Examine a proposal from more than one perspective. Use these prompts to compare alternatives, surface assumptions, trace consequences and prepare a structured review. Suggested workflows are starting points; you choose which tools and providers to use.
How to use these prompts
Choose a template and open Preview & customise.
Fill the named fields with your details and check the completed draft.
Copy it into your preferred AI tool, or sign in to prepare a Chat draft in Ortivo.
Copying is free and does not call an AI. Generating an answer requires your own configured provider or an available trial. Review important facts and every draft before use.
Critically evaluate this proposal: {{proposal}} within {{operating_environment}}. First, make the strongest possible case for why it will meet {{success_criteria}} (Blue Team). Se…
Suggested: Multi-Model Compare → AI CouncilRead template
Critically evaluate this proposal: {{proposal}} within {{operating_environment}}. First, make the strongest possible case for why it will meet {{success_criteria}} (Blue Team). Second, ruthlessly attack its fragile assumptions, hidden costs, and second-order consequences (Red Team).
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Hidden Assumption Extractor
Deconstruct the following plan or argument in {{domain}}: {{argument_or_plan}}. Identify the main implicit, unstated assumptions required for this plan to succeed. Rank those assu…
Suggested: AI Council → Decision NotebookRead template
Deconstruct the following plan or argument in {{domain}}: {{argument_or_plan}}. Identify the main implicit, unstated assumptions required for this plan to succeed. Rank those assumptions from least verified to most verified, and suggest an empirical test for the top three.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Cognitive Bias & Blind-Spot Audit
Review our rationale ({{decision_rationale}}) given our recent history ({{historical_context}}). Identify where sunk-cost fallacy, confirmation bias, survivorship bias, or anchori…
Suggested: AI CouncilRead template
Review our rationale ({{decision_rationale}}) given our recent history ({{historical_context}}). Identify where sunk-cost fallacy, confirmation bias, survivorship bias, or anchoring may be distorting our judgment, and reframe the problem from a zero-based perspective.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Multi-Stakeholder Perspective Simulator
Simulate how three distinct stakeholders—{{stakeholder_a}}, {{stakeholder_b}}, and {{stakeholder_c}}—will react to {{initiative}}. Detail each group's primary incentives, unspoken…
Suggested: Multi-Model CompareRead template
Simulate how three distinct stakeholders—{{stakeholder_a}}, {{stakeholder_b}}, and {{stakeholder_c}}—will react to {{initiative}}. Detail each group's primary incentives, unspoken fears, likely objections, and the specific concessions required to win their alignment.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Cross-Model Consensus & Divergence Map
Analyze {{question_topic}} where the stakes are {{decision_stakes}}. Separate facts with strong empirical consensus from areas of legitimate expert disagreement. Explain why diffe…
Suggested: AI CouncilRead template
Analyze {{question_topic}} where the stakes are {{decision_stakes}}. Separate facts with strong empirical consensus from areas of legitimate expert disagreement. Explain why different analytical frameworks reach opposing conclusions on this topic.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Second- and Third-Order Consequence Trace
Trace the ripple effects of implementing {{policy_or_change}} across {{system_or_market}} over {{timeframe}}. Map the immediate 1st-order effect, the reactive 2nd-order behavioral…
Suggested: Multi-Model CompareRead template
Trace the ripple effects of implementing {{policy_or_change}} across {{system_or_market}} over {{timeframe}}. Map the immediate 1st-order effect, the reactive 2nd-order behavioral adaptations by participants, and the long-term 3rd-order structural equilibrium.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Devil's Advocate Counter-Thesis
Our team currently believes {{consensus_belief}} based on {{evidence_cited}}. Construct the most rigorous, data-grounded counter-thesis that tests our current belief against the s…
Suggested: AI CouncilRead template
Our team currently believes {{consensus_belief}} based on {{evidence_cited}}. Construct the most rigorous, data-grounded counter-thesis that tests our current belief against the strongest available counter-evidence, and specify what disconfirming evidence we have overlooked.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Steelman Competing Alternatives
Present the strongest, most charitable version ("steelman") of both {{option_a}} and {{option_b}} evaluated against {{evaluation_criteria}}. Avoid strawman critiques and identify …
Suggested: Multi-Model CompareRead template
Present the strongest, most charitable version ("steelman") of both {{option_a}} and {{option_b}} evaluated against {{evaluation_criteria}}. Avoid strawman critiques and identify the exact boundary conditions under which Option A outperforms Option B and vice versa.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Ethical, Reputational & Regulatory Stress-Test
Audit {{feature_or_campaign}} launching in {{jurisdiction}} for {{public_audience}}. Identify potential regulatory compliance gaps, data privacy concerns, unintended misuse vector…
Suggested: Multi-Model CompareRead template
Audit {{feature_or_campaign}} launching in {{jurisdiction}} for {{public_audience}}. Identify potential regulatory compliance gaps, data privacy concerns, unintended misuse vectors, and how a hostile headline might frame this initiative.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.
AI Council & perspectives
Action Plan Synthesis & Dependency Graph
Synthesize a concrete execution plan to achieve {{objective}} by {{deadline}} within {{constraints}}. Sequence tasks by critical-path dependencies, assign clear milestone verifica…
Suggested: AI Council → Decision NotebookRead template
Synthesize a concrete execution plan to achieve {{objective}} by {{deadline}} within {{constraints}}. Sequence tasks by critical-path dependencies, assign clear milestone verification criteria, and identify the single likeliest bottleneck.
Use only supplied material or sources actually accessed. Distinguish evidence, estimates and assumptions. Do not invent facts, citations, test results or actions performed. Flag missing information and tool limitations.