Step 01
Set Up the 'AI Co-Founder' Persona
Create a business sparring assistant around documented decision principles, expertise, company context, and prior decision examples. Do not frame it as a literal copy of a colleague.
BeginnerProduct
How to Build an 'AI Co-Founder' in ChatGPT for On-Demand Brainstorming
Create an on-demand business sparring partner from documented company context and decision principles, using it to challenge a rough idea before bringing the stronger options to real teammates.
Try this with your AI assistant
Download the skill for this workflow. Version 1.0.1.
Source episode · 46:00How I AI: Building a Personal AI Wellness Coach to 'Feel 25 in a 40-Year-Old Body'
with Claire Vo
Lucas describes loading an AI assistant with business context and the complementary thinking styles of his co-founders so he can pressure-test thorny questions when distributed teammates are unavailable.
Before you start
What you need
- A current strategy brief and operating constraints
- Documented decision principles and areas of expertise
- Examples of prior decisions and their reasoning
- A clear list of information that must stay out of the model
What you’ll make
A structured decision memo with options, assumptions, risks, counterarguments, and questions for the real leadership team.
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
Provide Business Context
Load a dated strategy brief with goals, constraints, metrics, customers, current bets, and unresolved tensions. Exclude confidential information unless the workspace and use are explicitly approved.
Step 03
Initiate a Brainstorming Session
Start with the decision, why it matters now, options already considered, and missing information. Ask for distinct alternatives and a pre-mortem.
Example prompt
Help me pressure-test [decision]. Current goal: [goal]. Constraints: [constraints]. Evidence: [evidence]. Options considered: [options]. Generate at least two materially different alternatives, the strongest argument against my current preference, likely second-order effects, missing evidence, and a pre-mortem. Cite the supplied context and mark unsupported assumptions.
Step 04
Use It as a Sounding Board
Challenge the response in a second pass, then convert the useful reasoning into a short memo for the real team with options, tradeoffs, recommendation, confidence, and decisions still requiring people.
Example prompt
Turn this discussion into a decision memo for [team]. Include context, options, evidence, tradeoffs, recommendation, confidence, reversible tests, open questions, and named decisions for the accountable people. Do not write as or attribute views to a synthetic co-founder.
What good looks like
- The assistant cites current company context rather than inventing a co-founder’s opinion.
- At least two materially different options and a serious counterargument are explored.
- Private or regulated information stays within the approved workspace and source set.
- No strategic commitment, external message, or team decision occurs without the accountable people.
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 assistant imitates a colleague and creates false confidence
- Model documented decision principles instead of identity, use third-person analysis, and cite examples.
- The advice relies on stale strategy, metrics, or constraints
- Date the source packet, state freshness requirements, and refresh it before consequential decisions.
- The assistant validates the founder’s first idea without pressure-testing it
- Require competing options, disconfirming evidence, pre-mortem risks, and a recommendation with uncertainty.
- A synthetic discussion substitutes for alignment with actual teammates
- Turn the output into a decision memo and route unresolved tradeoffs to the accountable team.
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
