Prompts.
Copy. Run in ChatGPT or Claude with one click. Stolen and refined from issues you should be reading.
The Agent Access Auditor
Decide account by account which ones an AI browsing agent should be allowed to touch — and which to lock away — with a green, yellow, or red verdict for each.
The AI Travel Companion Interview
Turn AI into a trip planner that remembers your preferences for the whole trip — not just for one question.
The Family Document Digitizer
Turn any old family document into a clean, shareable write-up — with a privacy check and a fact-check built in.
The World-Model Cause-and-Effect Trainer
Experience the difference between predicting words and predicting cause-and-effect through guided interview questions.
AI Layoff Exposure Advisor
The Model Tier Routing Audit
Most workflows were built when one model tier was the only sane default. This prompt interviews you about one workflow you already run, step by step, then tells you which tier each step actually needs, where downgrading would be a mistake, and the single change that saves the most for the least risk.
The AI Compute Dependency Evaluator
The Ruthless Line Editor
Interviews you about your own paragraph, then hands back only cuts, flags, and a one-line verdict — never a rewrite in someone else's voice.
The AI Mode Connected-Apps Audit
Interviews you about a repetitive task, then tells you plainly whether AI Mode's Instacart/Canva/YouTube Music integrations actually save you a step — or not.
The 'Is This Actually Done?' Audit
Interviews you about one piece of AI-produced work, then tells you whether it's actually done or just looks done -- built around what the Remote Labor Index found about where AI deliverables actually fail.
The AI-Hype Headline Check
Interviews you about an "AI did X" headline you just read, walks you to the primary source, and checks whether the paper's own methodology language actually supports the claim — or whether the press release oversold it.
The Agent Payment Readiness Check
Before you let an AI agent pay for anything on your behalf, this interview walks you to a specific spending limit and the one habit that would catch a mistake fast enough to matter.
The Effort Audit
Interviews you about one recurring AI task, then names the model tier and effort level it actually needs — and where you are currently overpaying.
The Login-Wall Task Audit
Interviews you about the recurring task you keep doing yourself, then tells you honestly whether it's a good fit for a work agent that now remembers its own login — and drafts the actual handoff instructions.
Is This Real?
Interviews you about a suspicious celebrity endorsement, ad, or "exclusive" article, walks you through the actual verification checks, and gives you a real/likely-fake/unconfirmed verdict — not a guess.
The Real Use Audit
Interviews you about your own last week of AI use, checks it against the 2026 real-use research, and hands you one deliberate change — not a generic tip.
Which AI Can Actually Write to Your Spreadsheet
Find out whether your AI can actually write to your Google Sheet — or only read it — and get the exact route to real write access for your platform.
The Document Pile Audit
Interviews you about your messiest document pile, then hands you a build plan: exactly what to load into your first Gemini Notebook, the first five questions to ask it, and which output to generate first.
The Spec Adherence Test
A copy-paste prompt that builds you a side-by-side AI test with a right answer — so you can see which tool actually follows instructions rather than which one just looks impressive.
The AI Work-Agent Fit Audit
Interviews you about your own workload, then drafts real instructions for handing a recurring task to ChatGPT Work or Claude Cowork — and tells you honestly if it's not a good fit yet.
The AI Delegation Audit
Audits your last 5-10 AI tasks and tells you the single biggest habit to change to get more out of any chatbot.
The AI Subscription Audit
Interviews you about your task mix, volume, and current AI spend — then tells you which rung of the July 2026 price ladder fits, and whether your current plan is still the right one.
The "Which Claude Do I Actually Need" Checklist
Interviews you about your actual task mix, then tells you which Claude tier fits your day-to-day work.
The Client Email Audit
Paste any client email and this turns it into a clean checklist of everything they actually asked for — buried deadlines included — then drafts a reply that asks instead of inventing. The anti-fabrication audit from our six-model showdown, ready to run in any AI.
