01
Pattern match
The question’s structure is compared with the 60-category question-style bank.
EXAMPLE CASE STUDY
OwnerExamining a founder's capital-allocation decision
Follow a capital-allocation question through comparable criteria, downside testing, reversibility and the human consequences of reduced flexibility.
01 · ASK
The question as the user posed it
Pygar begins by preserving the user’s wording. Before any answer is formed, the engine separates the stated decision from its assumptions, constraints and missing evidence.
USER INPUT
Should I invest our available capital in growth, resilience or a new acquisition opportunity?
WHAT THE OPENING FRAME HIDES
The three options operate on different time horizons and create different kinds of exposure. The most exciting opportunity can dominate attention while liquidity, management capacity, reversibility and the cost of losing future choices remain implicit.
HOW PYGAR DETERMINED THIS
The engine looks for compound choices, hidden thresholds, assumed causes and missing decision criteria. These signals reveal where the opening wording may be narrowing the available reasoning.
02 · CLASSIFY
How Pygar chose the reasoning route
The classifier does not decide what the user should do. It identifies the structure of the question and selects the reasoning family, depth mode and prompt set most suited to examining it.
ROUTE SELECTED FROM THE 60-CATEGORY BANK
Matched within Pygar’s 60-category question-style bank as Strategic investment and risk. Family: Strategic Judgement. Mode: Standard. The selected route compares options on consistent criteria, tests downside and makes uncertainty explicit. It does not provide financial advice.
02
Family route
The dominant reasoning demand selects a cognitive family and operating mode.
03
Prompt assembly
The route builds five independent briefs without determining the answer.
03 · DELIBERATE
Five independent perspectives
Every panel role receives the same classified question with a distinct reasoning brief. The roles work independently, so one convincing argument cannot silently shape the others.
5
isolated reads, each optimized for a different failure mode in human judgement.
Lead
Clarify the missionDefine the objective the capital must serve and the minimum resilience that cannot be traded away. Compare all three options against the same criteria: strategic value, time to evidence, management demand, reversibility and downside.
Depth
Judge the contextSurface the assumptions behind revenue timing, acquisition fit, integration effort and access to future funding. Confidence is not comparable evidence. Specify which assumption is measured, inferred or still unknown for each option.
Test
Stress-test the frameReverse the strongest assumption in each case. If growth arrives later, the acquisition requires more attention or funding tightens, which commitment leaves the business able to respond and which creates a path that is difficult to reverse?
Ground
Apply real constraintsModel cash runway, decision stages, leadership capacity, operating dependencies and reversal cost. Separate an option that can be piloted in tranches from one that creates immediate legal, financial or integration exposure.
Human
Check people and impactReduced flexibility concentrates pressure on the founder and leadership team. Examine the effect on employees, existing customers and decision quality if one opportunity consumes the attention required to keep the current business resilient.
04 · SYNTHESIZE
Where the panel converged and what remained unresolved
The synthesizer compares the five reads for agreement, contradiction, shared assumptions and missing evidence. A separate verification pass then checks whether the combined answer is clear, bounded and honest about uncertainty.
PANEL SYNTHESIS
What the five reads establish together
The options should not receive one simultaneous yes or no. Protect a defined resilience floor, stage the growth investment where evidence can be learned cheaply, and treat acquisition diligence as a separate decision with commercial and integration gates before irreversible commitment.
VERIFICATION PASS
What the answer must not conceal
Comparable numbers are still needed for downside, time to evidence, management capacity and opportunity cost. The panel can structure those comparisons but cannot determine risk appetite or replace regulated financial, legal and tax advice.
HOW PYGAR PRODUCED THIS
The engine preserves useful disagreement, prioritises findings supported across more than one read and keeps unsupported certainty visible. Verification can trigger a bounded second synthesis when the result is unclear or incomplete.
05 · REFRAME
Turn the findings into better questions
Pygar does not merely replace the user’s question. It shows how the frame changed, then offers three deliberate operations that can expose sharper evidence and unexplored lines of consideration.
WHAT CHANGED IN THE FRAME
The question moves from Which option is best? to What must be protected, what can be learned reversibly, and what evidence justifies each successive commitment?
CLARIFY
Make the decision and evidence threshold more precise.What outcome must this capital create, what resilience floor is non-negotiable and over what time horizon will success be judged?
WIDEN
Introduce a credible alternative or overlooked stakeholder.How do growth, resilience and acquisition compare when each is scored for downside, management attention, time to evidence, reversibility and lost future options?
DEEPEN
Probe the assumption most likely to change the decision.If expected growth were delayed by twelve months, which staged commitment would preserve the greatest ability to adapt without undermining the core business?
REFINED QUESTION READY TO ASK
After protecting an agreed resilience floor, how should we stage growth investment and acquisition diligence so that each release of capital is tied to evidence, management capacity, downside limits and a clear reversal point?
06 · DECIDE
Convert insight into accountable human action
Pygar finishes by making the next evidence-producing action explicit while protecting the human decision boundary. The engine expands judgement; it does not replace authority, context or responsibility.
WHAT THE USER CAN DO NEXT
A bounded action that produces evidence
Apply one scoring frame to every investment option, including strategic value, dependencies, downside and reversibility. Release funding in stages, with explicit evidence gates before the next commitment.
HUMAN DECISION BOUNDARY
Where Pygar stops
Pygar can reveal assumptions and structure decision gates. The owner remains responsible for risk appetite and must use appropriate financial, legal and tax advice before committing capital.
1
structured recommendation, tested against five perspectives and returned to the person or team accountable for the choice.
Continue with another case study
