Claude GuideDevantia × Executive Partners Group
DevantiaExecutive Partners Group
0/23 Jean-Christophe Leroy
Jean-Christophe Leroy
Guide author
✓ Verified on September 3, 2026⏱ 5 min read
Module 03b

Decision frameworks — think better, faster

A good prompt isn't always enough: facing a complex decision, it's the thinking framework that makes the difference. Here are 12 proven frameworks from consulting and strategy — each with a ready-to-copy prompt. Claude applies the framework to your context, with your figures and your constraints.

A problem fuzzy or complex 🔍 Analyze SWOT · Fishbone · MECE Porter · First principles ⚖️ Prioritize Eisenhower · Decision matrix · Cost-benefit 🧭 Explore Scenarios · Ansoff Blue ocean · 6 hats 🛡️ Anticipate Pre-mortem · 5 Whys Hypothesis testing Claude applies the framework to YOUR real context A decision well argued
In plain terms These frameworks turn a vague question ("what should we do?") into structured analysis. Paste the prompt, replace the [brackets] with your situation, and ask Claude to challenge its own answer ("what are the flaws in this reasoning?").

The library — 12 frameworks, 12 prompts

SWOT

Strengths, weaknesses, opportunities, threats.

Run a SWOT analysis of [topic], taking into account [competitors / regulation / market]. End with the 3 priorities that follow from it.

Eisenhower Matrix

Sort by urgency and importance.

Here are my tasks: [list]. Sort them into urgent/important (do, schedule, delegate, eliminate) and propose a plan for the week.

Porter's 5 Forces

Assess competitive intensity.

Analyze our industry [specify] with Porter's 5 forces (rivalry, new entrants, substitutes, buyer power, supplier power), then derive 3 levers for advantage.

MECE

Structure with no overlap and no gaps.

Break down the problem [topic] into MECE categories (mutually exclusive, collectively exhaustive) and propose an action plan by category.

Pre-mortem

Anticipate failure before launching.

Our project [describe] will launch in [timeframe]. Assume it has failed: list the 8 most likely causes and one preventive fix for each.

5 Whys

Trace back to the root cause.

Recurring problem: [describe]. Apply the 5 Whys method to identify the root cause, then propose a durable countermeasure.

Decision matrix

Compare options on weighted criteria.

Compare [options] against [criteria: cost, timeline, risk, impact] with weightings. Give a scored table and a justified recommendation.

Cost-benefit

Quantify before committing.

Should we [decision]? Compare costs and benefits over 3 years vs. doing nothing, and recommend the best choice with the key assumptions.

Ansoff Matrix

Choose a growth axis.

Our offering [describe] is plateauing in [market]. Use the Ansoff matrix (penetration, product, market, diversification) and prioritize the most realistic axis.

Scenario planning

Prepare for several futures.

We're expanding into [market]. Build 3 scenarios (optimistic, base case, pessimistic) over 3 years and a strategy that holds up in all three.

First principles

Rebuild from the ground up.

Our [line-item] cost is too high. Break it down into fundamental building blocks and rebuild an optimal approach from scratch.

Bono's 6 Hats

Decide from multiple angles.

Analyze the decision [topic] with the 6 hats: facts, risks, benefits, emotions, creativity, process. End with an actionable synthesis.
💡 Expert tip Chain two frameworks: first Analyze (SWOT or Porter) to understand, then Prioritize (decision matrix) to decide. And keep the push-back reflex: "give me the strongest argument against this conclusion."
🎯 Practical case — an investment trade-off "We're torn between acquiring a competitor and building the feature in-house. Apply a cost-benefit analysis over 3 years, then a decision matrix (cost, timeline, execution risk, strategic impact, weighted). End with a recommendation and the 2 conditions that would invalidate it."
🛠️ Your turn — 5 minutes

Pick a decision in progress and paste the Pre-mortem prompt with your real data.

Expected result : A list of 8 causes of failure, including at least two you had not considered.