Three Figures Capital

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into a practical guide on how to actually build with Kimi find it below

Singapore’s Foreign Minister, Dr Balakrishnan casually explaining how he built his own AI agent (a 2nd brain for diplomacy) using Claude & WhatsApp integration etc. on a Raspberry Pi “You cannot govern a technology you have only been briefed on.” 🇸🇬

This Chinese guy created agents in Claude Code for landing pages and single-handedly serves 47 small businesses a month, taking $400 from each. He built a system of 7 agents on Claude Sonnet 4.6 that analyzes Google Maps in small towns, finds small businesses without websites there, and over 1 weekend takes each one to a finished mockup with video and cold message. No assistant, no sales team, no SDR. Just him, a MacBook, an iPhone, and 1 API key. And traditional web design agencies keep teams of 8 people on salary for the same order flow, while his expenses are only tokens and subscriptions to Lovable, Higgsfield, and Calendly. 7 agents work through 1 orchestrator on Claude Code Router. Usage is about 3 million tokens a day, the average API bill is about $480 a month. All 7 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions, and 1 of them lives right in the iPhone and picks up positive replies from the subway, a taxi, or on walks. And here is the system prompt he put into the orchestrator before launch: "You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes. sub-agents: // Scout (walks through Google Maps in selected cities, looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings) // Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words) // Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap) // Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom) // Pitcher (sends a personalized cold message through the right channel for the niche: email to roofers, SMS to tradesmen, IG DM to salons, LinkedIn to realtors) // Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending) // Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go). You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds $3,000 or the reply rate in a niche for the day drops below 12%." Meaning the system knows what it is and within what boundaries it is allowed to act. It knows it is supposed to find leads on its own. It knows it is supposed to take each one to a mockup, video, and cold message without intervention. It knows the human only steps in when a deal goes above $3,000 or the reply rate stops converging. → The system runs 24 hours a day → Scout goes through about 220 local businesses on Google Maps per day and leaves 30 new leads in the queue → Diagnoser outputs 30 structured diagnoses + briefs + cold messages per day → Builder assembles 3 to 5 finished landing pages in Lovable for the sharpest leads → Filmer renders a 10-second vertical video in Higgsfield for each one → Pitcher sends 30 personalized messages per day across 4 channels with a reply rate of about 14% → Checker runs every message through evals before sending And only when a deal breaks $3,000 or the reply rate for the day drops below 12% does the orchestrator wake the owner. And when the owner at that moment is sitting in the subway or a taxi, the Mobile agent in his iPhone picks up 1 move on its own: replies to a fresh positive reply from a dentist, books a Zoom through Calendly synced to the local time of the client, and puts the lead back in the queue. The owner only has to tap "approve" and in just 10 minutes join the call. Here is what the system writes in his log during 1 of the Saturdays: "scout report: 218 businesses checked in Austin, Denver, and Miami, 34 without a website, 19 with a website from 2014, 6 with an active redesign request in reviews. passing top 30 to diagnoser." "pitcher: 30 cold messages sent across 4 channels, 14 replies, 5 positive, 3 Zoom calls booked for Sunday. passing to closer." "builder: landing page for Westside Cosmetic Dentistry built in Lovable, 5 sections, mobile, soft beige. URL placed at /Users/dev/maps-agency/clients/westside/v1. filmer launching Higgsfield." "eval flag: deal with The Lotus Salon at $3,400 exceeds the approved limit of $3,000. sending for manual review." He has no server of his own and no separate backend. Just a local file sandbox at /Users/dev/maps-agency, an MCP router, 1 API key to Claude, and the same key forwarded to Claude Code on his iPhone. Out of everything I have seen this year, this is the cleanest one-person agency for selling websites to small businesses: $480 a month on the API, about $18,800 into the account, and between them 7 prompts, 1 file system, and 1 phone in the pocket.

Luna Classic Community The Big Picture on Binance’s Role for $LUNC👇 Thanks to @Masterincryptoo -> We see you. We see the accumulation patterns, the deposit flows, and the strategic positioning. Far from a negative — it’s a sign that a major institution sees long-term value in keeping Terra Classic functional. They hold the keys to massive potential burns, recovery mechanics, and ecosystem revival. Dig deeper: Back in 2022-2023, @btcturk funneled approximately 1.1 TRILLION LUNC to Binance’s old deposit address (ending in EHT5). ~870B of that with the repeated memo 106125745 The rest in other batches These weren’t random transfers. They look like coordinated transfers — possibly client withdrawals, internal moves, or liquidity provisions landing straight into Binance’s ecosystem. — and the numbers point to one dominant player: Binance estimates floating around 80-90% of circulating supply. It’s the reality of a massive exchange that stepped up during the Terra collapse, absorbing huge volumes when others stepped back. They became the primary liquidity hub for $LUNC and $USTC. This isn’t blind trust. The community is watching on-chain data closely (wallets, memos, flows). Transparency matters. $LUNC holders aren’t going anywhere. Smart money positioning for whatever comes next — whether that’s a phoenix revival or continued steady support.

Anthropic's Head of Product for Claude Code just explained how they ship in days — not months. 30 minutes. Free. More useful than every product strategy course you've ever bookmarked. Save this. Watch it tonight.

No sponsorship here. Just reading what the numbers say. Looking at $WASABI Token data from April 23, 2026: -> Price move: Up 35.89% in the last 24 hours. Strong momentum in a single day. -> New wallets: 22% of total supply now sits in fresh wallets. That’s a clear sign retail buyers are jumping in recently. -> Public figure holdings: 32.83M tokens are held by public figures. Suggests community hype is doing more to push price right now than big institutions. More breakdown coming soon... @Raejessica34 @EtherealGirl24 @MTSonAnon If you want to analyze a project or token, kindly drop the ticket below or Dm

This guy does $20 million/yr with his agency and just broke down the psychology of high-ticket closing:

If you want a smart way to practice this, read the following:

THIS IS INSANE!! some 22/yo kid killing the entire vibe coding industry.

I might be a massive conspiracy theorist person here but, as a British person accents are really really noticeable. You can discern and notice any slight small changes. I think Cobie is using some sort of sound distortioning device here to maybe prevent AI scam/hackers from repurposing his voice. There's even some American speech/accent patterns coming through. I dunno, something just sounds off.

These are cool! I think most companies will want to use them.

Claude Design in 60 seconds: One session. Five outputs: 1. Logo concept. A polished direction for your visual mark, ready to refine. 2. Color palette. Core brand colors, supporting neutrals, and a usable mood board. 3. Social assets. Launch graphics, post visuals, and campaign-ready layouts. 4. Landing page copy. Hero message, CTA, sections, and conversion-focused structure. 5. Brand brief. Tone, audience, positioning, and next moves in one concise doc. No Canva. No Figma. No designer on retainer. Describe the goal. Refine in conversation. Export when it feels right. Full breakdown in the article below.

最近不少人求各种抓妖币的AI 工具 实际上 OKX 免费开源的就已经秒杀市面上的AI工具了 我个人觉得最实用的是 OI × 价格四象限判断 Ai根据OI和价格的实时变化，直接给你四个清晰的象限结论 OI涨+价格涨 = 新多头在悄悄建仓；OI涨+价格跌 = 空头在加仓砸盘；OI跌+价格涨 = 多头获利了结；OI跌+价格跌 = 空头在平仓离场 Agent一句话就把逻辑+历史胜率全甩出来，附上Delta%和USD变化量 除了四象限，OKX Agent Trade Kit里还有「情绪雷达」和「市场筛选」两大Skill，组合起来才是真正的降维打击 情绪雷达的数据源会过滤掉无用的推特内容，独家锁定全球3万+加密核心KOL。新闻也聪明，同一件事六家媒体报，它自动去重合并，只给你一条核心摘要，不会浪费token 全链覆盖，不光CEX币，Web3全链甚至关联美股全看，一个入口搞定 再说「市场筛选与持仓量分析」 选币环节彻底简化 以前市场上几百个币中抓一个潜力币很难，现在一句话就行：“帮我筛 OKX 里过去 4 小时成交额靠前、资金费率正向且持仓量增加的低市值币” 这三样东西放一起简直夯爆了，抓妖币手到擒来！

Releasing designdotmd.directory. More than a hundred design.md to choose from for free with desktop and mobile previews, kitchen sink design system samples, filters by category and search. Also accesible through the CLI `npx designdotmd add gym-kettlebell`.

This 2 hour video by Andrej Karpathy (co-founder of OpenAI) will teach you more about using LLMs than every AI tutorial you've watched this year combined. Bookmark & watch tonight, it will change the way you use AI forever.

every billion dollar brand on the internet is now a file you can fork. google JUST open sourced design md and people already reverse-engineered huge brands into it. 5 plays to run THIS WEEK before everyone catches on 🧵 x.com/stitchbygoogle…

Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see. @eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)

is designers cooked??

CLAUDE CAN NOW BUILD GOOGLE AND META ADS DASHBOARDS IN 30 SECONDS. Connect it once, and it can pull the data, make account changes, schedule recurring tasks, and even start generating creatives.

This guy is shipping free value harder than Anthropic, and y’all still sleeping Please stop sleeping Thank you