Tuan Anh Ta

anthropic research lead: “99% of our engineers use 300+ AI agents working together.” “close the loop. let the AI check its own work.” in a 20-minute talk, an Anthropic team member explains how to build AI agents that can improve themselves. the setup uses Claude with loops, plan mode, and smart workflows. it’s better than most $300 AI agent courses. bookmark this and watch the talk. then read the article below.

Karpathy method + Claude Code reading your whole Obsidian vault is the smartest second brain on earth. The method is simple and brutal. If you can’t build a thing from scratch, you don’t know it. Tutorials are fake learning and your brain deletes them in 3 days. Most people ignore this. They build a second brain that just sits there, folders of notes nobody reopens, dead text. Point Claude Code at the vault and it wakes up. 5,000 notes, one mind. It reads all of it and answers in your own words and your own proofs, not a model’s guess. Then the loop closes. Want to understand neural nets? Skip the 3-hour video and ask Claude Code to build a tiny one. 200 lines from scratch. Watch it train, break a layer, watch it fail, fix it. It clicks in 20 minutes instead of 3 weeks. The second it lands the note gets written. One idea per file, linked to 10 others, dropped into the vault while the memory is still hot. Now it compounds. Month 1: is 60 notes. Month 6 is 900. Every new note pulls in old ones, so you ask anything and the answer comes from your brain, not the internet. Before: 40 tabs, 6 half read PDF, 0 retained. After: build it once, own it for life. Setup takes 4 minutes. Plain text, no lock-in. A second brain nobody reads is a graveyard. Yours just started thinking.

today we're launching @Palmier_io, a video editor Claude can edit. use AI to edit, organize, and generate footage directly in the timeline. finally, a video editor built for AI. open-source. mac native. available now.

SOMEONE JUST DOCUMENTED EXACTLY HOW THEY HIT $17,000 MRR BY ROUTING LLM TRAFFIC THROUGH CLAUDE 4.8.Not a theory. Not a course selling you on the idea.A step by step breakdown of the exact system that generated $17K in monthly recurring revenue. The traffic source. The Claude 4.8 setup. The conversion architecture. Every step documented. Read this and Bookmark it now.

This is incredibly scary.

Anthropic CEO: "we got seven more months." the bet was a $1B one-person company by end of 2026. two-person AI companies already crossed $1B, one-person companies are past several hundred million. not everyone can make a $1B company. but a $10K MRR AI agent company is on the table. this guy dropped the exact roadmap. Bookmark this and start this weekend.

Anthropic just leaked their 2026 agent roadmap in 22 minutes. Claude team walked through tools, memory, observability, and the things most builders are 12 months behind. The last 3 minutes alone are worth the watch. Watch it, then save the setup below 👇

How to run paid ads with an agent in 2026. > Claude Cowork researches competitor ads in Ad Library. > Higgsfield MCP generates creatives. > Upload visuals to Ads Manager. > Meta MCP launches ads and reads performance. > Winners scale via Higgsfield MCP. > Runs every Monday.

3-month-old Shopify store is printing $412,000 a month, and the whole thing runs on Claude. Shopify connected directly to Claude on May 4th. You type the order. The store updates. Products, descriptions, ads, collections - all from a chat window. He didn’t hire a developer. Didn’t pay a copywriter. Didn’t touch an ad agency. Store setup - $0. 40 product descriptions - $0. Full ad campaign - $0. First month - $412,000. 605% growth. 4,086 orders. Now Shopify is offering him $250,000 in capital to scale faster. He opened the app to check his stats. Got a new order before he finished reading them. Then went back to configuring his BMW M3. Most people are still paying $15,000/month for a team to do what Claude does for $20. $412,000 a month. A BMW on the side. 3 months. Do the math.

Instead of watching an hour of Netflix, watch this 2 hour hour Stanford lecture will teach you more about how LLMs like ChatGPT and Claude are built than most people working at top AI companies learn in their entire careers.

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.

Claude is INSANE for ad creative research. I've built a file with 5 prompts we've tested, with examples. Our creative strategists run these exact prompts for our 7/8-figure clients before any brief gets written. Inside the mini-guide: - The 5 prompts - Claude setup walkthrough - Worked examples Want a copy? Like + Comment "Claude" and I'll send it over ASAP (Must be following)

pov: you read this article and became cracked at AI UGC

how i used claude design to create this email marketing template step 1: - click new prototype (name your prototype) - select high fidelity option step 2: - use following prompt formula write a promotional email for [BRAND] launching [PRODUCT] tone: [ADJECTIVES / TONE] Include: 3 subject line options 2 preview text options hero image direction 1 strong headline concise body copy secondary image direction 1 clear CTA structure: open with a bold statement introducing [PRODUCT] describe it as [POSITIONING] highlight these benefits: [BENEFIT 1], [BENEFIT 2], [BENEFIT 3] emphasise the visual/style appeal: [STYLE DETAIL] make it feel ideal for [AUDIENCE] include hero image direction: [SUBJECT / COMPOSITION / MOOD / BACKGROUND] include secondary image direction: [ACTION / DETAIL / STYLING / SETTING] end with a strong CTA that drives the reader to [ACTION] direction: keep it punchy, premium, and visually driven avoid generic, corporate, or overly long copy make it feel like campaign language, not filler step 3: - iterate as needed, update images, edit template and change fonts where necessary NOTE: i went back and forth several times to get it exactly how I wanted it. you can also use your own design system. for this one i did not use pre existing design system step 4: - export and publish

This 30-minute speech by the Head of Anthropic "Coding Agents" researcher will teach you more about vibe coding than 100 paid courses. Bookmark it & give it 30 minutes today. This video will change the way you use AI forever,

@lorenzo_pravata Agent

AI Agents are the next big thing for ads But most brands aren’t even planning for it. I just broke down the ideal workflow we are creating in-house: - Which type of agents we’re using right now - Use cases that we’re testing & applying to our process - The 4 materials we’ll use for our knowledge base moving forward Want access to the breakdown? Like + Comment “AGENT” and I’ll DM it (Must be following).

In 1998, Warren Buffett explained how to never lose money. MUST BOOKMARK🔖 The lecture was 1 hour 24 minutes long. The company built on those ideas is now worth $1 trillion. This is the closest thing to a cheat code that exists. I'm sharing my latest viral find with you - watch even 5 minutes and your trading mindset will shift forever. Share it. You'll thank yourself later.