Build "Mini-scribe" — an AI meeting notetaker on Claude using Minimi: Before you paste this: you need (1) the Minimi memory connector installed and your laptop online, and (2) an environment that can create live artifacts (e.g. Claude Cowork). A strong model helps — this is a one-pass build. Paste everything below this line. Build me a live artifact called Mini-scribe — a Granola-style AI meeting notetaker that runs entirely on my Minimi memory. It's a self-contained, light-mode HTML page (inline all CSS/JS, :root{color-scheme:light}) that pulls fresh from Minimi each time it opens. Brand it "Mini-scribe · built with Minimi". Design: off-white background, dark text, green accent; sidebar main panel. Don't build a page-reload button (the artifact header has one). Use my Minimi tools via window.cowork.callMcpTool(...): meeting_memory (actions list, get_context), list_active_threads, and search_memory. Use window.cowork.askClaude(prompt, data[]) for all AI generation. Probe first. Before coding, call each tool once and build parsers around the ACTUAL responses — Minimi returns markdown, not JSON. Expect these shapes (verify them yourself): Every response may start with an italic line _User local time: ... (timezone)._ — skip it. meeting_memory list → ### N. Title blocks with - **App:**, - **Thread ID:** (UUID), and — only for real calls — - **Started:** (ISO UTC) - **Duration:** ("1 min", "1 hr 5 min"). Plain chat threads appear in the same list WITHOUT Started/Duration. time_range accepts {day:"YYYY-MM-DD"}; limit caps at 20. meeting_memory get_context → ## Title, the same fields, then ### Transcript with the transcript inside a ``` code fence. Lines are tagged [You] / [Others]. The ASR is noisy: mixed English Hindi, garbled words, and the same sentence often ECHOED on both speakers' lines. list_active_threads → ### N. App / ThreadName blocks with - **Last updated:** - **Preview:**. Thread names can be URLs — split app/name on the FIRST " / " only. Takes time_range:{from,to} in epoch ms. search_memory → ### Result N blocks with - **Source:** App / Name, - **Captured:**, optional - **Memory:** gist, and a - **Context:** code fence. time_range supports {day, between:{from:"HH:MM", to:"HH:MM"}} — between cannot cross midnight, so split windows that do. Read results defensively: r.structuredContent ?? JSON.parse/r.content[0].text style, tolerate missing fields. Requirements Calls only. Keep a meeting only if it has BOTH a start time AND a non-zero duration. Exclude plain chat threads; drop 0-minute recordings. Beat the 20-item cap. Recent chats bury older calls in list. Fetch one day at a time ({day:"YYYY-MM-DD"}, limit 20) across the window, with a small concurrency pool; dedupe by thread ID; sort newest-first. Load-more paging. Start with the last 10 days. A "Load 10 more days" button fetches the next 10-day window and appends, showing days loaded. A whole window with no new calls → "No more calls", stop — but NEVER treat an offline response as "ended" (see 9). Group-by switcher in the sidebar (top of the drawer, full-width tabs): Date (default, Today/Yesterday separators), People, App, Theme. Theme = 1–2 word category from one AI pass over titles. Resolve People/Theme lazily on first select with a progress state; cache in localStorage. Per-call notes fused with screen context. On open: fetch the transcript AND screen context via search_memory (query = call title, window ≈ 5 min before start → 90 min after end, midnight-split). Pass BOTH to askClaude; demand STRICT JSON: {summary, keyPoints[], actionItems[{who,task}], decisions[], followUps[], resources[{label,url}], related[{name,note}]}. Instruct it to: use screen context to fix garbled transcript terms (names, companies, numbers → the on-screen spelling); weave genuinely related on-screen activity into the summary; capture follow-ups that already happened right after the call; drop unrelated tabs. Render Granola-style; Follow-ups/Resources(clickable)/Related sit behind a persistent show/hide "screen context" toggle. Cache notes per thread in localStorage; add "Regenerate". Parse the AI reply leniently (strip fences, first-{-to-last-}, retry once). Transcript tab with color-coded [You] vs [Others] bubbles, plus: ⧉ Copy — copies the visible version with a title/date header and real speaker names. Make it sandbox-proof: try a synchronous hidden-textarea execCommand("copy") INSIDE the click gesture first, then navigator.clipboard, and if both are blocked open a modal with the text pre-selected for ⌘C. ✨ Enhanced view (Raw | Enhanced toggle) — an AI cleanup pass fed the transcript screen context the notes summary: correct mis-heard words to on-screen spellings, merge/drop echoed duplicate lines (attribute each sentence to the actual speaker), fix punctuation/casing, keep Hindi as Hindi, never invent or summarize. Output plain [You]/[Others] lines. Chunk long transcripts on line boundaries (~6k chars) with progress; validate output (tags present, ≥25% of input length; one retry) and never overwrite a good transcript with garbage. Cache per thread; offer Redo. ✎ Fix words — user-editable corrections for mis-transcribed words (names, companies, products — e.g. "Shrum → Shram"), scoped per-call or all-calls, persisted, removable. Case-insensitive with Unicode word boundaries (Devanagari-safe, must not corrupt longer words). Apply display-time to titles, every notes section, both transcript views, copies, and chat answers (instantly, even cached ones), and to everything sent to the AI — but never to the user's own typed questions or URLs. Ask tab — chat that answers questions from ONLY the selected call's transcript via askClaude, with brief Q&A history. Participant identification ("With: ___"). Blend three signals: (a) greeting/vocative in the opening lines, English or Hindi ("Hey Sara", "हां, आर्यन") — strong; (b) a contact's personal DM thread active around the call via list_active_threads (~10 min before → 75 min after) — ignore group chats, channels, and web/app entries; (c) the title. Greeting matching a thread name = high confidence; voice notes with no counterpart = "—". Show an editable "With: name · source" line; manual edits persist in localStorage and override the AI. The People grouping must use this resolved participant and read transcripts (batch: fetch transcripts with a pool, then ONE askClaude call for all unresolved calls). Offline handling. Minimi is local-only: when the laptop is asleep/offline its tools return text like "device is not currently connected / must be running and online". Detect that (regex on response text), show a "laptop offline" banner with Try-again wired to retry the failed operation, and never mark the list ended or show a false empty state because of it. In-app ↻ refresh — re-queries the last ~3 days, merges without losing loaded history, spin state " N new" / "Up to date" flash. Hide calls. Hover ✕ on a sidebar item hides it (persisted); footer shows "N hidden" which toggles revealing them dimmed with an ↩ unhide button; hidden calls are excluded from groups, counts, and AI passes; handle the "everything hidden" state. Sidebar chips: per-app colored dot app name time duration ( participant when known). Engineering bar. One <script>, no external libraries, event delegation (artifact CSP-friendly), escape all injected text, all caches namespaced in localStorage with try/catch, transcripts cached in memory only. Before publishing: extract the JS, syntax-check it (e.g. node --check), and unit-test the markdown parsers against the real probed outputs. Finally: publish it as an artifact, listing only the three Minimi tools you actually called.Progress10 of 10Probe Minimi tools to capture actual response shapesBuild Scribe HTML artifact with all featuresVerify JS parses and publish artifactAdd transcript copy AI-enhanced transcript viewAdd hide/unhide for callsAdd name-fix (find/replace) for transcriptsGeneralize to word fixing across title, notes, chatMake transcript copy bulletproof in the sandboxMove group-by switcher into the sidebarWrite shareable build-prompt for Mini-scribeWorking foldermini-scribe-prompt.mdscribe.htmlContextConnectorsminimi

@mcuban @GoogleCalendar w #GoogleMeet In @gmail w/ #videoConf w #SharedScreen & body stating #Actionitems #links,#reminders b4. I avoid #email like the #plague 8-10hr? 1k 📧?#GCalendar 20-100 Items, 50-100 #Sms/day,4 #Gmeets,10 #GoogleVoice,1-3 Events #IRL=5hr! 2K=10hr>over 24hr.

4/ TURN NOTES INTO ACTIONS → ActionItems pulls a clean task list right after the call → Share outcomes while the conversation is still fresh 5. AUTOMATE THE HANDOFF → Push outputs to Slack, CRM, or tasks → Meetings shouldn't die in a notebook

Measuring real progress matters. Track three simple things this week: minutes spent on post-meeting documentation, action-item completion rate, and how drained you feel at 5 p.m. Most professionals see 30% improvement in the first 7 days once they baseline it. Small numbers, massive freedom. Who’s up for a quick 7-day challenge? Comment “I’m in” and I’ll cheer you on! #PlaudNotePinS #AIMeetingNotes #AIProductivity #ProductivityHacks #WearableAINotetaker #ActionItems #ProfessionalProductivity pin.it/2bwPzubIW via @pinterest

Tasks were assigned. Ownership was unclear. 📘 Death Engine Protocol — a.co/d/caWsasc 📘 Japanese Robots Love to Dance — a.co/d/a0j61vI #ActionItems #MeetingCulture #CorporateDystopia #OfficeBurnout #RobotsWouldntSurviveThis #UnsubconsciousRobot #DarkHumor

I do not repost my own tweets often, but this one is very, very important. #ActionItems

What were the #outcomes of such a long #pc ?? Any #publicrepresentation should be evaluated basis the #actionitems emanating from it rather than duration !! #Quality #India #Maldives #Presidentmohamedmuizzu

Transparency might be the appetizer, but we're still waiting for the main course @seraphagent. It's time to see who's actually cooking in the kitchen and serving up those tangible actions. Show us the recipe for progress and who's on chef duty #ProgressOverTalk #ActionItems

My transcription app fed me these #actionitems post-interview, thank you to AI for continuing to #innovate

⚠️ Social media impact on athlete mental health: #RealityCheck #BJSMEditorial covering the benefits, the harms and the need for more research and education in this area 🔍 What should you be doing? 🤷‍♂️ See the #ActionItems ⬇️ 👉 bit.ly/3ORdZaB http

Meet @MilaAtmos, the amazing host of @futur_hindsight. ➡️ Read the full Q&A: democracygroup.org/blog/meet… #podcast #democracy #futurehindsight #CivicLife #EverydayPeople #ActionItems

⚠️ Social media impact on athlete mental health: #RealityCheck NEW #BJSMEditorial covering the benefits, the harms and the need for more research and education in this area 🔍 What should you be doing? 🤷‍♂️ See the #ActionItems ⬇️ @Mputukian team 👏 👉 bit.ly/3ORdZaB

7/ 📊 Action Items and Key Considerations 📈 As we digest the CPI report and navigate the uncertainty, here are some action items to consider, from analyzing political rhetoric to monitoring market reactions. Stay informed, stay ahead. 💼🌐 #MarketAnalysis #ActionItems

Sup founders, VCs are saying no to you for many reasons. If you pass the first meeting, it’s essential to understand the risk factors VCs consider when evaluating your deal. Here are some top risk factors and actionable insights to help you navigate these challenges: 🎯 Market Risk - Ensure your target market is $1B and growing. Demonstrate thorough market research that makes it easy for VCs to believe your market is VC backable. Action: Make sure you are solving a real pain that it’s worth solving at scale. 🧗‍♂️ Execution Risk - Showcase your ability to execute your plans. VCs want to see a strong team with a track record of success and a clear plan to perform on a roadmap. Action: Build a diverse team with relevant expertise and show them you can execute together by demonstrating traction. 💰 Financial Risk - Provide realistic financial projections and a clear path to profitability. These days, VCs need to see a sustainable business model. Action: Highlight your unit economics and show strong gross margins that support sustainable long-term growth. 🔍 Competition Risk - VCs don’t like saturated markets with easy-to-copy business models. So make sure you can clearly define who your competitors are and why you will be the winner who takes it all. Action: Prove you can outperform, differentiate from your competition and build a moat around your business. ⚖️ Legal and Regulatory Risk - Don’t be another SBF at FTX. Diligence is back in fashion. So ensure you have your legal boxes checked and comply on all fronts. Action: Consult with legal experts and let them do their jobs, it costs money but allows you to be fundable. 🌐 Technology Risk - Showcase your technology and its ability to scale and retain customers. Be prepared to defend your tech capabilities and can handle an audit. Action: Build a capable technical in-house team, maintain up-to-date documentation, and give credit to where credit is due (open source libraries). 🎲 Timing Risk - Is your tech and sector hot right now? Timing is critical. Just ask the crypto peeps who are working on AI now about timing… Action: Monitor market trends and be ready to pivot or adapt your offering as needed. By addressing these risk factors and implementing these action items, you'll be better equipped to attract venture capital investment and navigate the challenges ahead. If you’re looking to see which VCs are a good fit for your company, be sure to check out Thunder. #VC #RiskFactors #StartupFounders #Entrepreneurship #ActionItems

I'd like to review veterinarian literature describing STLV (SIV) prior to the crossing. A Stanford colleague says this is the case, but I've yet to track down citations. #ActionItems #MissionObjectives

I just published Top Tips for Running a Successful Online Business link.medium.com/rilyDXPxNBb Enjoy the article🙂 #template #business #ai #jedaai #agenda #coldsales #scripts #actionitems #decisions #share #jedaai #ai #chatgpt #generativeai #wireframe #workout

MprooV is a game changer. We breakdown topics into digestible, custom Action Items. You can take them on anytime, anywhere, at your own pace. Self-improvement that improves with you! #ActionItems

The #SupremeCourt decisions provide great momentum. But not just to celebrate and dance. We have to harness this momentum and codify these decisions with #ActionItems in #RedState legislatures. Today’s #CRpodcast w/ Daniel Horowitz @RMConservative podcasts.apple.com/us/podcas…