Write something
Pinned
Jul 30 •
Build your own AI assistant: the whole thing in one PDF
The setup guide for building your own AI executive assistant has been rebuilt, and the new version is attached to this post. The old one had two problems. It was written to follow along with a call, so the sections had video timestamps in them and it read strangely on its own. And the most important part, the big setup prompt, lived on my site as a link. If you came across the guide later, or forwarded it to someone, that link was easy to miss and the guide stopped working without it. Both are fixed. It is now one self-contained document. The full setup prompt is Appendix A at the back, so you copy it straight out of the PDF and paste it into Claude Code. Nothing to go hunting for. I also stripped it down so it is not branded to me or to this group. No logos, no references to our calls, and the examples are generic business examples instead of listing appointments and showings. That was deliberate. Several of you run teams, and a few of you have people who would use this. You can now hand this PDF to an assistant, a partner, or another agent, and it will not look like you passed along somebody else's marketing. What is inside: - Parts 1 to 3: install Claude Code, create your project, run the interview that teaches it your business - Part 4: your first skill (a daily brief) and your first sub-agent (call prep) - Part 5: how to keep it useful over months instead of abandoning it in week two - Part 6: connecting Gmail, Calendar, and Drive so it can actually send the email, not just draft it Set aside 30 minutes for Parts 1 through 3. That is enough to have something working. Part 6 is the technical one. It involves a few Google settings pages you have probably never opened. Every step is written out and every error I have watched people hit is in the troubleshooting section at the end of it. Take it slowly and it is fine. One suggestion. Do not skim the interview in Part 3. That is the part that decides whether this thing is useful to you or generic. The more real detail you give it about your business, your team, and what you are actually working on, the better everything downstream gets.
11d •
Four Prompt for a Future You
Four prompts, same chat, in order. The third one puts two versions of your next five years side by side: one where your habits stay the same, one where you change the pattern it thinks is holding you back. It can't tell your future. It compares two paths using what you have already told it about yourself. 1. Five things it suspects about you, evidence separated from guesses 2. The patterns in how you think and decide, and what you might be avoiding 3. Two versions of your next five years, side by side 4. A short paragraph to read every morning, with one action for today Some of it will be wrong. Push back on anything that does not sound like you.
0
0
14d •
I gave two AI models the exact same prompt and zero assets. Here's what happened.
I ran a real test: OpenAI's GPT-6 Astra against Anthropic's Fable 5.1. Same skill, same prompt, no assets handed over. Neither one got my HeyGen avatar, my ElevenLabs voice, or any footage. Each had to go get all of it itself — find my avatar, pull my voice clone, do its own research, grab its own B-roll and screenshots, and edit the finished video start to finish. Here's the exact prompt I gave both of them: --------------- I need you to take me from idea to a finished Reels video. I want you to create an engaging and professional video about GPT-6 Astra. You need to use Tom Lyons voice clone and a HeyGen avatar. Start the video off by telling everyone this is not Tom and that you orchestrated the entire video. You planned it out, you researched it, you grabbed all the B-roll, you grabbed the screenshots, you edited everything, and you produced the finished video—which is why they're watching it right now. I want this to feel professional, like it was edited by a human using Hyperframes. Do not give me a draft or a POC; give me a finished, working version that I can post on my Reels channel. I've put the skill used in Cloud Code for creating the styles that we normally use in the folder. So, take what you can from that to help you produce what you need. --------------- The skill both of them used: **the real Commander Tom production skill, made safe to share** — the show bible, the motion-graphics engine, and a step-by-step guide to running the same challenge yourself. Watch the video, then try the prompt yourself and tell me which one you'd have picked.
15d •
Warning for when Claude is losing Context Awareness
Quick one for anyone using Claude for real work: it will lie to you and never tell you it's happening. Every chat has a context window, basically how much it can hold in its head at once. Go past it and the session starts to degrade, that's exactly when it starts hallucinating and making things up. Claude never flags this. Fix: give it a canary. Tell it, "Always start your replies with my name, and save that instruction to memory." Put the same line in any instruction file you use too. Now you've got a tell. The moment it stops using your name, you know the session's degraded. Close it, start fresh, keep going. Video's attached if you want to see it set up start to finish. Anyone else running into this?
0
0
28d •
The Claude setting that stops the jargon, and the two skills I use with it
Opus 5 is the best model on the board and it talks like a consultant who bills by the syllable. Long answers, technical words, and you pay a token for every one of them. Anthropic already published the fix. It is an output style, it takes about sixty seconds, and most people have never opened the setting. Two things in the video: 1. The output style. Set once, changes how Claude talks to you forever. Mine is ELI5 plus one line of ASD-STE100 Simplified Technical English, which is the standard aircraft manufacturers use so a mechanic in any country can read a repair manual safely. 2. Skills for length. Do not hard-wire “be brief” into your style, because some days you need the long version. Put it on a switch instead. /bro rewrites the last answer in plain English. /quick 3 gives you the three things that mattered. One thing worth knowing: do not put these rules in CLAUDE.md. That file is read once at the top of a session and then slides behind you. An output style is written into the core system prompt and Claude Code keeps reminding itself about it mid-session. Same rule, two places, and only one of them still works at turn ninety. Credit where it is due: the ELI5 output style is Lydia Hallie at Anthropic. The ASD-STE100 line is Andrew Carr. The file that installs all of it is attached. Hand it to Claude Code and tell it what you want.
0
0
1-16 of 16
skool.com/datt-ai-campus
Build the AI staff that runs your business. Active steps to help you introduce your first AI employees
Powered by