In a recent LinkedIn post, Ruben Hassid explores how to leverage AI effectively for creating sophisticated, board-ready spreadsheets, moving beyond simple data manipulation to strategic financial modeling. Hassid emphasizes that the true bottleneck in modern financial analysis is not the spreadsheet software itself, but the user’s ability to ask the right questions of AI tools.
Hassid highlights the critical need for structured prompting to ensure financial models are not only accurate but also comprehensible to executive audiences. He presents a comprehensive list of 30 prompts designed to guide AI in building, analyzing, and refining spreadsheets for high-level review.
“These prompts are everywhere now. Board decks. Investor models. Monthly reviews. Even messy bank exports. The formula bar used to be the bottleneck. Now it’s knowing what to ask.”
The core of Hassid’s advice centers on a five-step process for building robust financial models using AI assistance. He stresses that these prompts, while seemingly straightforward, can automate significant portions of an analyst’s workload, provided they are applied strategically.
The Foundation: Assumptions and Transparency
Hassid’s first principle for effective AI-driven spreadsheet creation is to demand transparency from the outset. Before any complex calculations begin, he advises forcing the AI to articulate its underlying assumptions.
“Force the AI to expose its logic. Before anything, ask ‘list your top 10 assumptions.’ Non-negotiable.”
This foundational step, according to Hassid, is crucial for building trust and understanding. By identifying assumptions early, users can ensure they align with business realities and avoid potential misinterpretations down the line.
Structuring for Clarity and Scenario Planning
Beyond assumptions, Hassid details how to structure spreadsheets for maximum clarity and analytical flexibility. This includes using named ranges for readability and setting up distinct tabs for different components of the financial model, such as a P&L, revenue forecasts, and a sales funnel.
A key element Hassid advocates for is the inclusion of scenario toggles, allowing for the easy comparison of Base, Bull, and Bear cases. This feature is vital for board-level discussions, enabling stakeholders to understand potential outcomes under various market conditions.
Readability and Input Separation
Hassid argues that readability is paramount. He contrasts unintelligible formulas like “=B4C71.12” with the clarity provided by named ranges that read like natural language. Furthermore, he insists on separating input variables onto dedicated ‘Assumptions’ tabs, preventing hardcoded numbers within formulas and enhancing auditability.
“Keep all inputs on an Assumptions tab.”
This separation, as Hassid explains, makes it easier to track changes, understand the impact of different assumptions, and perform thorough audits.
Analysis, Debugging, and Stress-Testing
Hassid also provides prompts for performing analysis directly through AI, identifying trends, comparing actuals to budgets, and categorizing expenses without necessarily relying on complex manual formula creation. He emphasizes the importance of debugging and auditing the model before it reaches stakeholders.
Prompts like “Explain what the formula in [CELL] does in English” and “Trace [CELL] back to its source inputs” are presented as essential tools for ensuring accuracy and understanding. Hassid’s approach culminates in the critical step of stress-testing the model.
“Stress-test the model — what breaks first?”
According to Hassid, identifying potential failure points or edge cases before a board meeting is far more productive than encountering them during a presentation. This proactive approach, he suggests, ensures that the financial model is robust and defensible.
In conclusion, Ruben Hassid’s insights on LinkedIn offer a practical framework for financial professionals seeking to enhance their spreadsheet creation capabilities with AI. By focusing on clear prompting, structural integrity, and rigorous auditing, users can move towards building models that are not just data-driven, but also strategically insightful and board-ready.
📝 About This Content
This article is based on insights shared by Ruben Hassid on LinkedIn.
📅 Originally posted on June 2, 2026 | View original post on LinkedIn →