summree
Are You Wasting Your Time Learning Claude? (important video)
Claude
Brock Mesarich | AI for Non Techies

Are You Wasting Your Time Learning Claude? (important video)

⏱ 9 min video · 2 min read8 Jun 2026
TL;DR
The creator argues you are NOT wasting time learning Claude, because the real asset is your platform-agnostic foundation: local folders, skills, context files, and MCPs that work across Claude Code, Claude.ai (formerly Cogram/CoWork), Codex, and other AI coding tools. He demonstrates this live by running the same PDF-generation skill across all three platforms from one shared workspace folder.
Key points
1
Your core assets — workspace folders, skill files, Claude MD context files, and MCP connections — are stored locally and are fully portable across AI platforms.
2
Claude Code, Claude.ai (CoWork), and Codex (ChatGPT's coding agent) all function fundamentally the same way: they operate inside local folders and share compatible context files.
3
A live demo shows the same PDF guide skill producing near-identical output when run in Claude CoWork, Claude Code, and Codex from a single shared project folder.
4
MCPs (integrations with tools like Gmail, Slack, Stripe, ClickUp) can be connected in any of these platforms, and Zapier MCP alone unlocks 9,000+ app integrations.
5
The correct mental model is 'platform agnostic': build one foundation, then swap or test any AI layer on top without losing your work or starting over.
Actionable insights
Store all your agents, skills, and context files in a local project folder — this single habit makes your work transferable to any new AI coding tool immediately.
When a new model like GPT-5.5 (Codex) releases, do not abandon your setup — simply open your existing workspace folder inside the new platform and test it side by side.
Use the Zapier MCP as a universal connector so your integrations are not locked to one platform's native plugin/connector ecosystem.
Notable quotes

It literally feels like you're on an endless treadmill chasing different AI releases that are coming out — and I feel this myself, and it's literally my job to stay on top of AI every single day.

Our foundation is just our folders, our skills, our context, our MCPs that live on our local computers — and then whenever a new tool comes out, we could actually go ahead and begin using those if those models are more powerful.

When you understand the fundamentals I'm going to talk about in this video, it really doesn't matter which tool that we're building with.

Worth watching?
⏭️
Worth watching the full video?
The core insight and live demo are fully captured here — skip the video unless you want to see the side-by-side PDF output comparison visually or are new to the concept of local AI workspaces.
Topics
AI & TechClaude

Explore more summaries on these topics →

Saved you some time? The creator still deserves a like.

Watch on YouTube →
More like this

Want this for your own channels?

Add the channels you follow. Every new video summarised and in your inbox the moment it drops. From £4/month.

Try it free