Magai

Prompt pack for marketers, agencies and creators, PDF, 7 pages

The monthly client report prompts

The brief, eight prompts and a six line check that turn a client's analytics export into a monthly report you can trust, for the Thursday before it's due.

  • The client brief template, with goals, voice and banned words
  • Eight prompts in order, from the data check to the task list
  • A six line check to run by hand before you send
  • The reporting agent's instructions, ready to paste

Made in the tutorial How to Use AI for Client Reporting That Holds Up, where every prompt in it is run to its result.

This is for the person who owns the monthly report for six clients and has until Friday. It is the set of prompts that turned a sample analytics export into a report that said the right thing about a number that looked like a failure and was a tracking problem.

Inside is the client brief template, the eight prompts in the order they run, the six line check to do by hand before you send, and the instructions for a reporting agent. Every prompt is a code block with the blanks in square brackets. Nothing outside the brackets needs changing.

Paste the brief and the export into a new thread in the client's folder in Magai, and run step one first. Start with /Claude for the writing and switch to /GPT or /Gemini for the second read. The thread keeps the files and every reply, so the second reader sees what the first one saw.

A look inside

Three of the prompts, as you would paste them

Three pieces of it, as they are in the PDF. The rest is the same shape.

  • 1

    I'm writing the [month] report for this client. Before any writing, check the data. List what you see in each file, check whether the numbers agree with each other, and flag anything that looks like a tracking or data problem rather than a real change in performance. Do not write the report yet.

  • 2

    Now explain what moved and why. Make a table of the five biggest movements in [the number the client cares about], in dollars first and then percent. For each one, label the explanation as CONFIRMED BY THE DATA, LIKELY, or UNKNOWN, and say what we would check to confirm it. Do not assume anything I haven't told you.

  • 3

    You are the second reader. Check every number and every claim in the draft above against the files and against what I told you. Make a table: the claim as written, what the files show, and PASS, FIX or UNSUPPORTED. Then list anything a reader would take away that the numbers don't support, even if each number is right.

Save the ones you use to Magai’s prompt library and they are one click away in every chat, with every model. See how saved prompts work

The prompts are the start. Magai is where they run.

Every leading model in one chat, a workspace for your team, and your saved prompts one click away in all of it. Thirty-day money-back guarantee.