Jake Sablosky

@underwoodbrent I don’t ever get claustrophobia, but I had it watching this video of you 😑

I Spent 5 Years Digging Into an Abandoned Mine…and Finally Got In

@tommchale @jspujji I find it more reliable with a bigger context window and easier to work with given all my custom MCPs. To be honest though I have not tried Cowork at all in about a month.

@JakeSablosky @jspujji Interesting. I use both, but mainly Cowork. Why do you prefer Code? CLI or app?

@obviceo Openclaw

Have a 9 figure jewelry brand looking for a Google Ads consultant, any good connections?

@nickgraynews Describes my last two months

I've talked to a lot of people working in AI with agents, Claude Code, etc One thing I keep hearing that nobody has written about is that many builders have stopped going to the gym The reason is always the same: the perceived opportunity cost of stepping away from their projects feels too high I've noticed it in myself too It's hard to break away when we're all building such cool stuff But I'm typing this from the gym right now And I'll tell you that it feels great You should go exercise if you haven't lately You'll have better energy and better focus Less prompting and more lifting!!

@clairevo @openclaw It’s not just onboarding that’s the hard part, it’s the constant support when it breaks!

Just to be clear: this was 3+ hrs for a basic “AI for families” setup: new Mac user, Homebrew, Node, OpenClaw CLI, Claude API + CC, config the gateway, Google Cloud project + OAuth creds, GCal/Gmail/Drive APIs and oauth across gmail + workspace, Telegram BotFather wiring, multi-user 1Password vaults, per-agent workspaces + soul/memory files, browser + tool permissions, and a forest of kids’ sports/work/personal calendars. It's not done. Setting up @openclaw is onboarding a junior engineer + training a chief of staff, not installing an app.

I helped set up my friend's @openclaw yesterday and this is undercharging by 4-5x

@mikefutia Skills

Claude Skills are a cheat code for DTC creative teams 🤯 One setup, reusable forever. Claude automatically follows your exact creative process — briefs, hooks, ad copy, research — without you explaining anything twice. Perfect for e-comm brands and agencies who are using Claude for creative work but wasting time re-explaining context every single conversation. Here's the problem: You open Claude: you paste in your brand guidelines, explain your brief format, write the copy, you close the chat. Next day, you do it all over again. Every conversation starts from zero. You're burning 20 minutes on setup before you even get to the actual work. Claude Skills fix this: → Write your creative process once as a Skill (a simple markdown file) → Claude reads it automatically whenever the task comes up → Skills compose — research triggers the research Skill, briefs trigger the brief Skill, copy triggers the copy Skill → All in one conversation, all building on each other → Share across your team so everyone gets the same quality output No re-explaining your brand voice. No pasting the same context every chat. No siloed projects that don't talk to each other. What's in the playbook: → The full architecture (how Skills trigger, chain, and compose) → 5 ready-to-use Skill templates built for DTC and agency creative teams → Step-by-step setup from zero to working Skills → How to write instructions that produce consistent output every time → The composability framework for running multi-step creative workflows in one conversation I put together the complete Claude Skills Playbook for DTC brands and creative agencies. Want it for free? >Like this post >Comment "SKILLS" And I'll send it over (must be following so I can DM)

@IMJustinBrooke Skills

My entire sales process is AI now... Last week it brought in $35,946 in sales, with $23,958 cash collected. You need these 3 skill files if you want to do the same for your sales process... 1. VSL script writer 2. 7 day email promo 3. Long form sales letter Comment "skills" below and I'll DM you the skill files to install.

@mikefutia Vault

I just packaged up 10 of my best AI automation workflows into one database 🤯 (honestly I should probably be charging for this) Every system I've built for AI content, competitor research, and ad creative — now in one place. Plug-and-play & ready to run. Perfect for DTC brands and agencies who want to skip the build phase and start generating. Here's the full list: → YouTube Research Agent Scrapes top videos in any niche → AI extracts hooks, angles, themes → organized in Airtable → Instagram Reels Agent Pulls trending Reels by keyword → Gemini analyzes creative patterns → comment insights included → TikTok Research Agent Scrapes viral TikToks → extracts hooks and engagement data → performance tracking built in → Facebook Ads Spy Monitors competitor ads daily → AI breaks down hooks, CTAs, offers → Slack digest every morning → Claude + Facebook Ads MCP Turns Claude into your ads analyst → generates performance reports → just ask in plain English → Sora 2 Cameos Consistent AI characters across videos → automated UGC generation → full Airtable tracking → Sora 2 Consistent Characters Same creator across entire campaigns → brand consistency at scale → Loom walkthrough included → Nano Banana + Veo 3 One product photo → 50+ UGC videos → auto-stored and organized → HeyGen Long-Form UGC 1-minute+ talking head videos → testimonials and demos → scales without creators → Nano Banana Static Ads 1,000+ ad variations on autopilot → bulk image generation → built for creative testing Every workflow includes the n8n templates + Airtable bases. Copy, paste, run. Want the full database for free? > Like this post > Comment "VAULT" And I'll send it over (must be following so I can DM)

@photomatt @NoamEppel @kavinbm Do you mean build a custom plugin for claude code that connects to WP?

@JakeSablosky @NoamEppel @kavinbm I agree! You can customize all that with your personal plugin that AI writes. ☺️

I setup OpenClaw exactly 7 days ago. Since then here's what I've built. In 2025, this would've taken a team of 10-20 people 6-9 months and $1M+ in funding. 7 days. Just Me + OpenClaw + Claude Code. Building 12-15 hours a day. Total cost ~$600 (Tokens, Compute etc). PRODUCTS 1. Simple Notes: A full blown Apple Notes replacement with full sync working on all devices iOS, Mac, Web, Android. 2. Lumenote: A full blown Obsidian replacement with full sync working on all devices with slick UX (handling markdown better) + AI fully integrated to speak to my knowledge base. 3. CleoAI: OpenClaw but for normies built into Telegram. You just talk to it. No app needed. OC is too techincal for a normie referencing settings and md files all the time. So a version that my gf and siblings can use. No tech speak, gog bs etc. Architecture is TBD. OC has a hard coded system prompt that is tricky to override so likely I just re-build OC from scratch (with better security) or re-build all skills in a way that sound non-tech. WIP. Waiting for Apple to approve a new developer account to publish 1 & 2. Btw, all using Vercel, Railway, Supabase behind the scenes. AGENTS This has been unreal. I setup OpenClaw 7 days ago + Telegram and I did not know what to expect. In short, there are just no limits. Here's my current setup (evolving fast): 1. Sam (CoS): Sam is my new Chief of Staff. And calling him a CoS is a massive understatement. Here's all the things he's doing already: • Emails: Helped me triage and make sense of a 1000+ emails (has full access to my Google account). • Calendar: Drives my calendar and appointments • Bookings: My go to for booking restaurants. He uses my Chrome browser in a different profile to browse and book. • Shopping: Helped me shop for a few things. Research to filling my shopping cart online. He sent me a payment link to pay via Telegram through which I paid (I was walking at the time). • Groups: Sam is in 3 group chats with me and a few friends helping out with a few things. I don't think they know he's an agent (!). • Code & Build: Helps make quick fixes to all projects above and sometimes is better than Claude Code • Personal CRM: Built and maintains a 697-contact CRM from my Gmail + Calendar. Know who I talk to, when, and how often. • Optimizes Infrastructure: Security audits, gateway config, model routing optimization (Opus Orchestra), cost management. Sam has memory across all sessions and maintains daily notes. He also spins up 5+ sub-agents often automatically to get work done. I've given him tasks overnight only to realise he's done the in 30 mins. Sam also has his own email and his own phone number. I've plugged in ElevenLabs to give him a super voice. It's unreal. 2. Midas (Investor): Midas is my autonomous crypto trading guy. Calling him an agent is like calling a hedge fund manager a calculator. Here's what he's doing: • Portfolio Management: Managing a meaningful size portfolio with a 14-week DCA deployment strategy. • Trade Execution: Executes trades directly on exchanges. Sizes his own DCA tranches, handles currency conversions, places market and limit orders all with built-in risk guardrails. • Yield Farming: Autonomously stakes ETH and SOL on exchanges with custom trigger rules. Knows when to unstake for take-profit and when to restake on dips. • Risk Management: Tracks portfolio drift vs targets, flags overweight positions, adjusts DCA allocations to correct imbalances. E.g. automatically skipped BTC in Week 3 because it was 65% of portfolio (target 45%) and reallocated to underweight tokens instead. • Market Intelligence: Scans markets every 4 hours pulling from 8 live data sources. Calculates RSI, tracks on-chain metrics, monitors ETF flows to inform decision making. • Strategy: Operates under a locked strategy document that I've built with it's help, that governs every decision. Has its own trigger framework and won't deviate without approval. • Daily Briefs: Morning brief every day with prices, P&L, drift analysis, macro signals, and yield tracking. Weekly deep dives on Sundays with thesis reviews and watchlist scans. Midas has full exchange API access (trade, query, staking) but can never withdraw funds. He speaks in market language, celebrates wins, owns losses, and keeps me honest when I want to FOMO. 3. Ritam - ऋतम् (Physics Research): Ritam is my deep science research guy. He's focused on one mission -understanding gravity well enough to engineer it. Here's what he does: • Vedic-Modern Bridge: First, takes Vedic science seriously as physics. Treats the universe as one unified system from which matter, life, consciousness emerge. Looks for where ancient models make testable predictions. • Research & Paper Hunting: Searches arxiv, patents, journals, and obscure sources for bleeding-edge physics from EM universe theory, anti-gravity, torsion fields, scalar waves, and modified gravity theories. • Theory Synthesis: Cross-references across domains. For e.g. it connected ball lightning confinement to plasma physics to Gertsenshtein EM↔gravity coupling and proposed a hypothesis 🤯 • Engineering Oriented: Every theoretical insight gets pressure-tested with "so what can we build?" Equations and models are means to an end. The goal is technology for humankind. Ritam has full web search, paper access, browser automation, and compute tools. He speaks in physics, gets genuinely excited about breakthroughs, and won't sugarcoat when an idea doesn't hold up. 4. More Coming: There at least a dozen more agents WIP. I just spun a team of agents for Marketing & Distribution and I have no idea what to expect!

@NoamEppel @photomatt @kavinbm This is actually very good feedback, even if a bit harshly delivered. As a small business owner, it resonates, and I would say I lean much more technical than the average small business owner.

Yes, building on existing open source projects can be beneficial - when it actually makes sense to do so. Matt, take a look at this screenshot. This is what a typical person sees today when they log into their WordPress site: multiple alerts, plugin advertisements, security warnings, update notices.. Serious question: if you're building a new website today, why build it on WordPress in the age of AI? Matt sit down with a typical small business owner who runs a WordPress site. Ask them to add a YouTube video to a page. That's it. Watch what happens. Watch them log in, navigate the cluttered dashboard, click through layers of menus, search for the right page, wrestle with Gutenberg or Elementor, maybe they need to visit the plugins page to search and install a video plugin that actually works, insert the video, preview it, adjust it, preview it again and hope adding the video didn't break anything. Or you could show them they can open Claude Code and type, "Please add this YouTube video to the Contact page, full-width and add a short caption underneath the video." and have it implemented correctly in under a minute and be done. What are we actually gaining by preserving the clunky, slow WordPress dashboard? What value is this adding? At what point does it make more sense to replace stagnant legacy systems with new tools that genuinely work better for users? The WordPress investment in testing and hardening is real. But it is no longer the advantage it once was. AI has bent the development curve so significantly that accumulated time is less valuable than rapid feedback loops and continuous hardening.

@bryan_johnson Sauna

What do you do in the evenings for good clean fun?

@mikefutia Agent

Anthropic just shipped Agent Teams into Claude Code and it completely changes how you run creative research and campaign workflows 🤯 OpenClaw has been blowing up up. 140K+ GitHub stars in a week. Everyone’s trying to configure multi-agent setups with it right now. Custom skills, MCP integrations, environment variables, Docker containers. It works. But let's be honest: it’s unnecessarily complicated for what 99% of business owners actually need. Anthropic saw the demand and made it native. No Mac mini, no VPS, not 6-hour installation setup. Instead, they built right into Claude Code. Here's how it works: Instead of one agent doing everything solo in a straight line, a lead agent breaks your task into pieces, spins up multiple teammates, and they all work on different parts of your project at the same time. One researches competitors, one audits your landing page, one analyzes ad creative. They talk to each other, share findings, and coordinate through a shared task list without you managing any of it. This is different from sub-agents. Sub-agents can only report back to the parent. They can't message each other or share discoveries mid-task. Agent teams can. That's the unlock. Best use cases I'm seeing for e-comm and agencies: → Competitor ad research across Meta, TikTok, and YouTube in parallel → Landing page QA from 4 angles at once (conversion, performance, copy, technical) → Creative brief development where audience research, competitive analysis, and concept ideation happen simultaneously → Product catalog audits where 4 agents each handle a segment of your SKUs → Campaign launch QA checking pixels, UTMs, forms, and compliance at the same time The catch: It's experimental. It burns through tokens fast. Each teammate has its own context window so usage scales with team size. But for complex marketing workflows where parallel work actually matters, it's a game changer. I put together a complete breakdown covering: → What agent teams are and how they actually work → How they're different from sub-agents (and when to use which) → How to enable them in your settings in 30 seconds → Copy-paste prompts for competitor research, landing page QA, and creative briefs → Best practices so you don't burn through tokens → The limitations you need to know before you start This is one of those features that sounds small on paper but completely changes how you run research and QA once you start using it. Want access completely for free? > Like this post > Comment "AGENT" And I'll send it over (must be following so I can DM)

@AndrewWarner Yes

I recorded an interview on how to save $1000s on Opus 4.6 with Openclaw. I need some feedback. Can I show it to a few people before publishing? I want to make sure the video + prompt guide are clear and useful. Comment "yes" and I'll DM you before publishing.

@fortelabs Agreed, PARA is a relevant as ever and has been a huge foundation moving into Claude desktop and openclaw workspaces.

@noahkagan This has been my experience 100% and I think the allure of openclaw is that non-technical people who are willing to troubleshoot using AI are now able to do some of the things that only technical people could do in the past, and it becomes better every day.

72 hours with OpenClaw - 100% overhyped and 100% amazing! Last week I joined AppSumo’s OpenClaw workshop, set it up live and then got obsessed ever since… So much so I had it run my X account for the past few days. The hype is real but people are also completely full of it. This moment feels like when I first found AOL chatrooms and could get mp3’s or jpegs. It’s super early, buggy, risky, etc but it’s one of the first AI tools that I can see where the future can really go. Here’s my overall review of the product:

@NabbilKhan @AndrewWarner @calebhodges Very interested in seeing this!

@AndrewWarner @calebhodges The shutdown issue is real but solvable. We run Claude Code across 8 persistent agents using tmux + heartbeat monitoring. If one dies, the system detects and restarts within 30 seconds. File-based state means zero context loss. Happy to share the architecture.

I'm at a Claude Code event right now. Everyone's complaint: Openclaw keeps shutting down. @calebhodges gave us all a markdown file that solves the common issues. Want it? Comment "openclaw" and I'll DM it to you.

@AndrewWarner @calebhodges Openclaw

@fortelabs I was super excited about Cowork but I found the MCP connections failed a lot, and I was running out of context much quicker than normal chat. Very strange because I would think context would be better in cowork. This was about a week ago though, and that is a lifetime in AI.

My review of Claude Cowork after a week of using it exclusively: 1. It works great as a direct 1-to-1 replacement for the standard Claude chat interface It feels like a more powerful, thoughtful, thorough, and well-organized version of the same chatbot, without sacrificing usability 2. It's also a good alternative to Claude Code, removing or hiding some of the scarier technical aspects that made Code intimidating for beginners They've managed to make Code more approachable, without sacrificing its power and functionality 3. Plan Mode is now hidden but activated automatically when needed Cowork will ask you followup questions with multiple-choice answers to clarify your intentions, which I find very helpful 4. Cowork favors creating documents for complex or long outputs For example, it decided to make a Word doc for a travel itinerary, and an markdown file for a long list of suggested edits to an essay 5. Context is now provided via a folder, the contents of which it is able to read, edit, delete, or create new docs as needed This is a much more effective approach than uploading single files into the web interface, and I believe will be the standard going forward. It also makes markdown files and folder structures (like PARA) important once again 6. Skills and tools are available in Cowork, but not essential That strikes a nice balance between flexibility and user-friendliness; the barrier to entry is low, but the ceiling of what's possible is high, giving me confidence to invest my time in it My main question is: what can Code still do that Cowork can't?

@jspujji Ga

I hired an ex McKinsey consultant to compile all my sales materials to document how GrowthAssistant company reached $22M in ARR. He collected: - Recordings of sales calls - Sales scripts - SOPs - Lead gen systems - etc 100s of top companies paid me for access to it. Today I'll give it away for free. RT + reply "GA" to get a copy in DMs.