Step 01
Create a New ChatGPT Project
Create a dedicated ChatGPT Project named for the preparation use case. Keep it separate from unrelated chats so the manager context and project memory remain focused.
IntermediatePersonal
How to Create an AI Simulation of Your Boss Using ChatGPT Projects
Build a ChatGPT Project from your manager's operating manual and other professional artifacts, then use it to rehearse pitches and working conversations in the style of feedback that manager is likely to give.
Try this with your AI assistant
Download the skill for this workflow. Version 1.0.1.
Source episode · 07:58How I AI: Hiten Shah's Advanced ChatGPT Workflows for a Personal Coach, Sales Playbooks, and Managing Up
with Claire Vo
Hiten creates a What Would Morgan Do project, uploads his boss's operating manual, generates project instructions, and tests how to pitch an ambitious product idea.
Before you start
What you need
- A ChatGPT Project
- Manager authored operating manuals or professional writing
- Optional relationship context you are authorized to use
- A real conversation or decision to prepare for
What you’ll make
A manager perspective simulator that gives source grounded preparation for pitches, updates, blockers, and difficult conversations.
Tools used
- ChatGPTVisitChatGPT
OpenAI conversational AI
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Step 02
Gather and Upload Contextual Files
Upload manager authored material such as an operating manual, public writing, team guidance, or examples of feedback you are authorized to use. Prefer first party artifacts over speculation.
Step 03
Generate Project Instructions with a Meta-Prompt
Ask ChatGPT to draft the project instructions from those files. Require it to ground advice in the sources, label inference, and help prepare rather than claim to predict the person.
Example prompt
Create instructions for a project that helps me prepare for conversations with my manager using the uploaded professional artifacts. Reflect their documented priorities, decision style, communication preferences, and expectations. Ground advice in the files, cite the relevant source when practical, label inference, and never claim to know what they will definitely say.
This meta-prompting technique is a clever shortcut to creating a detailed and accurate persona for your AI assistant. Copy and paste the AI's output directly into the project's instruction settings.
Step 04
Test the Project with a Real-World Scenario
Test the project with an upcoming conversation. Ask for the likely concerns, strongest framing, evidence to bring, and questions to expect, then compare the response with what you know from the source material.
Example prompt
I want to pitch an ambitious product idea to Morgan. Based on the uploaded artifacts, how should I frame the user problem, evidence, risk, and ask? List the concerns he is likely to raise, why you infer each one, and a concise opening I can use. Do not invent preferences that are not supported by the files.
What good looks like
- Advice cites or clearly reflects the uploaded manager artifacts.
- The project distinguishes documented preferences from inference.
- A real test response sounds specific rather than generic.
- Sensitive or private material is excluded unless authorized.
Build your next product with ChatPRD
Turn an idea into a PRD, user stories, and a plan.
Runbook notes
How to recover when the loop fails and where human judgment helps.
If it goes sideways
- The response sounds like generic management advice
- Add manager authored examples and instruct the project to cite the artifact or state when it lacks evidence.
- The simulation exaggerates one personality trait
- Prioritize direct operating guidance over personality frameworks and require balanced advice with uncertainty.
- The project includes material you should not upload
- Use only work artifacts you are allowed to process, remove confidential details, and follow company AI policy.
Related workflows
intermediateDataMeta Muse
How to Use AI for Hobby Improvement and Data Analysis for Golf & Chess
Connect data from your hobbies (like golf scores or chess games) to an AI agent to get automated analysis, visual dashboards, and actionable coaching insights. Turn raw data into a story that helps you improve.
Open
beginnerPersonalMeta Muse
How to Create a Personalized Shopping Catalog from Your Instagram Saves Using AI
Turn your unstructured Instagram 'Saved' collection into a fun, personalized shopping catalog. This workflow uses an AI agent to organize your saves and present them in a nostalgic, engaging format like the SkyMall magazine.
Open
advancedContentMeta Muse
How to Revive an Old Blog or Digital Archive as a Personal AI Podcast
Resurrect your old digital content, like a forgotten blog from Blogger or Tumblr, by using an AI agent to find, consolidate, and transform it into a daily personal podcast. Reconnect with your past self in a new, listenable format.
Open
Start shipping better products.
Join 250,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.
Free to start · 14-day Pro trial · SOC 2 Type II
