipping fast. ## The mindset I ran a Startmate mentor session in January on Claude Code and shipping fast. I opened with a line I repeat to myself: you do not win by being right, you win by finding out faster. Most teams treat being right upfront as the goal. Weeks scoping, debating architecture, polishing Figma, aligning stakeholders. By the time they ship, the market has moved or nobody wanted it. At Fingertip and VenueSafe we shipped early, watched real users, and iterated hard. Speed was survival. ## Invert the question Charlie Munger: invert, always invert. Do not ask how to ship faster. Ask what is making you slow. For us it was usually one of these: - Work blocked waiting on approval. - Meetings that exist out of habit. - Fear of shipping something imperfect. - Vague ownership, where nobody owns the outcome. - Optimising systems that do not need to scale yet. - Too many projects, too much context switching. None of that is technical. You fix it by changing the shape of the team, not by adding process. ## The team shape that ships The fastest teams I have been on shared a few things. One owner end to end, not a chain of handoffs between product, design, and engineering. Fewer meetings. Small, because communication overhead scales quadratically. A clear definition of done, or everything sits at 90 percent forever. And the builder close to the user, because secondhand feedback loses texture. ## Think to 80 percent, then ship You do not need full confidence to ship. Just enough to know you are pointed roughly the right way, then get signal from real users. The last 20 percent of certainty is the most expensive and the least useful. Teams burn weeks on edge cases that never happen. Ship at 80 percent and course correct with data instead of opinions. ## Building with Claude Code AI changed the speed equation for me, not because it writes perfect code but because it compresses the feedback loop. Claude Code writes, I review, I give feedback, it iterates. Dozens of times in an hour. When I start something new the loop looks like this: - Pick one tiny behaviour. Not a feature, a single user action. - Ask for a plan before writing anything. - When something breaks, paste the error, the context, the intent. - Show the result to one user. - Fix the first friction point, then repeat. It builds in layers, which matches how I think about product. Start with a Wizard of Oz where nothing behind the surface is real. Then a low-fi UI in code, the data model, API, back end, and finally front-end polish. Each layer ships and gets tested on its own. ## You do not need to make AI slop AI output is not automatically low quality. But carelessness shows. People can tell when a product was generated and left unedited. Generate a bad first cut, sand the rough edges, keep sanding until it feels right. The first draft is raw material. The craft is in the editing, same as always. ## Give AI a good setup AI works better with the right scaffolding around it. TypeScript gives it types to reason about. A linter and formatter like Ultracite keeps things consistent. Git lets you experiment and roll back. Logs give it context when it is debugging. If AI finds a change hard to make in your codebase, take the hint. The coupling slowing it down is slowing your humans down too. ## Ship fast, rollback faster Speed without safety is reckless, but safety does not have to mean slow. Bias towards action, ship small changes straight to main, and use pull requests for visibility, not as gates. If something breaks, [roll it back](/blog/delete-everything-and-start-over). Raise the quality bar only where mistakes are costly. Every standard costs a little speed, and that cost compounds. ## Do not guess what is broken Once you are shipping fast you need to see what is happening. Session replay, analytics, logs, alerts. Without them you are shipping fast and blind, which is worse than shipping slow. ## Anyone can ship The barrier to shipping a real product keeps falling. AI handles the parts that used to need deep specialisation. What is left is taste, clarity, and the willingness to put something in front of users before it is ready. That last part is uncomfortable. It is also how every product I built that mattered got built. ## Related - [Method (manifesto)](https://matthewblode.com/method) - [Speaking](https://matthewblode.com/speaking) - [VenueSafe case study](https://matthewblode.com/case-studies/venuesafe) - [Fingertip case study](https://matthewblode.com/case-studies/fingertip) - [About Matthew Blode](https://matthewblode.com/about) --- # Skills are the new packages > Claude Code skills and plugins are markdown files you install like npm packages: small, focused, composable units of capability, and the ecosystem is forming. *AI-assisted engineering* Published Feb 23rd, 2026 I made a skill that creates skills, then allmd to turn the universe into a skill. Then the pattern clicked: agent skills are composable units of capability the way npm packages are composable units of code. Based on building agent skills, shareful.ai, and allmd in early 2026. ## A skill is just a markdown file An agent skill is a markdown file: instructions in plain language, saved as `.md`, and your agent knows how to do something new. No API, no SDK, no build step. Distribution is the interesting part. `npx skills add mblode/agent-skills`, one command, and it is in your project. **This is `npm install` for agent capabilities.** I have built skills for Claude Code since late 2025, pulling out any instruction I repeat across projects: deployment patterns, review checklists, animation guidelines, into shareable files. ## The meta moment Then I built agent-skills-creator: a skill that creates skills. Then [allmd](/blog/the-crafty-context-trick), which turns any URL, PDF, video or audio into clean markdown, tagline "turn the whole universe into a skill." Then shareful.ai, Stack Overflow for AI coding agents, because the problems we solve with agents are not the ones we Google. Each felt standalone. They are one idea: build the ecosystem that makes agent capabilities shareable. ## The npm analogy In 2010, npm was a weird idea. Why install `left-pad` instead of writing four lines yourself? Because small, focused units compound into capability no single developer could build alone. Skills are on the same trajectory. One for database migrations, one for accessibility audits, one for performance profiling, and your agent is competent across domains you are not expert in. The early npm ecosystem was messy and exciting. Skills are that now: no dominant registry, best practices still forming. The people building skills today are the first npm publishers. ## MCPs are the other half MCPs are infrastructure for agents rather than humans: natural language APIs so bots can run commands. Stainless auto-generates SDKs and MCPs from OpenAPI specs, and that layer is standardising fast. Skills sit on top. The MCP provides the capability, the skill provides the judgment. ## The tension Here is what I keep wrestling with: even skills for CLI tools are mostly overkill, because Claude Code can figure it out. Give it a well-documented tool and it reads the docs and uses it correctly. So why do they matter? Quality and consistency. The gap between "the agent can do it" and "the agent does it the way I want" is real, and skills close it. Whether that gap shrinks to zero I do not know. Maybe skills are transitional: essential now, obsolete later. ## The open question Will skills consolidate the way npm did, with a dominant registry and standard format? Or will agents absorb them into their own intelligence? I do not know. The people who shaped npm's early ecosystem defined how a generation shared code. The people shaping skills today get the same shot. A bet worth making, even if the agents eventually eat it all. ## Related - [The crafty context trick](https://matthewblode.com/blog/the-crafty-context-trick) - [The Blode Stack](https://matthewblode.com/stack) --- # The crafty context trick > How to manage the Claude Code context window: feed better references, not better prompts. Mediocre and great output are fifteen minutes of context apart. *AI-assisted engineering* Published May 6th, 2026 Most people skip the crafty part, the initial context. Research papers, niche blog posts, specific docs, reference implementations. Feeding the right material in is the highest-value move you can make with AI coding tools. Based on workflow patterns from building with Claude Code and Codex throughout 2025 and 2026. ## The prompt matters less than what surrounds it I built an ASCII art renderer (now part of fx.blode.co) in a day. Not off a clever prompt, but by starting from a blog article on ASCII rendering and handing the whole thing to the agent. That article was the context. Then I built allmd so I could turn any URL, PDF, video, or audio into markdown and feed it in the same way. Most people refine their prompt for an hour when fifteen minutes finding the right reference would do more. **Better references beat better prompts.** ## Front-load the right material My Raycast snippet "zcc" expands to: "Do extensive research. Make a plan with phases and todos. Use a swarm of subagents and teams." Even that is just research before you build. The best result always comes from the attempt where I front-loaded the right material, never the first one. I run Brian Lovin's /simplify skill at the end of every session, so the agent grades its own output. The people who get the most out of these tools curate inputs instead of writing sophisticated prompts. The difference is almost never the model. It's the fifteen minutes you did or didn't spend gathering context before you hit enter. ## Related - [Skills are the new packages](https://matthewblode.com/blog/skills-are-the-new-packages) - [Forcing normies into the terminal](https://matthewblode.com/blog/forcing-normies-into-the-terminal) - [Method](https://matthewblode.com/method) --- # The internet came full circle > The web went from plain HTML to SPAs and back to markdown. This time the reader is an agent. *Product & craft* Published Apr 29th, 2026 The internet came full circle: plain HTML, then SPAs, now back to markdown. The difference is who's reading. First time humans, this time agents. Based on observations about the shift from visual web interfaces to agent-consumable markdown formats in 2025-2026. ## The arc nobody planned The web started as plain text. Tim Berners-Lee wrote HTML with hyperlinks and that was it: text pointing to text. Then we wanted interactivity. jQuery gave us dropdowns. Angular gave us SPAs. React gave us a virtual DOM that diffed against itself to render a todo list. Thousands of lines of JavaScript so a human could click a pretty button. Now the reader is changing. Agents want structured text, not animations, so the output is collapsing back to markdown. Plain text, then bloated SPAs, now plain text again. ## MCPs and Stainless An MCP is a natural language API: you expose tools, the agent calls them, things happen. No pixels. Stainless goes further. Point it at your OpenAPI spec and it auto-generates a typed SDK and an MCP server, for free. It is what OpenAI use. If your service has an API, an agent can already drive it. ## Why I built allmd I kept hitting the same wall. I wanted to feed something into an agent and it was trapped in a format the agent could not read: a PDF, a YouTube video, a webpage buried under JavaScript. So I built allmd in an afternoon. It takes any URL, PDF, video, or audio file and hands you back clean markdown. That is the whole tool. Turns out that is the shape of a lot of what I build now. Years spent on rich visual interfaces, and the useful thing is a script that throws the pixels away and gives an agent plain text. ## The reader changed **The web didn't get simpler or more complex. The reader did.** Heading levels, bold text, link labels: those were visual hierarchy for a human scanning a page. Now they are structure for a machine reading to understand. If your product cannot be represented as structured text, an agent cannot use it. That is already shaping what gets built. ## Related - [Side projects](https://matthewblode.com/side-projects) - [About Matthew Blode](https://matthewblode.com/about) --- # Voice is the next interface > I built Rubber Duck, a voice coding agent, because typing is the bottleneck when the listener speaks natural language. Voice cuts the translation layer. *AI-assisted engineering* Published Jun 2nd, 2026 I built Rubber Duck, a voice coding agent. A Todoist Ramble clone for Things 3 that streams audio to OpenAI Realtime with gpt-4o-mini and runs tool calls. Commandment, an open source WisprFlow alternative. Each started from one observation: typing is a bottleneck when the listener speaks natural language. Based on voice AI projects built between late 2025 and early 2026. ## Two voice tools, one annoyance I built Rubber Duck, a voice coding agent. It streams audio to OpenAI Realtime with gpt-4o-mini, runs tool calls, and drops what I ramble into Things 3. Then [commandment, an open source WisprFlow alternative](/blog/build-the-tool-youre-too-cheap-to-pay-for), in one night. Both came from the same annoyance: when the thing listening is an LLM, typing is the slow part. You feel it after using them for a while. Talking all day is uncomfortable in its own way, but I keep reaching for the mic instead of the keyboard. That is the tell. ## Voice removes the translation layer You do not work out how to type what you mean. You say it, and the agent does it. The friction in typing was never words per minute. It is turning a thought into structured input, and voice skips that step. When the listener is an LLM, the mouth beats the fingers for tasks, code, and controlling tools. Until voice tools mature, [a high performing keyboard](/blog/high-performing-keyboards) is still the fastest physical interface between thought and shipped code. ## The interface is collapsing Every tool I build now points the same way. Speech will replace typing for AI work. The only open question is how fast the tooling catches up to the demand, which is already here. ## Related - [Side projects](https://matthewblode.com/side-projects) --- # You can sense carelessness > AI raises the floor but flattens the result. Users sense carelessness before they can name it, so taste and editing still decide quality. *Product & craft* Published Feb 2nd, 2026 People can sense carelessness. They cannot see the code, but they notice when something feels rushed or stitched together without thought. Based on my February 2026 Next.js Melbourne talk about care, craft, and product quality. ## Care is visible in the finished product **You can sense carelessness.** You cannot see the code, but you notice when a page is slow to settle, when the copy is vague, when a form makes you guess. You are reacting to the experience, not inspecting the source. ## AI raises the floor, but it can flatten the result AI makes competent output fast. It also makes it easy to stop too early and ship the first plausible version: something that works but feels generic. - A fast draft is not a finished product. - Generated interfaces need more editing than most teams expect. - The closer a product sits to the user, the more obvious careless details become. ## What care looks like in practice Editing. Cut the awkward steps, rewrite the vague copy, tighten the motion, simplify the hierarchy. And be honest about where AI helps: it is great at momentum, less reliable at deciding what should matter most. ## Fingertip after the MVP: a series of 1,000 small iterations At Fingertip, care was deliberate improvement after the MVP shipped. Each change was small. Together they changed the whole thing. ### Static list to drag-and-drop grid The page editor was a static list. We replaced it with a drag-and-drop grid, giving users real control over layout. ![Page editor before: a static list of sections](/blog/you-can-sense-carelessness/design-before.png) ![Page editor after: a drag-and-drop grid with visual hierarchy](/blog/you-can-sense-carelessness/design-after.png) ### Sharing that matches reality The default share preview was the Fingertip logo. We swapped it for a live screenshot of the user's page via a headless render API. ![Social share before: generic Fingertip logo](/blog/you-can-sense-carelessness/og-before.png) ![Social share after: live profile screenshot](/blog/you-can-sense-carelessness/og-after.jpeg) ### Default shadcn to intentional system Central icons, custom typography, taller inputs, and a curated colour palette turned default shadcn into a considered design system. ![Form inputs before: default shadcn styling](/blog/you-can-sense-carelessness/outcome-before.jpg) ![Form inputs after: polished event settings with structured hierarchy](/blog/you-can-sense-carelessness/outcome-after.png) ## Why this matters to me My work sits between product, engineering, and design. VenueSafe under time pressure, Fingertip growing into a broader SMB platform, LinkApps at Linktree: the question stays the same. Does this feel right to the user? It is not about perfection, or polish for its own sake. Just enough care that the product feels deliberate. ## Related - [Method (manifesto)](https://matthewblode.com/method) - [Speaking](https://matthewblode.com/speaking) - [Fingertip case study](https://matthewblode.com/case-studies/fingertip) - [About Matthew Blode](https://matthewblode.com/about) --- # You don't have to make AI slop > What AI slop is and how to avoid it: better fonts, better icons, stolen taste, and relentless editing on your vibe-coded UIs. *AI-assisted engineering* Published Apr 30th, 2026 Everyone can tell when you vibe coded your app. Default shadcn, Lucide icons, Inter, glowing gradient borders. It screams that you shipped [the first thing the prompt gave you](/blog/ai-can-code-but-it-cant-design). It does not have to be that way. Based on my January 2026 Melbourne builder meetup talk about using AI tools without sacrificing product quality. ## The tools are table stakes I build with shadcn/ui, Tailwind, Motion, React, and Ultracite/Biome. So does everyone else, on the same defaults. The taste you layer on top is the advantage. ## Great artists steal Find a product with an irrationally tasteful UI and copy it. Right click, inspect, rip off elements until your version is identical. Screen record the interactions and step through them frame by frame. Point AI at their minified JS bundle to un-minify it and read the animation logic. You're training your eye on the gold standard, then pointing it at your own product. ## Simplicity above all else AI will go rogue: glowing borders, gradients, decorative illustrations, badges, tooltips, seventeen things nobody asked for. Delete most of it. If a paragraph can be a sentence, make it a sentence. If a sentence can be a label, make it a label. If a label can be removed, remove it. ## Use better icons Lucide is fine for prototyping but too light to carry a polished product. I use Central (iconists.co/central): considered strokes, tighter proportions. People feel icon quality without being able to name it. ## Add delightful animations Use motion.dev, and work through the animations.dev and devouringdetails.com courses. Keep them fast: most transitions between 0.2 and 0.3 seconds, prefer ease-out, animate transforms and opacity, respect prefers-reduced-motion. They should feel responsive, not try to impress you. ## Don't just use Google Fonts Default Google Fonts are typographic stock photography. Everyone recognises them, and they say nobody made a choice. Inter on everything is the same tell. Find a typeface that suits your product on Typewolf and track it down; plenty of great fonts live on GitHub. Typography is one of the highest-impact things you can change, and engineering-led teams almost always underinvest in it. ## Learn from products with restraint Study products that feel calm instead of feature-stuffed: Zed Editor, OpenAI, Mintlify, Raycast, Linear, Things 3, Family Crypto Wallet, ElevenLabs. They show only what matters and their interactions feel precise. Copy that. ## Go the extra mile The last ten percent is where most people stop. Push there. - A dark mode-aware SVG favicon that adapts to the user's system. - Dynamic OG images so every page has a proper social preview. - Polished hover and active states on every interactive element. - Proper SEO metadata per page: title, description, canonical URL. - Keyboard shortcuts for power users. None are hard alone. Together they separate a weekend project from something that feels cared for. ## Death by a thousand tweaks The real work is the five hundred small improvements after the first version. Sand it, feel the grain, get a splinter, sand again. Nothing replaces the willingness to keep going. **AI gives you a fast start. What you do after decides whether you shipped something worth using or just more slop.** ## Related - [AI can code but it can't design](https://matthewblode.com/blog/ai-can-code-but-it-cant-design) - [Fingertip case study](https://matthewblode.com/case-studies/fingertip) - [The Blode Stack](https://matthewblode.com/stack) --- # Your career compounds > Why the biggest career advantages come from stacking high-learning environments, not individual wins. The decisions behind VenueSafe, Fingertip, and Linktree. *Founding & investing* Published Jun 16th, 2026 I started working the day after high school. No plan, just a want to learn. Every role since got picked the same way: learning velocity over comfort. Careers compound like interest, but only if you keep reinvesting. Based on LinkedIn posts about career compounding and the Fingertip acquisition story from 2025. ## The day after high school I walked into Expense Check and started building software the day after I finished high school. No plan, I just wanted to be somewhere that expected output from day one. Every role since got picked the same way: whichever one I'd learn the most in, the fastest. ## VenueSafe, in six months VenueSafe went from idea to acquired by me&u in six months. It was COVID contact tracing, so it was urgent, and urgency strips out everything that slows a team down. No planning cycles, no alignment meetings, no architecture debates. We built, shipped, watched, fixed, every day. You don't learn to move that fast from a project manager's deadline. You learn it when real people need a real thing and the clock isn't negotiable. ## me&u, at 15 million users After me&u acquired VenueSafe I scaled mobile ordering across their platform: 15 million users across multiple countries, plus the US expansion out of Austin. Every assumption I had got stress-tested. A query that's fine with a thousand users falls over at a million. Turns out elegance isn't clever code. It's boring systems that don't wake you up at 2am. ## Fingertip Then I co-founded Fingertip with Olly Hoffman, alongside Gabby and Hezi Leibovich: websites, bookings, and payments for small businesses across more than 100 countries. VenueSafe and me&u were the prerequisites. Without the urgency we'd have over-planned it. Without the scale instinct we'd have built something that broke the moment it grew. Fingertip needed both, plus a way of thinking in platforms instead of products. A product solves one problem well. A platform sets up the conditions for a lot of problems to get solved, which sounds abstract right up until you're making architecture calls that constrain the next three years. ## Then Linktree bought it When Linktree acquired Fingertip, [people treated the acquisition as the goal](/blog/from-builder-to-angel). It wasn't. It was a byproduct of the skills, the team, and the product all reaching a point where they were worth more at a bigger scale. Now I'm Co-Head of LinkApps at Linktree, building for 70 million creators. The urgency from VenueSafe means I don't waste cycles. The scale instinct from me&u means I build things that hold up. The platform thinking from Fingertip means I see how one feature connects to the rest of the ecosystem. ## Under all of it is clarity One skill carried across all of it: clarity. Knowing the user problem, the first useful version, and what to ignore for now. The environments changed completely. That never did, and zero to one always came back to it. ## The compounding part Every role where you coast is a year of zero returns. Every role where you're a little overwhelmed is a year of high-interest deposits. Returns from urgency stack on returns from scale, which stack on returns from platform ambition. You can't buy it or shortcut it, you earn it by showing up to hard environments for years. **So pick the role that scares you slightly more than it excites you.** That's where the rate is highest. ## Related - [About Matthew Blode](https://matthewblode.com/about) - [VenueSafe case study](https://matthewblode.com/case-studies/venuesafe) - [Fingertip case study](https://matthewblode.com/case-studies/fingertip) - [Speaking](https://matthewblode.com/speaking) --- ## Agent discovery - Sitemap: https://matthewblode.com/sitemap.xml - llms.txt: https://matthewblode.com/llms.txt - llms-full.txt: https://matthewblode.com/llms-full.txt - RSS feed: https://matthewblode.com/feed.xml - API catalog: https://matthewblode.com/.well-known/api-catalog - Skills index: https://matthewblode.com/.well-known/agent-skills/index.json - MCP server: https://matthewblode.com/mcp - MCP discovery: https://matthewblode.com/.well-known/mcp.json Any page on this site returns markdown when requested with `Accept: text/markdown` or by appending `.md` to the URL.