Bart V

@jordan_ross_8F AY

Building a second brain for your advertising agency has never been easier. But most agency owners don't have the time to learn Obsidian + claude code or validate it's even worth their time. So I put my team to work for you. 196 pages built to help you install, set up, and start using Obsidian to run your agency with claude code powering it behind the scenes. Inside you'll find: → The 5-folder vault structure that scales (plus the CLAUDE.md file that turns Claude into a collaborator who's been reading your notes for months) → 29 ready-to-paste plays for daily ops, content, sales calls, client delivery, and strategic thinking → The 30-day rollout plan Comment AY and I'll send it.

@jordan_ross_8F HERMES

Ad & SEO agencies can add 5-10 clients without making a single hire by rolling out hermes to their agency. The problem is most agency owners don't have time to figure out how to install it, where to start, or what to actually hand it first. So my team built an 83-page playbook that does it for you. Inside: — The 5 daily prompts that turn it into a second brain — Plain English setup for Mac, Linux, and Android — How to lock it down without torching client data — 8 copy-paste workflows across reporting, outreach, sales, and ops — The cron trick that drops token spend by 90% 10 new clients at 5k/mo= 50k/mo in new profit just from this one tool. Comment HERMES and I'll send it.

@AminZecom Can you sent me the system, thanks

I tested my IQ. Top 0.4% of the population. It kept me poor for years. Because when you know you can succeed at anything... you try everything. I started ecom. Made crazy money. Then built 4 other businesses at the same time. Went from $100k/month profit down to $20k. Chaos. Burnout. Zero focus. Everything changed when I stopped trying to be everywhere and built 4 AI agents instead : 1. The Brain Agent — my second brain. Thinks, strategizes, decides. 2. The Ops Agent — handles daily operations so I never touch them 3. The CEO Agent — builds landing pages, websites, apps, software. Alone. 4. The Explorer Agent — scrapes the entire internet to find the best suppliers, strategies, opportunities before anyone else does I also stopped buying courses. Now I download entire YouTube channels from the best entrepreneurs in the world and train my AI to answer me exactly like they would. Alex Hormozi in my DMs. For free. Anytime. Comment anything below and I'll send you the full roadmap to build the same system. No course. Nothing to sell. Just answers from a mate passionate in marketing.

@dorampu1 So 5 May...

Moondate Right there 100%

@jordan_ross_8F STACK

The agency owners who fix their AI tech stack in the next 90 days are going to look like geniuses in 2027. The problem is every tool markets itself with the same words.. Agents Copilots. Memory. Automation Read about three and you can't tell which one to pick. So my team built a 105-page field manual that does the categorization for you. Inside: — The 8 software roles every modern agency stack collapses into (brand names change, roles don't) — The 5-question decision model that ends every "which tool should we buy" debate in under a minute — Specific picks by revenue band — what to run at $1M, $5M, $10M, and $20M+ — A task-to-tool matrix across marketing, sales, ops, fulfillment, reporting, and exec — 6 setup quickstarts including the $400/mo warehouse you can stand up in a weekend Comment STACK and I'll send it.

@jordan_ross_8F OS

I fully reverse-engineered Ramp's internal AI operating system for marketing agencies. Their system — called Glass — is how they got 99% of their entire company using AI every single day. 350+ reusable workflows. Every tool connected at first login. Memory that refreshes every 24 hours. Automations running while everyone sleeps. I partnered with my engineering team and we broke down every component inside it. Then we rebuilt the whole thing for marketing agencies. 76 pages. Every system. Every layer. Every step. Steal it. Comment "OS" and I'll send it directly. Must be a following to receive auto DM

@itsalexvacca Email

Giving away the exact Custom Skills Folder we use inside Claude Code to write our cold email sequences at ColdIQ. Trained on the same emails that have generated over $10M for our clients. Plus the master prompt we engineered to clone their buyer psychology. I've tested every AI model for cold email. ChatGPT. Gemini. Grok. They all produce okay copy. But okay doesn't get replies. Claude Code is the first one that changed that. It doesn't come off as AI. It comes off as your best AE on a good day. How it works: > Drop in a target website, a LinkedIn URL, or a detailed ICP > It returns a 3-step outbound sequence > Fully optimised for Instantly > Under 45 seconds, start to finish It feels conversational. Opens strong. Ready to launch in your campaigns. Most people are still prompting ChatGPT to "write a cold email." This is what running 7-figure outbound in the background actually looks like. Want the Skills Folder, the master prompt, and the full system? → Like this post and follow me → Comment "EMAIL" and I'll send you the link.

@jordan_ross_8F OS

I fully reverse-engineered Ramp's internal AI operating system. Their system — called Glass — is how they got 99% of their entire company using AI every single day. 350+ reusable workflows. Every tool connected at first login. Memory that refreshes every 24 hours. Automations running while everyone sleeps. I partnered with my engineering team and we broke down every component inside it. Then we rebuilt the whole thing for marketing agencies. 76 pages. Every system. Every layer. Every step. Steal it. Comment "OS" and I'll send it directly. Must be a following to receive auto DM

@ecomshreddie Yes, see my profile.

Anyone doing any AI consulting/training for Ecommerce teams?

@JeffKirdeikis AI consultant + builder. Shipping cookierisk.eu (GDPR scanner → DPO platform) and cookiefines.eu (5,400+ enforcement records, 33 countries). Bags in $TAO + $RENDER. Want to swap notes with people who actually ship. Followed.

I'm building a private group for people who are laser focused on AI, who want to network, share ideas, and actually build. Usually it costs money to join a group. You get paid to join this one. Companies have already offered $50+ in free credits and cash giveaways to the first 1,000 members, with more on the way. Everyone gets the bonus. Inside you'll get: → Direct connections to investors, developers, and founders → A real network that moves your ideas and business forward → Exclusive access to the latest AI tools at discounted prices This group is not for everyone. There will be a vetting process. -- To get in: 1) Comment below with one of the following: - what you're building - what you've invested (or looking to invest) in - what you're looking to gain and/or share with the group - anything else relevant 2) Then, hit follow, so my DM with the invite link reaches your inbox if you're selected in.

@codyschneider Completed the form, but not receiving anything?

how to start building an AI agent that mines linkedin comments, adds leads to Hubspot, and then does lead enrichment constantly in the background for you first download set up hermes agent on a hetzner machine then give it an openrouter key with mini max 2.7 access next create a data pipeline and a data warehouse using open source software then connect your business data sources to this you need the data warehouse so the GTM agents can actually make good decisions this is literally all you have to do to get started now here's how to actually do this using apify, hubspot api, and exa ai step 1 set up an apify actor to scrape linkedin comments from target posts. pick 20-50 posts from your ICP's thought leaders, your competitors' announcement posts, and any viral content in your space. the actor pulls commenter name, profile url, comment text, and timestamp. run it on a 4 hour cron. step 2 pipe the raw comments into your warehouse (clickhouse works great) as a staging table. don't skip this. you want the raw data sitting somewhere you can re-query later when you change your qualification logic. step 3 write a classifier prompt that runs each comment through minimax via openrouter. score intent 1-10, extract any pain points mentioned, flag buying signals like "we're evaluating" or "anyone know a tool for." dump the enriched rows into a scored_leads table. step 4 for anything scoring 6+, hit exa ai with the person's name + company to pull recent context. what they've posted about, company news, funding, hiring signals. exa is way better than google for this because it's built for semantic lookups on people and companies. store everything in a lead_context table keyed to the linkedin url. step 5 push qualified leads to hubspot via the contacts api. create or update based on email match (or linkedin url as a custom property if no email yet). set a custom property called ai_intent_score and another called signal_summary with a 2 sentence writeup from the agent explaining why this person matters right now. tag the source as "linkedin_comment_mining" so you can track conversion separately from your other channels. step 6 set the hermes agent to loop. every few hours it re-scrapes, re-scores, re-enriches, and checks hubspot for any leads that have gone stale (no activity in 14 days) to re-enrich them with fresh exa context. this is the part most people skip and it's the whole point. enrichment isn't a one time event, it's a background process that keeps your CRM alive. the magic is that you wake up and your pipeline has 30-80 new qualified leads every morning with context already attached, and your SDRs (or you) just write the first message. no more manual prospecting, no more stale CRM, no more guessing who to reach out to. if you want this go to market agent for your business get it below

@AminZecom AGENT

I run 5 businesses and made €30,000 last month from my agency alone. Fully delegated to AI agents. I didn't send a single email manually. Tools: €270/month. Here's the exact system. A full-time sales rep costs €3,500/month. Gets you maybe 2 or 3 clients if you're lucky. Mine costs €270. Got me 15. And it works every month on autopilot. 𝗦𝘁𝗲𝗽 𝟭 — 𝗔𝗜 𝘀𝗰𝗿𝗮𝗽𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 Connects to LinkedIn via PhantomBuster. Finds every decision-maker in my target market. Name, company, role, contact info — dropped into a Google Sheet automatically. 𝗦𝘁𝗲𝗽 𝟮 — 𝗔𝗜 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗮𝗴𝗲𝗻𝘁 For each prospect, it researches the company. Finds pain points, recent news, growth signals. Builds the context for a personalized approach. 𝗦𝘁𝗲𝗽 𝟯 — 𝗔𝗜 𝗰𝗼𝗽𝘆𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 Writes a personalized email for each prospect. Not a template. Actual personalization based on the research and his lasts posts. 200 emails ready to send. Zero written by hand. 𝗦𝘁𝗲𝗽 𝟰 — 𝗔𝗜 𝘀𝗲𝗻𝗱𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 (𝗜𝗻𝘀𝘁𝗮𝗻𝘁𝗹𝘆.𝗮𝗶) Use Instantly .ai or Lemlist to send at scale. 500 emails/day. Optimized to never hit spam. Follows up automatically — 3, 5, 7 times if needed. 𝗦𝘁𝗲𝗽 𝟱 — 𝗔𝗜 𝗾𝘂𝗮𝗹𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗮𝗴𝗲𝗻𝘁 Handles replies. Answers questions. Qualifies the lead. Books the call directly in my calendar. Everything connects to one AI CEO agent. It coordinates every step, remembers every conversation, and reports to me in real time. I pilot the CEO agent from Telegram. That's it. That's the whole job. I just show up to the call. €270/month in tools. €30,000 in profit from signed contracts. No sales rep. No cold calling. No wasted hours. The companies that figure this out first will eat everyone else's market share. Most still haven't figured it out. 𝗝𝘂𝘀𝘁 𝘀𝘁𝗮𝗿𝘁𝗶𝗻𝗴 𝗼𝘂𝘁? 𝗖𝗼𝗺𝗺𝗲𝗻𝘁 "𝗔𝗚𝗘𝗡𝗧" 𝗮𝗻𝗱 𝗜'𝗹𝗹 𝘀𝗲𝗻𝗱 𝘆𝗼𝘂 𝗮 𝗳𝗿𝗲𝗲 𝘀𝘁𝗲𝗽-𝗯𝘆-𝘀𝘁𝗲𝗽 𝘁𝘂𝘁𝗼𝗿𝗶𝗮𝗹 𝘁𝗼 𝗯𝘂𝗶𝗹𝗱 𝘆𝗼𝘂𝗿 𝗳𝗶𝗿𝘀𝘁 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁, 𝘀𝗮𝘃𝗲 𝟴𝟬% 𝗼𝗳 𝘆𝗼𝘂𝗿 𝘁𝗶𝗺𝗲, 𝗮𝗻𝗱 𝗴𝗿𝗼𝘄 𝘆𝗼𝘂𝗿 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗳𝗮𝘀𝘁𝗲𝗿 𝘁𝗵𝗮𝗻 𝘆𝗼𝘂 𝘁𝗵𝗼𝘂𝗴𝗵𝘁 𝗽𝗼𝘀𝘀𝗶𝗯𝗹𝗲. 𝗔𝗹𝗿𝗲𝗮𝗱𝘆 𝗿𝘂𝗻𝗻𝗶𝗻𝗴 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀? Follow. The secret sauce for duplicating whole companies in 1 day is coming to this account.

@jordan_ross_8F Marketing

Anthropic ran their entire marketing operation with one person. $380 billion company. Paid search. Paid social. SEO. Email. App stores. One non-technical hire doing all of it — for 10 months. I pulled it apart. Compared it to every system we've built across the clients we've worked with. Then asked myself one question: If I had to reverse engineer this from scratch — what would it actually look like? Turns out the architecture isn't that complicated. I mapped the whole thing into a 47-page PDF you can upload directly to any LLM. It coaches you through building your own version step by step. Comment "marketing" and I'll send it over.

@mikefutia SKILL

I just built a Claude skill that audits your entire Google Ads account in under 5 minutes 🤯 One prompt → a full account score, wasted spend breakdown, and a prioritized fix list telling you exactly what to change this week. All inside Claude Cowork. Perfect for DTC brands and agencies who are running Google Ads but have no idea how much budget is leaking. If you're managing Google Ads and your "optimization" process is logging in, staring at the dashboard, sorting by cost, and hoping you spot the problem before it costs you another $500... This audit skill finds it for you: → Connects to your live Google Ads data via MCP → Scores your account across 6 dimensions: wasted spend, search term quality, keyword health, quality scores, budget allocation, and creative performance → Calculates your exact wasted spend in dollars — search terms burning budget with zero conversions → Flags quality score issues dragging up your CPCs → Identifies keyword cannibalization across campaigns → Surfaces your top 5 highest-priority fixes ranked by budget impact → Generates a clean audit report you can hand to a client or share with your team No CSV exports. No pivot tables. No guessing where the money went. What you get: → A single Claude skill file you install once → An account health score (0-100) every time you run it → Exact dollar amount of wasted spend identified → Prioritized action list — not "optimize your account," but "pause these 12 search terms and save $847/month" → Works with any Google Ads account connected I'm giving away the full audit skill — the actual .md file you drop into Claude and run against your own account. Want it? Like this post Comment "SKILL" And I'll send it over (must be following so I can DM)

@mikefutia ADS

Claude Cowork + Google Ads is f*cking cracked 🤯 Set up once → ask Claude questions like: "What's driving my CPA spike this week?" "Which search terms are wasting budget?" "Run a full account audit and tell me the top 5 things to fix." All inside Claude Cowork. Perfect for DTC brands and agencies running Google Ads who are still pulling reports manually, digging through search term reports, and trying to figure out where budget is leaking. Claude Cowork eliminates the entire loop: → Connects to your live Google Ads data via MCP → Runs a full account audit across campaigns, ad groups, and keywords → Finds wasted spend — search terms burning budget that aren't converting → Analyzes quality scores and flags what's dragging them down → Detects anomalies — CPA spikes, CTR drops, budget pacing issues → Generates a prioritized action list: what to pause, what to scale, what to test → Writes a weekly performance report in plain English, not spreadsheet noise No logging into Google Ads and staring at columns. No exporting CSVs and rebuilding pivot tables every Monday. No guessing which search terms to negate. What you get: → 21 specialized Google Ads skills that plug into Claude → Full account audits in minutes, not hours → Negative keyword discovery on autopilot → Search term mining that surfaces hidden winners and budget waste → Quality score analysis with specific fix recommendations → Weekly reports your clients or team can actually read I put together the full skill pack: All 21 Google Ads skills for Claude, plus the setup guide to get Cowork connected to your accounts. Want it for free? > Like this post > Comment "ADS" And I'll send it over (must be following so I can DM)

@iamliamsheridan PROMPTS

outbound will never be the same after Claude Sonnet 4.6. dropped today. most people will use it wrong. there's a fine line between AI that makes you faster and AI that makes you sound like everyone else. we took a different route. we use Claude to make our human outbound operators 3-5x faster - not to replace them. that's why i put together a doc of Claude prompts built specifically for outbound pipeline. designed for $10K-$250K+ B2B deals. inside you'll find prompts to help your team: → analyse accounts and map buying committees in minutes → run 10-minute research before writing a single email → generate 3-5 cold email variants per angle without sounding like a bot → draft follow-ups based on specific replies and objections → prep talking points before outbound calls → tighten copy to avoid spam triggers and protect deliverability these aren't generic chatgpt prompts. they're built to make Claude think like a seasoned outbound operator plugged into a human-led engine. the best part? paste them straight in and go. comment "PROMPTS" and i'll send it over.

@iamliamsheridan Claude

Claude Opus 4.6 can contact every decision maker in your market In just 45 days. While everyone's obsessed with "AI SDRs" spamming inboxes, we built something different. Claude as a research copilot. Inside a human-led outbound engine. We're not automating conversations. We're automating the grunt work that kills productivity. Here's what it does: → Ingests your ICP and past wins → Scans raw lead data to surface actual decision-makers (not interns) → Pulls 3-5 real signals per account for messaging → Outlines multi-contact plays for Tier 1 accounts Humans still decide who to contact, what to send, and who gets booked. Claude Opus just handles the spreadsheet hell. Result: Fewer junk meetings. More calls with people who can actually sign. I just put together a breakdown covering: • How we use Claude to clean and filter lead lists • Our exact prompt structures for decision-maker discovery • How we combine Claude Opus 4.6 + ChatGPT/Gemini without building a bloated AI stack • Real workflow examples from our outbound engine This is the same system we use internally to book qualified pipeline. No fluff. Just the actual prompts and process. Want the "Claude Outbound Copilot" breakdown? 1. Connect with me 2. Comment "CLAUDE" (must be following - RT for priority access)

@WorkflowWhisper HEAL

@Motion_Viz PROMPT

Stop prompting AI to "make me a landing page." 200+ hours testing taught me this: Generic prompts → pretty pages My prompts → pages that sell The pack includes: → 3D Landing Hero Section → Sentient 3D Core → Cyberpunk Volumetric Shaders → Microlender Protocol → Hyper-Futuristic MCP-2099 Like + reply "PROMPT" for the library. (following required for DM)

@b_erryn @KoertsNiels Je begrijpt het niet, je moet op 1 januari betalen. Dus als je 100k winst maak moet je 36k betalen oftewel 36k van je aandelen verkopen. Hierdoor is het compounding effect kapot...

Het was tot voor kort lang niet zeker dat de vermogensaanwasbelasting er doorheen zou komen. De wens vanuit de politiek was een vermogenswinstbelasting. Het klopt overigens dat de Telegraaf een van de weinige media is die over Box 3 heeft bericht. Wat mij vooral stoort is dat het onderwerp nooit op TV is geweest. Dat terwijl ruim een miljoen beleggers worden benadeeld.