Activity
Mon
Wed
Fri
Sun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More

Memberships

Clief Notes

35.7k members • Free

8 contributions to Clief Notes
Thoughts on integrating ICM for marketing?
I'd like to trade notes. My client is working on their ideal customer profile (ICP). I'm thinking Google Drive will be where the ICM filesystem resides, with Claude referencing that and accessing myriad tools to drive outbound/inbound marketing workflows. Made this quick video for the client to educate them a bit on ICM and how it applies to their current objectives. Feedback is welcome.
2 likes • 3h
@Kurt Henninger That Google Ads workflow is a really good example of the same pattern. In this case, we're starting with the top-priority vertical in the client's ICP framework. Primarily outbound marketing with cold email and LinkedIn outreach to start. Google Drive will hold the ICP doc along with approved proof, vertical-specific rules, offer/positioning context, source notes, stale-context flags, and a learning log from each campaign cycle. So the marketing use case for ICM in Google Drive is to keep the context interpretable, let Claude reason across it and help maintain it, then connect to the right execution tools at the right time.
ICM filesystem vs project-management?
How are you all thinking about project management tools and how they connect with ICM file systems? I have an Airtable base with Projects, Tasks, Logs that predates the ICM setup. I don't want to have duplicative data between that and my ICM workspaces. Curious what architecture you all are using.
0 likes • 3h
@Matt Paine thanks Matt! that sounds right. And if the agent gets it wrong, I'll tell the agent what went wrong and to go update ICM files to better encode the right way of doing things.
0 likes • 3h
@Bayo Olorounto Good template, thank you! Airtable has evolved a lot. They position themselves as a low-code AI app building platform these days. Think of Airtable as a relational database engine wrapped in a NoSQL-style flexibility layer, queried via modern APIs instead of SQL. Database of spreadsheets is a fair characterization. Except increasingly you'll find end users never have that spreadsheet experience, instead interacting with app interfaces that people like me created for them. So the 'spreadsheet' part of the base is like the database and backend, then interface pages are built on top of that to support specific workflows.
Agent Rules?
have you written structured rules for your agents? interested in seeing what I may be missing, though this has greatly cut down on re-explaining and re-working. (not actual pipeline stages, parallel execution routes based on needs in each new session)
Agent Rules?
2 likes • 4d
@Jordan Shaw and @Aaron Kruger from what I can tell, Claude Chat and Claude Cowork and Claude Code all seem to operate in silos. And then Claude on the web is another silo. Maybe ICM helps to break those silos down. I haven't tried yet. Codex is just one chat interface, no separate cowork or code versions. Also, the new Codex extension for Chrome is quite effective at browser automation without taking over your screen and your mouse. And the new computer use automation can work on your computer with its own mouse without taking over your computer. Both of those processes run much faster than Claude Especially if you use the 5.3 Spark Codex model. I have my ICM file system in one GitHub repo, and then I have my skills in another repo and I'm trying to maintain them in a way that is portable between Claude and Codex. So that if the situation changes and Claude or another platform becomes better than I can switch without fear of vendor lock-in.
0 likes • 13h
Turns out my 5x plan has been on a temporary double usage promo until now. So it’s actually been 10x. Will see if 5x actually works for me.
🚨 You've been asking when the Lyceum opens. The waitlist is live. 🚨
The waitlist is up and seats are limited, so this is your nudge to go lock yours in. 👇 New here? Quick context. 👀 The Lyceum is Jake's live cohort program built on ICM, the methodology 35,000 people in this community are already using to get real results with AI. The short version: folders over agents. You learn the layer underneath the tools, the one that keeps working when the next model drops. Full breakdown is on the site. Here's what's inside: 🎯 Three cohorts, Technical, Business, and Creator. Same methodology, built around what you actually do. 🎥 Live sessions with Jake and a full team of instructors. ♾️ Lifetime recordings, written curriculum, and a private cohort Discord. 📜 An Eduba ICM certification you can put on your resume. And a guarantee no course makes: ✅ You leave with a working product, or the team finishes it with you. ⏳ Seats are limited and this community moves fast, so the math is not in your favor if you wait. 💡 Pricing and start dates aren't public yet. The waitlist sees them first, gives feedback on timing, and gets in before the program opens. Everything you want to know is on the page. If you already know this is for you, get on it. 🔥 👉 https://lyceum.eduba.io
1 like • 2d
Chrome says your site is unsafe
What breaks first when an AI workflow leaves your head?
I made a short video on an ICM-adjacent idea: using Airtable as a context registry so workflow context is easier to reuse, review, and hand off without copying every source doc into Airtable. When you try to reuse or hand off an AI / automation workflow, what breaks first?
Poll
Cast your vote
1
0
1-8 of 8
Marty McCoy
3
39points to level up
@martin-mccoy-3803
Greetings, you can find me here: linkedin.com/in/martymccoy

Active 3h ago
Joined May 24, 2026
Powered by