💰 Week 1 winner @Ian Barriopedro took home $200 cash. 🎟️ This week the prize gets bigger. ✨ Winner gets a FREE seat in The Lyceum. ✨ https://www.skool.com/quantum-quill-lyceum-1116/12-weeks-real-projects-250k-in-prizes-lets-talk?p=e850567b 🎯 Pick your cohort: Technical, Business, or Creator. Your call. 📋 THE CHALLENGE: "The Returning Client" You just got hired again. Different client this time. Meet Marcus. 👋 📎 Download the full client brief attached to this post. 🛠️ YOUR DELIVERABLE An interactive artifact built in Claude that does what Marcus asked for. ✍️ Plus a 100 word writeup covering: - 👤 Who it's for - ⚙️ What it does - 🎨 One design choice you made and why 📐 THE RULES ✅ It has to work ✅ It has to sound like Marcus, not a bank ✅ The writeup matters ⚖️ Judging: Myself, Jake, and the mods. 🎟️ Who can enter: Premium and VIP members only. Free members, this is your sign. Upgrade and you're in the running for a Lyceum seat. 🚀 📨 How to submit: Drop a screen recording or screenshot of your artifact, the link if you've got one, and your writeup in the comments below. 📅 Deadline: Saturday, May 2nd at 12:00 PM EST 🎉 Winner announced: Monday, May 4th at 12:00 PM EST 💡 A note before you start. This isn't a finance challenge. It's a design and voice challenge. You don't need to be a CFP to win this. Read the brief. Marcus tells you exactly what he wants and how he thinks. Your job is to build something that solves his problem and sounds like him. 🆕 If you've never built an artifact in Claude before, this is a great first one. The brief is clear, the scope is reasonable, and the bar is "would Marcus actually send this to a prospect?" 🔥 @Ian Barriopedro set the standard last week. Your turn. LFG 🚀

Meta shipped a connector for Claude and ChatGPT on April 29 that runs write operations directly on your Facebook ad account, no API keys, no app review. Okay the title is half clickbait, but the substance behind it is the part nobody is covering correctly, so here goes. First, understand what Meta actually shipped. It's two surfaces. There's the Meta Ads MCP server, which is what you point Claude or ChatGPT at to control your ad account by talking to it. And there's a Meta Ads CLI, which is the same capability surfaced as a command line tool for engineering teams building internal pipelines. Both are in open beta, both are free, and both authenticate through a normal Meta login. That last part is the unlock honestly, because every prior attempt at agentic Meta ads required going through the Marketing API, which means dev credentials, app review, and business verification. The MCP server collapses that whole credential dance into clicking "log in with Meta." The capability itself is split into four buckets and they actually let you write, not just read. Reporting is the obvious one, pull performance, surface insights, the standard stuff. Campaign management is where it gets interesting because the agent can create and edit ads, ad sets, and full campaigns by natural language. Catalog management lets it build product catalogs and fix data feed problems. Signal diagnostics covers Conversions API health, learning phase status, and signal prioritization. Most third-party ad-MCP wrappers (AdKit shipped one for Google plus Meta on May 1, two days after Meta's own launch) are read-only, because writing to ad accounts through unofficial APIs is risky and Meta gates it hard. Meta's own connector doesn't have that limitation because Meta is the platform. Now the part where I'm not just selling it. It's open beta, so the rate limits and edge cases aren't fully documented. The bigger thing to know is the learning phase, which is roughly 50 optimization events that Meta uses to actually figure out who to show your ad to. If your agent edits a campaign mid-learning, the campaign resets and your performance tanks. Meta hasn't built guardrails for this yet, which means the agent has zero idea by default. You have to tell it. If you don't, you'll watch your CPA spike on the first day you let Claude touch your account and blame the connector when it was actually you. (fyi this is the same thing that happens to humans editing campaigns mid-learning, the AI just does it faster.)

Signed before the tool is finished. Signed before the new company is even incorporated. I'm building a Marketing Stack for my SaaS company and before I was finished with Phase 1 of the seven planned phases I was thinking about several people who had talked to me recently about their pain in the same area. Made the call, explained the idea, addressed their pain, and signed the deal. If you approach what your are building as a system that can be deeply customized for each user, then you have a product that people will want. Build it to solve your problem but remember that the customization, the personalization, the flexibility, and the agility of what we can build with AI as the newest abstraction layer of software development is what makes what we are doing here better than what SaaS can do. SaaS is a cookie cutter template that the r has to cram themselves into. What we can build is deeply personalized software solutions.