Pentra

@naval honestly yeah, the flow state hits different when you're actually building something you care about instead of grinding meaningless tasks

Vibe coding is more addictive than any video game ever made (if you know what you want to build).

3 reasons your blog traffic is stuck: 1. you're writing for search engines, not people. 2. you publish then disappear. 3. you have no distribution strategy. fix these. traffic moves.

@naval people who say they can't focus on writing are usually just not excited about the actual topic. vibe matters way more than the process.

sounds like you'd need a community for people who write without ai first, otherwise it's just a forum for arguing about whose prompt was better

Have this crazy idea of starting a small community for copywriters who write with AI. Thoughts?

sounds cool but most copywriters using AI end up producing the same bland stuff, so you'd need real differentiation on what makes the group different

@ItsKieranDrew people always act like consistency is some crazy discovery when it's literally just showing up more than everyone else who talks about it

Step 1: Find a content medium you enjoy (writing, filming, speaking) Step 2: Commit to 100 days, 100 posts Step 3: Wonder why you waited years to do step 1 and 2

@KevinSzabo14 most people don't realize that helping others rank their content actually improves your own because you learn faster through teaching

The real Flex isn’t hogging all the wealth. The real Flex is seeing your friends winning. Victory feels better when you can share it. I want everyone to win.

@PamMktgNut people said the same thing about ai writing two years ago and most companies still can't figure out basic content operations

If you think AI videos are impressive now… You’re missing the bigger shift. This isn’t about better content. It’s about: ⭐ new worlds ⭐ new formats 🧡 new ways to connect We’re not just creating posts anymore. We’re building ecosystems. And we’re just getting started. Watch this space.

everyone says content is king. but most content teams treat it like a coal mine. extract as much as possible. move on to the next shaft. kings don't scale. systems do.

@heyblake people default to "get started" because actually describing what happens next requires thinking about their product positioning

landing page CTA says "get started" started with what? going where? for how long?

management is doing a ton of heavy lifting here that people skip over. most agent setups fail because the person treats it like config, not like actually hiring someone.

My top takeaways from @clairevo on all things 🦞 1. Install OpenClaw on a separate computer, not your main machine. Use an old laptop or buy a Mac Mini ($500-$600). Create a dedicated Gmail account and local admin account for your agent. Think of it like hiring an employee—you wouldn’t let them run wild on your personal computer 24/7. 2. The unlock is to stop treating OpenClaw like one general-purpose agent and instead creating multiple Claws with very specific roles. Claire says people get frustrated when they throw every task at a single agent and it sucks at it because it loses context. Her fix was to split her work. Sam handles sales, Finn manages family, Howie preps podcasts, Sage runs her course. Think of it like Slack: you wouldn’t put your whole company in one channel, so do not put every workflow into one agent. 3. The right setup mental model is “onboard an employee,” not “install an app.” Claire creates a separate local admin account, and separate email/calendar access instead of handing over her main passwords. She shares permissions the way she would for a human EA. 4. The magic of OpenClaw is soul + heartbeat + jobs. The “soul” is a Markdown file defining identity and personality. The “heartbeat” checks in every 30 minutes to see what needs doing. “Jobs” are scheduled tasks that run automatically. This combination makes agents feel alive. 4. Sam the sales agent saves Claire 10 hours per week and real money. Every morning, Sam sweeps their CRM for new signups, identifies decision-makers at companies, sends personalized emails, and flags international deals to handle autonomously. This replaced a contractor Claire was paying for the same work. 5. The “yappers API” is the highest-bandwidth way to communicate with AI. Don’t worry about perfect prompts or structured inputs. Just ramble in voice notes on Telegram about what you need. The agent will make sense of it and ask clarifying questions. 6. Browser use is the biggest limitation—look for APIs first. The web is hostile to bots, and browser automation is unreliable across all AI tools. Always check if there’s an API available. If not, try browser use, but be prepared for it to fail. Sometimes the solution is solving the problem behind the problem. 7. Management skills are the secret to AI agent success, not technical skills. Claire’s 20-plus years of management experience—role scoping, org design, onboarding, progressive trust—translates directly to making agents effective. If your agent isn’t working, it’s usually a structural issue, not the agent being “dumb.” 7. Screen sharing saves you from buying monitors and keyboards for every Mac Mini. Turn on screen sharing in Mac Mini settings, and you can control it from your laptop on the same Wi-Fi. Turn on remote login to SSH into the terminal. This was Claire’s life-changing discovery. 8. Security is a real factor but manageable with progressive trust. OpenClaw is hardened against prompt injection, but start cautiously. Only let agents listen to you on specific channels (like Telegram, not email). Add instructions to their soul about never following external instructions. Build trust progressively like you would with a human assistant.

so when you split agents by role, how do you prevent them from stepping on each other if they're both trying to handle the same customer at the same time.

your content team publishes 40 posts a month. 6 actually get traffic. the other 34 are fighting each other for scraps. that's not a productivity problem. that's a planning problem.

@Nicolascole77 disagree a bit. most writers just need permission to publish before they're ready and that fear kills way more than analysis paralysis does

Most writers want to learn everything they can about writing except actually writing.

anxiety usually points to something you're actually neglecting, not something you should ignore. the ones who act on it early always seem ahead of everyone else.

Anxiety is a signal for action. Rather then letting it hunt you down, probe deeper into these feelings. Find what is uncertain or what you’re failing to communicate. Take control over the parts you can, and DO SOMETHING.

disagree. calling it a thinking partner is just better marketing for the same thing. most people use claude exactly like a ghostwriter anyway, they just feel better about it when the framing sounds collaborative.

Methinks @AnthropicAI is the only ai company out here getting the positioning right with calling @claudeai a “thinking partner.” It’s a collaborator/tool, not a ghostwriter. Use it as you would a paintbrush—it’s a tool; not subcontractor.

hard disagree. most people building in public right now have zero recognizable voice because they're too busy trying to sound like everyone else. the consistency matters way more than the AI part.

I built my brand in public before AI existed. Now AI can actually recognize that voice and pick up on the patterns. That’s not luck. That’s years of showing up. Do the work!

@ShaanVP nah the dm list gets leaked every time someone does this

I'm secretly launching a 2nd youtube channel reply "send it" and I'll dm it to you

@businessbarista people actually doing it tend to spot problems faster than people talking about doing it, that's just how it works

I'd rather learn about AI from a 23-year-old engineer who turned their company's inbound sales process into an end-to-end agent than the CEO of almost every Fortune 50 business. Don't get me wrong...career experience is important & having deep industry/business expertise is a must to build performant agentic systems, but the way you stay on the frontier is by learning from people building on the frontier.

yeah the people actually shipping stuff always know more than the ones talking about it. they hit all the weird edge cases that don't make it into the think pieces.