Claude Code Automation: 5 Real Wins From My Solo Stack
Six months on Claude Code, Max plan: the five automation wins that stuck, and the setup tax no one warns you about.
Six months on Claude Code, Max plan: the five automation wins that stuck, and the setup tax no one warns you about.
After eight months on both paid plans, here is how I split client research between them, and where each one wins.
The six-check pass I run on every client proposal before hitting send: where AI quietly saves me from myself.
Cursor’s new Composer model claims smarter long-running tasks. Four signals from a non-developer’s CSV cleanup week.
Notion turned the workspace into a hub for AI agents this month. Four shifts a solo consultant feels in a daily stack.
A year on Perplexity Pro across pitch research and competitive monitoring — five honest wins and the limits I work around.
Six months in with Claude Projects across three retainer clients — the five wins and two limits that compounded.
I tested Slack against Notion, Discord, Teams, and email for six weeks. Here is the 2026 trade-off math.
Canva AI 2.0 went agentic in April. After four weeks on Pro, I tracked the wins, the limits, and credit math.
Claude Sonnet 4.6 became the default on claude.ai this month. Four shifts a solo consultant feels in a daily AI stack.
Running Nous Hermes 4 locally for client work. Five tests, three pleasant surprises, and the privacy trap I almost stepped into.
Google Antigravity sits in my agent IDE rotation now. Four honest signals from the first two weeks beside Claude Code for a solo consultant.