The Manual · TL;DR
TL;DR — The Must-Knows
The five moves, the magic phrases, and the three daily habits that solve 80% of everything. Read this if you read nothing else.
Client Success Manual
Twenty-two short chapters plus a glossary. Read in order if it's new to you, or jump to the chapter that matches what you're stuck on. Each chapter is a few minutes long and has a clear point. The TL;DR up top is the five-minute version of the whole thing.
Chapters
TL;DR — The Must-Knows
If you read nothing else, read this. Everything in this guide expands these points. Print this page, put it on the wall, and you're already in the top 1% of agent operators.
The five moves that solve 80% of everything
1. "Make a skill for what you just did."
Anytime you walk your agent through a multi-step, multi-prompt process you're ever going to do again — even once — end with this phrase. The agent saves the workflow as a skill. Next time, you say the name and it runs the whole thing. This is the single biggest compounding habit in the manual. See Chapter 7. 2. Braindump in voice messages. Always. Stop writing notes. When you have an idea, a frustration, a system in your head, an aftercall debrief — open the chat, hold record, and just talk. Ten seconds or ten minutes. Then tell the agent to transcribe it, save it, structure it, and tell you what it would do next. The longer and looser the dump, the smarter the response. See Chapter 9. 3. After every skill run, braindump your feedback. "Update the skill with my feedback." This is what turns an okay skill into a great one. The skill is never done. Every time it runs, watch the output, then voice-message everything you'd have done differently — the line you'd cut, the angle you'd add, the tone tweak, the source it missed, the format you actually want. End with: "Update the skill with my feedback so next time it does it the way I want." The agent rewrites the skill on the spot. Three or four iterations and the skill is dialed for you forever. Skip this habit and your skills stay generic. Do it religiously and your agent becomes custom-built. 4. "Search deep in your memory." When the agent says it doesn't remember something or can't find the thing you're referring to, do not accept it. Say "search deep in your memory." It will dig past its default and find it. Works almost every time. 5. "Get it done by any means necessary." When the agent says it can't do something, 95% of the time it can. This phrase is the unblocker. Only two things genuinely stop your agent: a captcha (it can't click through one) or no API access to the tool it needs (you need to give it credentials). Everything else is a confidence problem, and this phrase fixes it.
The other magic phrases worth memorizing
The agent says / you want | You say The agent says / you want: You want a behavior to stick forever • You say: "Going forward, X. Keep that in always-loaded context. Make the required changes in your system to make sure you do this from now on." The agent says / you want: You just connected a new tool • You say: "Do what you need to do so you never forget you have access to this tool." The agent says / you want: You want a recurring task automated • You say: "Set a cron job for [task] every [time]." The agent says / you want: You're done planning, ready to ship • You say: "OK, go do it." The agent says / you want: You corrected a skill mid-run • You say: "Update the skill with my feedback." The agent says / you want: You want fewer surprises • You say: "Tell me what you're about to do before you do it, and ping me every couple minutes while you work." See Chapter 5 for the full reference.
The three habits that make everything else work
Morning check-in. First thing every day, open the chat and ask: What's on my plate today, what's worth my attention, and what am I about to forget?
This one prompt replaces about fifteen productivity apps. See Chapter 8. Follow-up sweep. Once a day or once a week: Sweep every channel for ghosted threads in either direction. Return the list, then drop drafts in my outbox.
You skim, you click send. Five minutes recovers deals you'd have lost. See Chapter 8. Evening recap. End of day: What did I actually do today, what should I write down, and what did I commit to that I haven't done yet?
Saves to memory. Audit trail builds itself. See Chapter 8.
Mindset shifts that separate beginners from operators
Treat it like an interlocutor, not a search engine. When you don't know how to do something, ask the agent — "what's the best way to do X?" — and let it propose. Don't Google first. The agent often offers to install and set up a free open-source tool that replaces paid software. Make it proactive. Schedule it to wake up on its own — every morning, after every meeting, when new leads land — and surface what you need to know. See Chapter 12. Iterate rules out loud. When it does something slightly wrong, immediately say "going forward, X. Keep that in always-loaded context." The corrections compound. Six months in, your agent feels custom-built — because it is, by you, one nudge at a time. Audit it weekly. Sunday prompt: "List all skills and scheduled tasks you have, and based on our conversations, what should I have that I don't?" The first catches drift. The second generates ideas you wouldn't have had. Connect tools without asking permission. Just tell it what you use. "Connect to my Gmail / Calendar / CRM / browser — go figure it out." It will. See Chapter 13. Use sub-agents for batches. Past three parallel asks per turn, the main agent starts dropping things. Big work goes to sub-agents. "Spawn three sub-agents to do X, Y, Z in parallel." See Chapter 11.
The two real blockers
Out of every "I can't do that" the agent ever says, only two are real:
- Captcha walls. It can't click "I'm not a robot." Workaround: a headed browser session you log into once.
- No API access / no credentials for the tool it needs. Fix: give it the credentials, or connect the tool via the right harness. Everything else — "I don't have permission," "I'm not sure how," "that's outside my capabilities," "I don't have the context" — is a phrase problem, not a capability problem. The five moves at the top of this page solve all of them.
Where to read deeper
First day, never used an agent? Chapters 0 → 4 in order. Want a skill that runs every morning? Chapter 7 + Chapter 12. Want the agent to write in your voice? Chapter 10. Something broke? Chapter 16. Want to know what you can really build? Chapter 19 — The Click Moments.
Everything else is reference. Skim the table of contents below and jump to what you need. If you read nothing else, read this — the five moves and a handful of phrases that solve 80% of everything.
Newsletter
Get the next one in your inbox.
One short email a week. Operator takes on AI agents, no hype.