Hey Clief Notes fam! 👋 I'm Chris and I'm stoked to be here. 🙋 A little about me: I'm based in Maarn, Netherlands, and I run CK Consultant, where I help small businesses and freelancers get found on Google and in AI assistants like ChatGPT (SEO + GEO). I also coach a few people who are learning SEO themselves. On the side I handle customer support and finance ops for a breathwork company. Just this last week I delivered my first ICM like system to a coach/educator to turn his voicenotes into context with the intent to eventually write a book. 🎯 My current goal: Two things: turn my SEO work into a repeatable workflow for clients and coachees, and build my own SaaS product. 💪 What I'm currently building/working on: - A PII masker that sits between a user and an LLM and automatically strips out personal data (names, emails, IDs) before anything reaches the model. It's all deterministic code, with no AI in the masking path, so you can trust what gets through. - My own SEO toolkit built on Claude Code: a findability check for Google + AI answers, and a per-client check-in that pulls Search Console and GA4 into one note. 🤔 My biggest struggle or question right now: Splitting my time between client work and building the product. How do you protect build time when client work keeps filling the week? And for those who've shipped a SaaS: how did you find your first real users to test with? Let's get it! 🚀

Having your agents reflect what you are saying in an "Hand Drawn" style has been so helpful for me. Rather than reading through the proposed changes in text. Seeing it in an hand drawn sketch is way better.

This is the main reason I got premium!

RinDig/icm-architect It runs in pretty much any agent now: Codex, Gemini CLI, Hermes, Claude Code, Cursor. Or hand the folder to any model and tell it to use the skill. Workspaces now start from an AGENTS .md file, so they aren’t tied to one company’s tools. It would work with others before just not as reliably, should be better now. I also cleaned it up a lot. The whole method comes down to three building blocks now: a sequence of steps, a shelf of same-shaped files, and a small map that points to everything. Every step ends at a check, whether that’s you looking at it or a small model doing it, so a mistake gets caught before the next step builds on it. There are also some small scripts that check your links and draw your whole workspace as a graph you can click through (very basic graph, obsidian is better for viz ill make a nicer one later) github.com/RinDig/icm-architect Install steps for each agent are in the README. Try it on something you do every week and tell me where it breaks.

Jamie Lambe Benjamin Burt Jonathan George I couldn't find you in the search member! Happy to reconnect or if anyone know's their @ handle that would be appreciated.