SAT Selection Guide

Query: Given a problem type, bias risk, or point in the analytic process — which SAT(s) should I apply?

Use this page to select the right technique. For how techniques work together in sequence, see SAT Pipeline. For the full cross-reference, see Bias x SAT Matrix.


Select by: Where Are You in the Process?

StageProblemReach For
Before you startNeed to scope what questions to askStarbursting
Before you startNeed to generate candidate explanationsBrainstorming
During analysisHave a preferred explanation and want to test it rigorouslyACH
During analysisNeed to surface hidden assumptions in the current lineKey Assumptions Check
During analysisNeed to evaluate source reliabilityQuality of Information Check
During analysisNeed an adversary’s perspectiveRed Team Analysis
During analysisNeed to monitor for changing conditionsIndicators or Signposts of Change
Challenging a conclusionA consensus has formed; want to stress-test itDevil’s Advocacy
Challenging a conclusionNeed truly independent views (not just devil’s advocate)Team B
Planning / forecastingNeed to think about uncertain futuresAlternative Futures Analysis
Planning / forecastingNeed to consider low-probability but high-impact eventsLow-Probability Analysis
Post-analysisNeed to stress-test a finished productWhat If? Analysis, Key Assumptions Check

Select by: Which Bias Are You Worried About?


Select by: Problem Type

Attribution / “Who did this?”

Primary risk: Confirmation Bias, Mirror Imaging, Anchoring Bias

Recommended sequence:

  1. Brainstorming — generate all possible actors
  2. ACH — evaluate evidence against all actors simultaneously
  3. Red Team Analysis — would the attributed actor actually behave this way?

Forecasting / “What will happen?”

Primary risk: Status Quo Bias, Overconfidence Bias, Availability Heuristic

Recommended sequence:

  1. Alternative Futures Analysis — develop multiple scenarios from key uncertainties
  2. Low-Probability Analysis — explicitly address the tail
  3. Indicators or Signposts of Change — define observable signals for each scenario

Reviewing a finished product / “Is this analysis sound?”

Primary risk: Confirmation Bias, Anchoring Bias, Hallucination (LLM)

Recommended sequence:

  1. Key Assumptions Check — surface all load-bearing assumptions
  2. Devil’s Advocacy — build the best case against the conclusion
  3. Quality of Information Check — audit sources and evidence quality

Planning / “What could go wrong?”

Primary risk: Overconfidence Bias, Status Quo Bias, Motivated Reasoning

Recommended sequence:

  1. What If? Analysis — assume it has already failed; work backwards
  2. Low-Probability Analysis — enumerate the tail risks
  3. Key Assumptions Check — identify which assumptions, if wrong, cause the plan to fail

Adversarial / “What will an opponent do?”

Primary risk: Mirror Imaging, Framing Effect, Overconfidence Bias

Recommended sequence:

  1. Outside-In Thinking — force analysis from the adversary’s external constraints
  2. Red Team Analysis — adopt adversary persona and evaluate the plan from their perspective
  3. What If? Analysis — assume the adversary succeeded; reconstruct how

Multi-agent deliberation / “How do we prevent echo chambers?”

Primary risk: Groupthink, Sycophancy, Confirmation Bias

Recommended pattern:

  • Run agents independently before any agent sees others’ outputs (Team B pattern)
  • Assign one agent an explicit adversarial critique role (Devil’s Advocacy pattern)
  • Use different system prompts or models to prevent synchronization
  • See SAT Pipeline for the full multi-agent architecture

Minimum Viable Intervention

When you can only apply one SAT and bias risk is general, these deliver the broadest coverage:

PrioritySATBiases coveredLLM implementation complexity
1stKey Assumptions CheckAnchoring, Confirmation, Overconfidence, Motivated Reasoning, Status QuoSingle prompt; zero-shot
2ndDevil’s AdvocacyConfirmation, Groupthink, Motivated Reasoning, SycophancySingle adversarial prompt; or two-agent
3rdACHConfirmation, Anchoring, Availability, Motivated Reasoning, GroupthinkMulti-step sequential (see Roberts: LLM SATs FTW (2025))

See Also

SAT Pipeline | Bias x SAT Matrix | SATs for LLM Agents