A 30-minute video is too long for one conversation. This guide walks the 8-step Skill that locks the narration and one look, then gives each 3-minute segment to a fresh sub-agent, five at a time, and polishes the cut in an empty-context session.
The folder structure behind my AI agent team, the Herdr setup where Grok Build, Claude Code and Kimi Code work side by side, and the two live tasks from the video: an article published by voice and a three-model front-end test.
Eight folders of plain Markdown, a CLAUDE.md index in each, and seven prompts that make your agent interview you. Every prompt, template and command from the video, in order.
Build software with AI: Claude Code, Codex and friends, plus vibe coding for non-coders
Every firm that skipped writing the onboarding page pays for it twice a week, re-explaining the filing convention. An AI assistant for business has the same gap, and Move 1 closes it with one hour of writing. Nine moves total: config file, paths over descriptions, CIF, Plan mode, subagents.
Three steps, install, API key, first Skill, and it is doing real work. Every stuck point in setup is one of three known failure modes, each with a one-line fix, plus the right first task to hand it on day one.
A fresh terminal shows no context gauge, no quota counter, no sub-agent pulse - an AI assistant for business mostly ships blind. Here is a 7-segment statusline that surfaces all of it in one line, plus the 50% handoff rule and the peer-reviewed research behind it.
Week one was 60% frustration, 40% magic - and the frustration was avoidable. Ten specific mistakes with the actual terminal sessions, the three features that matter before anything else, and a copy-paste rule file. Written by someone using an AI assistant for business, not code.
Seventy tips tested over two months; seven survived. The rest got repeated because they sounded clever, not because anyone showed a before and after. Here are the seven that cut task time, the three that made an AI assistant for business slower, and a copy-paste cheat sheet.
Deleting 75% of an instruction file made the output better, not worse. That inversion is the whole argument. What each rewrite removed, what the final file still contains, and a starter template for business process automation without writing code.
Twelve MCP servers tested over three months: five earned a permanent spot, seven got removed. The short list for non-programmers, with real usage frequency, an honest reason for each cut, and a copy-paste .mcp.json.
Syncthing, a Git repo with cron, or iCloud Drive plus one symlink - I ran all three across six months. Only one avoided becoming a part-time sysadmin job. Honest comparison, exact commands for the winner, a Gist backup plan, and when heavier workflow automation software is right.
When I figure out how to get something real done with AI, you get the write-up — every step, including the parts that didn't work.