Christian Slagter-Koster

Why are brands paying $500+/month for LLM prompt trackers that just show you a number? "You're visible in 34% of prompts." Great. Now what? No context. No direction. No explanation of WHY a competitor gets cited and you don't. No analysis of what your content is missing. No understanding of how your web presence shapes AI perception. Just a dashboard with percentages. That's not intelligence. That's a vanity metric. This weekend I'm building Glippy Swarm for the Nous Research Hermes Agent Hackathon: an autonomous GEO visibility platform that does what prompt trackers can't. 7 AI agents covering 8 intelligence layers: 1. Prompt tracking -- yes, it checks citation status across ChatGPT, Perplexity, Gemini, and Copilot via live browser automation 2. Content forensics -- analyzes WHY competitor pages get cited (content depth, source citations, author credentials, format patterns) 3. Site audit -- structured data, Schema org quality, AI bot access, technical readiness, the 240+ checks I already have in Glippy(.dev) 4. Web presence mapping -- tracks your brand's mention footprint across news, reviews, forums, analyst reports, and directories vs competitors. The "training data signal" that shapes how AI models perceive your brand. 5. Multi-model analysis -- Observe what AI cites, evaluate why, recommend changes, and validate whether they actually worked. Evidence-based GEO. Market research where the AI is the market. 6. Citation Readiness Scoring -- 100-point score across content quality, authority, web presence, format, technical access, and competitive position 7. Optimization roadmap -- prioritized, specific actions. Not "improve your content." More like: "Add a comparison table, cite 5 external sources, your competitor has 47 G2 reviews and you have 8 -- that's why Perplexity prefers them." 8. Continuous monitoring -- runs on autopilot, detects changes, learns patterns, creates its own analysis skills over time. After 20 audit cycles, Glippy.dev knows that "adding FAQ schema led to Perplexity citation within 48-72 hours in 4 out of 5 cases" because it observed it happening. The insight from building this: AI citation is roughly 95% content and authority, 5% technical. Knowing your visibility percentage is step zero. Understanding what drives it and how to change it is where the value lives. Built on Hermes Agent using all 18 tool categories. Persistent memory. Self-improving. Runs 24/7. Deadline Sunday. Let's see if this thing can win $7,500.

A soldier ran up to a nun. Out of breath, he asked, "Please, may I hide under your skirt? I'll explain later." The nun agreed. A moment later, two Military Police ran up and asked, "Sister, have you seen a soldier?" The nun replied, "He went that way." After the Military Police ran off, the soldier crawled out from under her skirt and said, "I can't thank you enough, sister. You see, I don't want to go to war in Iran." The nun said, "I understand completely." The soldier added, "I hope I'm not being rude, but you have a great pair of legs!" The nun replied, "If you had looked a little higher, you would have seen a great pair of balls... I don't want to go to Iran either!"

@realtwitcourt Sterkte Chris!

I wish Ubisoft would make a new Rayman This is genuinely one of the most fun levels in gaming 🎸🎶

We stayed a little back. A little off the frontlines. My 24-year-old lieutenant was killed. Our female medic lost her leg. Another buddy lost his eye. My corporal was seriously wounded in his leg. Our engineer lost his hearing. My sergeant lost hearing in one ear and suffered multiple shrapnel wounds. I myself was seriously wounded in my leg. In the end, we lost five men during our mission that only lasted 4,5 months. Fortunately, we stayed a little back. A little off the frontlines. Can you imagine what would have happened if we had actually been on the frontlines.

This is the reason why Gen-X isn't worried about climate change...🤷‍♂️

@PeterBeuker Ah wat naar 😢, gecondoleerd en sterkte de komende periode.

RIP Kitty 💕 (30-05-2008 - 16-12-2025)

@auriqua Ik neem aan dat dit werkt 🤣?

Het mama-irritatie tarief....

Muziek verbindt! Veiligheid gaat niet alleen over regels, handhaving en grenzen stellen. Het gaat over vertrouwen, herkenning en menselijk contact. Over gezien en gehoord worden. Positieve veiligheid. De trompettist Jeffrey Parmentier heeft er een filmpje van gemaakt.🎶🙌

@NoahEpstein_ Interesting, I like finding the GAP 😉

talked to a business owner yesterday who paid $12k for a "lead qualification system" it was 4 nodes in n8n. a webhook, an AI node, a filter, and a slack notification. took maybe 45 minutes to build. this is the intelligence gap nobody talks about: businesses don't know what's possible. so they pay premium prices for junior-level work. not because agencies are evil— because clients can't tell the difference between complex and simple. if you understand automation, you're sitting on a goldmine right now. i put together a breakdown of the 7 "expensive" workflows that actually take <2 hours to build. reply "GAP" and i'll send it over. (must be following so i can dm)

@WorkflowWhisper Interesting take, MCP 👍🏻

Claude and Cursor can now deploy n8n workflows directly into your instance. Not "generate code you have to fix." DEPLOY. 95% complete. Ready to run. And you don't change a single thing about your setup. Same Claude you already use. Same Cursor you already use. Same n8n instance you already run. Just connect Synta's MCP and watch what happens. I typed: "Build a competitor monitoring system that scrapes pricing, analyzes with AI, and alerts Slack when I'm being undercut" Didn't open n8n. Didn't configure a single node. Didn't debug a single webhook. Closed Cursor. Made coffee. Came back. 6 workflows sitting in my instance. Connected. Running. Time: 4 minutes Nodes configured manually: 0 Consultant quote for this: $14,000 Here's why this changes everything: Most AI tools generate broken JSON you spend 3 hours fixing. Synta's MCP: → Interviews you before building → Scrapes real-time n8n docs (not 2023 training data) → Deploys directly to YOUR instance → Auto-debugs before you even see errors Your workflow. Your instance. Your existing tools. Just 10x faster. While consultants schedule "technical scoping calls"... You already shipped. Comment "MCP" and I'll send you: → Setup guide for Claude + Cursor → 5 workflows to deploy in your first hour → Link to check if you got early access The barrier to automation just became a conversation.

@auriqua 😍

Woezel! Foto door vriendin van zoon...

@dennismons Ah wat zielig. Sterkte de komende periode 😟.

Meh... verdrietig. Mijn beste doggovriend Moos heeft niet lang meer. Uitzaaiingen. Vandaag op ziekenbezoek geweest. Beestje kon amper staan 😭

@Ams_IndoRus Sterkte, geen eenvoudige beslissing.

@blvckledge Audit 👍🏻

sharing our internal Google Ads audit process + checklist these are the exact checks we run to help 7-8 figures brands diagnose and scale their spend used it on hundreds of accounts. it covers: → conversion tracking → gmc setup → targeting → campaign structure → bidding strategy → landing page → campaign setup inside, you’ll find everything you need to find what's broken and fix what's costing you money want the full thing? like + reply “audit” and i’ll dm it over (must be following)

@KongQuest64 @alex_prompter So this PDF is from him and BS? share.google/oOqBKPnfXX2H8Z…

@alex_prompter Stop the BS. There’s no perplexity at work guide from perplexity. What he did is just compile use cases from perplexity and made a pdf he just now farms for engagement. If you want to guide for work. Just ask perplexity to give you use cases based on your job and daily tasks.

🚨 Perplexity just dropped something wild. It’s called “Perplexity at Work” their official guide to actually getting more done with AI. Not another “productivity tips” doc this is the real framework their own teams use to: → Block distractions & reclaim focus → Scale yourself like a 5-person team → Turn AI from noise into results It’s clean, practical, and honestly the most useful thing I’ve read on using AI for work not just chat prompts. Comment “Guide” and I’ll send you the full PDF (it’s 100% free from Perplexity)

@mikefutia Lets give it a try, SPY.

This Facebook Ads Spy + n8n is absolutely wild 🤯 This AI agent monitors your competitor's Facebook ads on autopilot every single day. And sends daily digests to Slack each morning. Perfect for e-comm brands & agencies who need to know what's working in their niche. Here's the problem: Your competitors are launching new ads every day. By the time you manually check the Facebook Ad Library, you've already missed the testing window. This n8n automation solves it: → Runs every morning at 8am → Scrapes your competitor's newest Facebook ads via Foreplay API → AI analyzes each ad (format, hook, CTA, offer) → Sends a Slack digest with breakdowns → You see what's working before your coffee gets cold No manual checking. No spreadsheets. No missing winning angles. Built 100% in n8n. Want the complete Facebook ad spy workflow? > Comment "SPY" > Like this post And I'll send it over (must be following so I can DM)

@martinpostmus Gefeliciteerd 🥳

Jarig :-)

@auriqua Voor herhaling vatbaar dus 😉?

@slagter Valt erg mee! Wel wat "ver weg" spierpijn maar alles gewoon kunnen doen.

Ik deed vanmorgen zoiets: Nu benieuwd of ik morgen nog kan lopen...

@ivanlapanje Congratulations Boris 🥳🥰

First anniversary 💍 In this one year I gained 10kg and became Agent 007 in FIFA but it was all worth it guys