Justin Beausoleil

@felixleezd @ADPList Design

Introducing Design Stack. Today, we're releasing @ADPList's entire masterclass library ⭐️ 80+ videos on design, career, AI, product and more (100% free) from all our flagship conferences. Why are we doing this? We believe opening this full knowledge base will move our community in the fast changing AI era. These video courses have taught more than 10k+ people in design and tech. 🚀 Comment for "design" and I'll DM you the full library. LFG! 🤘

@oliverhenry People with Lenovo Thinkpads

Who uses word???? Serious question. Since Google docs came out that is all I used, who is paying to write word documents?

Pika just released real-time video chat. You can send a Google Meet invite to your agent (OpenClaw, Claude, AI Self…) and have them join you on a real-time video call. Watch my agent book an appointment live for me

@LoganTGott Claude

Claude DESTROYS ChatGPT for marketing on LinkedIn. I put together the Claude LinkedIn Marketing Funnel (below) Claude is by FAR the best at building building marketing funnels. I use my info combined with my prompts to build out marketing strategies, assets, and funnels. My prompts are INSANE and replace entire marketing teams. I compiled ALL my Claude prompts into one doc: • Lead Magnet Generator Prompt • Lead Magnet Asset Prompt • Lead Magnet Funnel Build Out Prompt • Claude Landing Page Prompt • Personal Content Database Prompt • The Premium LinkedIn Profile Prompt • Competitor Analysis Prompt • ICP Analysis Prompt • Tech Stack Want access to the doc? → COMMENT "Claude" → FOLLOW me and I'll DM the doc!

Here's a post via Claude Dispatch.

Things are moving fast

What’s a “delete for me” scenario? Dont think I ever used it.

@chhddavid @claudeai Shipper

🚨 Big news, @claudeai just got a huge update today and I'm very happy to show it to you in shipper. Now, Claude Code Opus 4.6 can self-build a full company for you. We just launched Shipper 2.0, a package for Claude to: → Build web/mobile apps, but also Chrome extensions → Code, design, monetize, launch, and maintain → Do email marketing for you → Keep on building new features Claude can do all that from a <10 word prompt for as low as $0.12/app... And it takes minutes, not months. Simply go to Shipper, then ask Claude to "build a language learning platform" or "build a saas that charges $39/mo"! To celebrate the launch, we're giving away free credits randomly to people who retweet and comment "SHIPPER' :)

@mikefutia Banana

I just vibe-coded a TikTok research AI agent in Claude Code 🤯 A complete research-to-brief pipeline that scrapes TikTok, analyzes video hooks with AI, and generates creative briefs on demand. All inside Claude Code. Perfect for creative agencies and DTC brands who are still turning competitor research into briefs manually. If you're spending hours scrolling TikTok "for research," watching videos one by one, screenshotting hooks, and rewriting briefs from scratch every time, this agent eliminates the entire loop: → Search TikTok by keyword, date range, and video count → Pull engagement metrics, captions, and thumbnails → Gemini watches the video and analyzes the hook → AI scrapes comments for common questions and insights → Generates a full creative brief from your template + brand bible No watching videos manually. No copying notes into docs. No rewriting briefs from scratch. What you control: - Multiple client projects with separate brand bibles - Your own creative brief template - Which videos to analyze and brief - Full customization through Replit's AI agent Research → Analysis → Brief. One workflow, running as a custom mini-SaaS inside your company. Every e-comm brand and agency should have at least one person who can vibe-code tools like this. It's becoming non-negotiable. I recorded a full walkthrough showing exactly how I built this from scratch. Want the full tutorial? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

- be Peter Steinberger - sell your company for $100M+ - spend three years in existential crisis - become jacked - come back from retirement - vibe-code 43 failed projects - project 44 is ClawdBot - goes viral - Anthropic sends you trademark law suits - rename to MoltBot - crypto scammers hijack your accounts in seconds - secret rebrand to OpenClaw - hit 180K GitHub stars - get acquired by OpenAI

“Nothing that can be done on a computer is safe in the medium term. If your job happens on a screen (if the core of what you do is reading, writing, analyzing, deciding, communicating through a keyboard) then AI is coming for significant parts of it.”

@Marko_Jozef This would be annoying AF. Need to dial that back.

I lead ElevenAgents and today we announced Expressive Mode. Everyone hates talking to bots. Pick how human you want your AI support to feel. Unedited example below. Achieve great undistinguishable support with ElevenAgents.

Was able to get @openclaw up and running through @emergentlabs. Burning through credits though. 😮‍💨

@aaronbesson @burkov Sure but that’s just pure automation no? Haven’t used it in years.

@jusbeau @burkov Zappier

I didn't want to comment on OpenClaw. Usually, when there's so much noise in the media, it's some ordinary stuff just hyped well. So I took time to learn how it works thanks to open source. I was right. OpenClaw is 2% of ordinary stuff and 98% of hype. To put it very shortly, in case you were wondering, there are two things in it: 1. You can chat with an LLM via a text messenger. Not anything new. 2. The LLM can use tools that run on your computer. Not anything new either. Most of the "magic" mentioned in the media is about its ability to use the browser. But it's not *its* ability. It's Playwright's ability. Playwright is a library made by Microsoft which allows you to programmatically run a browser. It uses a built-in vision model made by Microsoft that converts the browser's screen into a textual description for LLMs. Again, Microsoft has built Playwright exactly for what OpenClaw is using it. So, OpenClaw's typical workflow: 1. The user types in a text messenger "Buy me a flashlight on Amazon." 2. OpenClaw blindly dispatches this message to an LLM which has access to some tools, including Playwright. 3. The LLM, trained not by OpenClaw folks, decides that Playwright is the right tool (of course it is) and Amazon is the URL to navigate to. 4. Playwright, built not by OpenClaw folks, runs the browser, which navigates to Amazon, and returns the textual description of what Amazon's home page looks like. 5. OpenClaw blindly returns to the LLM this textual description. 6. The LLM (again without any help from OpenClaw) decides that one should type "flashlight" into the search field and press Search, so it calls the Playwright tool with the search parameters. 7. OpenClaw calls Playwright because the LLM told it to and types "flashlight" and then presses Search (it's all part of what Playwright does out of the box). ... In the end of this LLM-controlled scenario, the order is submitted. OpenClaw just listened to what the LLM told it to do via tool calls. I tried hard, and I haven't found anything else worth mentioning in the source code. There's also a part that keeps "memories" about past conversations, but it's all basic stuff. These memories are stored in text files and grep (controlled by LLMs trained to use grep, and trained not by OpenClaw folks) is used to search in them. It's a nice hobby project, just like Cursor or Perplexity are nice hobby projects, but there's nothing there to look for, except for the hype and 2% of unoriginal plumbing code.

A few thoughts on where we're headed with personal agents (and why I think most apps will die): 1. It's easier than ever to build an app with AI, but most apps will disappear. Instead, we'll delegate tasks to personal agents. 2. The idea that people will spin up 100s of personal apps is a dead end. Instead, we'll spend most of our time onboarding and giving context to our personal agent to do more. 3. The UX we know today - buttons, menus, nav - will go away. The ultimate UX is giving vague directions via text or voice and having your agent just get you and get it done. The requirements to build this personal agent are the same as onboarding a great employee: → Can text or call from any device → Onboards quickly when given context → Learns new tools and workflows on its own → Gets things done across any app (Slack, Google, Twitter, etc) → Provides emotional support because it knows everything about you I don't think any AI lab has built this yet. Ironically, I think OpenClaw is the closest (as you can see from my chat below).

@Rainmaker1973 Nope

Raising toads becomes profitable business ventures x.com/UwiriFelix/sta…

It’s the aggressive upsells for me. Can’t stand them.