Claude Code Can Now Control Your Browser (Setup Guide)
A 15-minute walkthrough of how Claude Code gets eyes: setup, tab groups, permissions, and three real browser automation use cases with an honest speed warning.
December 19th 2025A 37-minute tutorial showing non-developers how to replace one-off prompts with a persistent, file-based AI co-writing system built inside Claude Code.
Ninety-nine percent of people who use AI see the word 'code' in Claude Code and stop reading. Alex McFarland's thesis is that this is the most expensive mistake a writer, founder, or content operator can make right now — and his 37-minute masterclass is the corrective.
stated at 00:08“I'm gonna give you every single tool, every resource that you need as a downloadable to do that and to get started.”delivered at 15:50

Opens on the thesis — Claude Code is not just for developers. States the promise: a full co-writing system, downloadable starter kit included. Lists 5 things covered in the class.

Who this is for: newsletter writers, Substack/Beehiiv creators, email marketers, social media, business owners & CEOs scaling their voice, ghostwriters, SEO, brands and teams.

The core problem framing: AI doesn't fail because it's not smart enough — it fails because it lacks context. Identifies 5 failure modes: generic output, inconsistent voice, heavy editing required, re-explaining from scratch each session, prompt roulette.

Side-by-side comparison: Prompt Engineering (one-off, no memory, inconsistent) vs Context Engineering (persistent, predictable, voice-consistent). Formula: context + instructions = quality output.

Defines the 4 pillars: structured information (organized JSON profiles), persistent files (context lives in the project), reusable instructions (skills written once), system prompts (rules that define how AI operates).

Argues Claude Code is categorically different: file system access, bigger context window, reliable MCP connections, persistent CLAUDE.md, skill discovery, agent support. Claude Desktop cannot replicate this.

Recommends Cursor (AI-native editor) with Claude Code VS Code extension. Subscription vs API key — recommends subscription. Alex uses the $200/mo Max plan, runs Opus 4.5 all day, never hits limits.

Walks through the full folder structure: .claude/skills/, context/, knowledge/, CLAUDE.md. Shows the actual CLAUDE.md template: system identity, context routing, workflow rules, skills guide. Gives away starter kit download for paid Substack members.

Live demo of installing the Claude Code for VS Code extension in Cursor, opening it as a panel — shows it looks like a normal Claude chat, not a terminal.

The 3 core JSON context profiles that power the system. Explains Voice DNA as the most important — focuses on tone/personality, not just word patterns. Shows example JSON structure. Gives Substack members 3 creator prompts to generate their own profiles.

Pastes newsletter into knowledge/drafts, asks Claude to write 20 Substack notes. Claude reads system instructions, reads Voice DNA + ICP, invokes the Substack notes skill autonomously, outputs 20 notes, then creates a folder and saves them — all without explicit prompting.

Recaps the 4 components (concept, architecture, profiles, skills). Pitches paid Substack ($20/mo for starter kit + resources) and the Co-Writer System high-ticket training program waitlist.
The 4-part framework that makes AI writing output predictable and voice-consistent, as opposed to prompt engineering which produces one-off, context-free outputs.
The four-folder project structure that gives Claude persistent identity, audience awareness, and packaged expertise across every session.
Three structured JSON files that give Claude deep knowledge about creator identity. Voice DNA is the most important — Alex emphasizes it should capture personality and tone, not just vocabulary.
Side-by-side comparison. Prompt Engineering: one-off, no memory, re-explain everything, inconsistent voice. Context Engineering: persistent system, predictable output, memory built in, consistent voice. Formula: context + instructions = quality output.
“Most AI writing fails. And it's not because the AI isn't smart enough. It's because it lacks context.”
“You wouldn't hire a writer without showing them your past work, explaining your audience, and describing your style. So why would AI be any different?”
“If you stop using this traditional sense of prompting your way through everything and start actually building a system, now you're in the 1% of the 1% of AI users when it comes to writing operations.”
“The formula really is context plus instructions equals quality output. Better input, better output every time. Simple as that.”
“You don't even have to prompt anymore. You just do the system setup once and you never have to prompt again.”
“For my paid Substack members, your starter kit is here. You can download this file, you can open this folder right on your computer and just kick it off right away.”
Two-tier pitch: $20/mo paid Substack (starter kit + weekly guides) as entry, then high-ticket Co-Writer System training program waitlist. Soft sell — no countdown, no urgency. Relies on demonstrated value from the live demo.
Alex is selling a folder structure with JSON files and markdown skills — and it converts. The same architecture powers JoeFlow's Sessions, Chef, and Batch.
00:00
00:42
01:10
01:38
02:06
02:34
03:02
03:30
03:58
04:26
04:54
05:22
05:50
06:18
06:46
07:14
07:42
08:10
08:38
09:06
09:34
10:02
10:30
10:58
11:26
11:54
12:22
12:51
13:19
13:47
14:15
14:43
15:11
15:50
16:07
16:21
17:14
17:31
17:59
18:27
18:55
19:23
19:51
20:19
20:47
21:15
21:43
22:11
22:39
23:07
23:35
24:03
24:31
25:00
25:28
25:56
26:24
26:52
27:20
27:48
28:16
28:44
29:23
29:39
30:08
30:36
31:04
31:32
32:00
32:28
32:57
33:24
33:52
34:20
34:48
35:16
35:44
36:12
36:40
37:08A 15-minute walkthrough of how Claude Code gets eyes: setup, tab groups, permissions, and three real browser automation use cases with an honest speed warning.
December 19th 2025A 26-minute walkthrough of Anthropic's new Cowork tab — three real use cases for writers who are not developers.
January 14th 2026A 20-minute walkthrough of Anthropic's official Claude Code skills repository — install 16 packaged skills in two minutes, then combine them with context profiles to build a co-writing system that actually knows you.
December 16th 2025A 10-minute screen-share walkthrough of the three Claude Code slash commands that actually matter for writers -- live demo, real file tree, no developer jargon.
December 26th 2025An ex-Apple engineer benchmarks ref.tools and Exa AI against Cursor on a live Tailwind v4 refactor — and Claude Code wins at 2,800 tokens vs 98,000.
November 23rd 2025Austin Marchese translates Andrej Karpathy's viral AI workflow post into three copy-paste systems for Claude Code: a compounding wiki, an auto-research feedback loop, and surgical context engineering.
April 24th 2026