AI agent for founders
Business Model Sensitivity Agent
Founders know exactly which assumptions make or break their model.
What it does
Business plans hide which assumptions really decide whether the business works. Readers see one profitable base case. This agent calculates the base case, then chooses sensitivity tests where the model is most fragile, near breakpoints where profit turns to loss. It runs each scenario and checks whether the drivers of viability are clear. If not, it tests the next assumption. It reports which assumptions flip viability and by how much. If viability depends on an assumption with no supporting evidence, it looks for evidence or says so plainly. The owner of the plan decides what to change. Edge case: two assumptions that only break viability together are tested as a pair.
How it works
Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.
Read the steps as a list
- Model submitted
- Calculate the base case
- Choose the next sensitivity near a breakpoint
- Run the scenario
- Are the viability drivers clear?If not: test the next assumption. Back to step 3.
- Write the decision brief with key dependencies
- Assumption-sensitive model review
How it decides
It explores the assumptions near breakpoints first and stops when the key drivers are clear.
- Next test: the assumption closest to a breakpoint.
- Unsupported driver: search for evidence or flag it plainly.
- Pairs: test two assumptions together when neither breaks viability alone.
- Stop: when the top three viability drivers are clear.
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Viability measure (default operating margin above 0%)
- Range for each sensitivity test (default plus or minus 10%)
- Maximum tests per review (default 15)
- Output format (default decision brief with a tornado chart)
- Who receives the review (default the plan owner)
What keeps you in control
It always asks you first
- Investment advice
- Spending decisions
Hard limits
- No investment advice.
It stops when
- Done: key drivers identified.
Set it up
We guide you through the set-up, step by step
Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.
- One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
- The agent then walks you through connecting your own data, one source at a time
- A downloadable copy with the flow chart, the rules and the full guide
