Replace vague hunches with calibrated probability estimates you can track and improve over time.
by deciqai2 stars
Coding
Dual-System Thinking (System 1 / System 2)
Try itMake better high-stakes decisions by knowing when to trust intuition and when to force slow analysis.
What it does
A structured framework for applying Dual-System Thinking (Kahneman/Tversky). System 1 handles fast, automatic pattern recognition; System 2 does deliberate analysis. The skill provides a 6-step process, a stakes × familiarity matrix for deciding when to recruit System 2, and a coaching mode with guided steps. It includes domain-specific patterns for hiring, investing, medical, and strategic decisions; a list of common rationalizations; and red flags for when System 1 is misleading. Outputs a structured decision template with calibration logging. Designed for AI agents working alongside humans on consequential calls.
When to use it
- High-stakes decision feels obvious and needs verification
- Team converging fast without pushback on a consequential choice
- Evaluating a confident AI/LLM response on a high-stakes matter
- Unfamiliar domain where gut instinct is being trusted
The skill document
Dual-System Thinking (System 1 / System 2)
Overview
Two parallel modes: System 1 — fast, automatic, effortless (pattern recognition, gut feel). System 2 — slow, deliberate, effortful (analysis, computation, critical evaluation). System 1 runs ~95% of decisions by default; System 2 engages only when recruited. Most cognitive biases are System 1 shortcuts misapplied where System 2 should have intervened.
Composes with metacognition, every cognitive-bias skill (anchoring, confirmation-bias, availability-heuristic, etc.), deep-work, and wu-wei.
When to Use
- Decision feels obvious and is high-stakes; unfamiliar domain + fast intuition; time pressure on consequential matter; team converging without stress-test; depleted (tired/hungry/pressured)
- Designing a process or interface that depends on user attention
- Acting on a fast, fluent, confident AI/LLM answer (AI adoption, AI hype, "the AI said so") on a high-stakes call — when to force slow verification of a confident machine response
Not when: routine low-stakes decisions; calibrated expert System 1 in this exact domain; emergency requiring speed.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete decision → run The Process directly.
- Coach mode: user is unfamiliar → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line: when a high-stakes decision feels obvious, that obviousness is a warning — System 1 is firing and may need System 2 to check it.
- Check fit: routine low-stakes decisions are fine for System 1. This framework is for consequential, novel, or statistically-loaded decisions.
- Elicit the specific decision: what's being decided? Does it feel obvious? Are you tired / pressured / in your area of trained expertise?
[WAIT — do not advance until user responds]
- Work through: what's the System 1 answer? what's the System 2 check? what bias might be active? what procedure forces System 2 engagement?
[WAIT — do not advance until user responds]
- Close: name the system used and the procedure applied.
[WAIT — do not advance until user responds]
The Process
Step 1 — Identify decision + initial answer: note what comes to mind quickly, your confidence, and time-to-answer.
Step 2 — Classify system: quick + automatic + confident + no felt effort = System 1; slow + deliberate + uncertain + felt effort = System 2.
Step 3 — Recruit decision:
| Stakes | Familiarity | Recruit System 2? |
|---|---|---|
| Low | High | No |
| Low | Low | Optional |
| High | High | Yes (verification needed) |
| High | Low | Mandatory |
Step 4 — Recruit via procedure: write down the question; list 3 alternatives; name the active bias; apply a checklist; consult base rates; run a premortem; take 24h if possible.
Step 5 — Compare outputs: if S1 and S2 agree → high confidence. If they diverge → S2 wins for novel/high-stakes; in calibrated expert domains, S1 may be right. Document the reason.
Step 6 — Calibrate: log decisions + outcomes by domain. High-calibration domains: trust S1 more. Low-calibration: always recruit S2.
Output Template
Decision: | Initial answer: | Time to arrive: | Confidence:
System in operation: S1 / S2 / mixed
Stakes: H/L | Familiarity: H/L | Recruit S2: Y/N
Procedure used: | S2 outputs:
S1 said: | S2 said: | Agree/disagree: | Final answer + reason:
Calibration log — Domain: | System used: | Outcome (when known):
→ Method in Action: Kahneman 2011 + 40 Years of Tversky-Kahneman Research
→ 2026 lens: LLMs as System 1 — when to force System 2 on a confident AI answer (2024–2026)
Pack: Key Domain Patterns
| Domain | S1 role | S2 role | Common error |
|---|---|---|---|
| Hiring | First impression | Structured rubric; work-sample | Halo effect dominates |
| Investing | Pattern recognition | Base rates; bear-case | "Good feeling" in novel domain |
| Medical diagnosis | Quick pattern-match | Differential; base rates | Anchoring on first impression |
| Strategic decisions | Founder intuition | Premortem; market analysis | Confident S1 without calibration |
Applying It Well
"Obvious" is a warning, not a confirmation — treat it as a hypothesis. Structural System 2 recruitment (checklists, premortems, decision journals) beats willpower. Trained System 1 in a calibrated domain is valuable; outside that domain, it's dangerous.
→ Primary sources: references/sources.md
Common Rationalizations
[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.
| Fake move | Reality |
|---|---|
| [D] "I trust my gut" | Sometimes warranted (calibrated domain). Often a defense against System 2 discipline. Check the track record. |
| [D] "It's obvious; we don't need to overthink" | "Obvious" is System 1 output. The check is cheap; the cost of wrong is high. |
| [D] "We have to decide fast" | Often speed pressure is exaggerated. Most "urgent" decisions absorb a 1-hour structured pause. |
| [D] "I'm an expert; my intuition is reliable" | Expertise is domain-specific. Rapid, accurate, repeated feedback in this exact domain? |
| [D] "Cognitive biases don't apply to me; I know about them" | Bias-blind-spot effect: knowing reduces biases weakly. Structural procedure is the corrective. |
| [D] "The team agrees; we don't need to second-guess" | Team consensus is often System 1 cascade. Premortems are the System 2 counter. |
| → Add [O] entries here after each real use — paste the actual failure pattern | What went wrong and why |
Red Flags
High-stakes decision feels obvious and you're not checking it · tired/pressured making consequential decisions · novel domain + fast intuition · team converging without pushback · "I just know" is your justification · decision in <30 seconds on meaningful stakes
Verification
- System in operation diagnosed (S1 / S2 / mixed)
- Stakes × familiarity matrix applied
- If recruitment needed, structured procedure used
- S1 and S2 outputs compared; divergence justified
- Active cognitive biases listed
- Decision logged for calibration
Part of deciqAI Knowledge Skills — 227 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/c/dual-system-thinking · ⭐ Star the repo → https://github.com/deciqAI/knowledge-skills · Contributions welcome.
Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/dual-system-thinking.json
Questions people ask
- What does this skill actually do?
- It guides a structured comparison between System 1 (fast, automatic intuition) and System 2 (slow, deliberate analysis). You work through a 6-step process: identify the decision, classify which system is active, decide whether to recruit System 2, apply a verification procedure, compare outputs, and log for calibration.
- When should I NOT use this skill?
- Avoid it for routine low-stakes decisions, or when you have calibrated expert intuition in that exact domain and need to act fast. The document explicitly says: do not activate when you have well-trained, calibrated expert System 1 in that exact area and speed is needed.
- Does it work with other cognitive skills?
- Yes. The document lists explicit composition with metacognition, cognitive-bias skills (anchoring, confirmation-bias, availability-heuristic, etc.), deep-work, and wu-wei. It also references an AI-era lens for verifying confident LLM outputs.
Related skills
Make irreversible life decisions by projecting to 80 and naming which regret you'd rather live with.
by deciqai1 installs2 stars
Diagnose which mental domain is holding you back before choosing a cognitive intervention.
by deciqai1 installs3 stars
Diagnose feedback loops to predict how complex systems behave and find where intervention actually works.
by deciqai1 installs3 stars
Diagnose which of five decision domains your situation belongs to, then match the right approach — before committing to a plan.
by deciqai1 installs3 stars
Spot weak reasoning before you accept it — a structured audit for any argument
by deciqai2 stars
More from deciqai
Browse all skillsDiagnose your organization's strategic phase and spot misaligned initiatives before they drain momentum.
by deciqai7 installs2 stars
When multiple explanations all fit the evidence, pick the one that assumes the least.
by deciqai5 installs2 stars
Identify catastrophic failure paths before you commit — and design your plan around eliminating them.
by deciqai4 installs2 stars
Trace decisions past the obvious effect to catch the consequences that reverse it.
by deciqai4 installs2 stars
A structured interview and analysis process that uncovers the actual job customers hire your product to do — and who they're really competing against.
by deciqai3 installs3 stars
Diagnose why learners are struggling and redesign instruction to stay within working memory limits.
by deciqai2 installs3 stars