deciqAI Lateral Thinking
Overview
Lateral thinking is the discipline of solving problems by approaching them from unexpected angles — not by going deeper along an existing logical path but by moving sideways to a new starting point. Coined by Edward de Bono, it converts creative leaps into learnable, repeatable techniques: assumption challenge, random entry, concept extraction, and PO (Provocative Operation). The brain is a pattern-forming system — lateral thinking deliberately disrupts those patterns to make invisible solutions visible.
Compose with neighbors: Use first-principles before lateral thinking to clear inherited assumptions. Use six-thinking-hats after to evaluate ideas generated (Green Hat = lateral thinking space). Use inversion as a lightweight lateral move when time is short.
When to Use
Use when: team cycles through the same 2–3 options; an industry assumption has gone years untested; someone says "think outside the box / we need a breakthrough / how might we / we've tried everything"; solution space feels exhausted despite good problem definition.
When NOT: problem has a mathematical optimum; decision needed in under 5 min; team lacks domain knowledge (use first-principles first); task requires rigorous proof.
Coaching Novices (Adaptive Front Door)
- Engine mode: user brings a specific stuck problem → run The Process directly.
- Coach mode: user signals unfamiliarity or asks "what is this / how does it work?" → 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 what-it-is: lateral thinking is about starting from a different place, not going deeper on the same path — four specific techniques, not hoping inspiration strikes.
- Check fit against When to Use / When NOT to use — if the problem has a clear optimal answer, redirect; if time is very short, offer inversion instead.
- Elicit their real stuck problem. "We need to be more innovative" is not workable; "our checkout conversion hasn't improved in 18 months despite A/B testing" is.
[WAIT — do not advance until user responds]
- Walk through assumption challenge → random entry → concept extraction → PO one at a time. Pose each technique as a question and wait before advancing.
[WAIT — do not advance until user responds]
- Close by naming the specific assumption or pattern they broke. The cognitive move is more valuable than any single idea it produced.
[WAIT — do not advance until user responds]
The Process
Six steps producing a Lateral Thinking Report — a structured map of new directions generated by deliberately disrupting existing patterns.
Stop rule: At Step 6, if no direction passes the feasibility screen, return to Step 2 with different assumption targets or a different random entry word. Stop signal: all directions after screening are indistinguishable from the original frame.
- Reframe as a How-Might-We question. Strip hidden assumptions. Wrong: "How do we build a better airport check-in?" Right: "How might we help travelers move from curb to gate with minimal friction?"
- Extract the assumption inventory. List every "obvious," "given," "necessary" constraint — 15–20 minimum. Rank by importance × never-challenged; top 5 are challenge targets.
- Challenge each top assumption. For each: "Why must this be true?" and "What becomes possible if it is false?" Capture each answer as a direction candidate, not a solution.
- Inject random stimulation. Select 3–5 random words (dictionary, random generator, date-indexed). Force a connection to the problem for each. Do not evaluate — capture every association.
- Extract the concept layer. For 2–3 most promising candidates: abstract the underlying functional concept. Then generate 3+ alternative implementations of that concept.
- Apply PO as a final pattern-disruptor. Formulate 2–3 deliberately absurd statements (prefix "PO:"). Use each as a springboard. Filter outputs with feasibility: technical viability, commercial viability, time-to-validation. Select 2–3 directions for deep investigation.
Output: Lateral Thinking Report
# Lateral Thinking Report: <problem>
## Reframed Problem: How might we <...>?
## Assumption Inventory (top 5): | Assumption | Why false? | What becomes possible? |
## Random Stimulation: word → forced connection → direction candidate
## Concept Extraction: | Source direction | Functional concept | 3 alternative implementations |
## PO Springboards: PO: <absurd premise> → Executable direction: <...>
## Top Directions (post-feasibility): <direction> — tests: <assumption> — validation: <path>
## What pattern was broken: <one sentence>
→ Method in Action: IDEO Shopping Cart Redesign (1999)
Lateral Packs
| Domain | Top assumption targets | Cross-domain stimulation |
|---|---|---|
| Product strategy | pricing model, user identity, distribution | utilities, insurance, hospitality |
| Org design | managers manage individuals, vertical hierarchy, fixed comp | military units, ant colonies, jazz |
| Business model | revenue follows delivery, pay-per-unit, company owns assets | membership clubs, subscription media, platforms |
Contribute a pack: top 5 assumption targets + richest stimulation sources + 2–3 worked PO examples.
Applying It Well
- Reframe before you challenge. If the problem contains "better," you are inside the vertical frame — reframe to How-Might-We first.
- Volume before quality in Steps 3–5. Evaluation kills lateral movement; no feasibility assessment until Step 6.
- The forced connection is the technique. Any random word works; cognitive value comes from the act of forcing a connection, not the word.
- PO is a springboard, not a proposal. The absurd statement is never executed — it forces the mind into positions it otherwise refuses.
- End with vertical thinking, then name the broken pattern. The output is a newly visible assumption, not just a list of ideas.
→ Primary sources: references/sources.md
Common Rationalizations
[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.
| Fake move | Reality |
|---|---|
| [D] "We already brainstormed this." | Brainstorming is undirected divergence; lateral thinking uses specific techniques that target the pattern formation mechanism, not just idea volume. |
| [D] "The random word isn't relevant enough." | Relevance is the enemy. The value comes precisely from its non-relevance forcing a new connection route. |
| [D] "We can't challenge that — it's regulated / industry standard." | Most such constraints are conventions. Challenge first; legal/regulatory validation comes at Step 6. |
| [D] Generating variations on the existing solution and calling them "lateral." | If all candidates differ only in scale, speed, or cost, the pattern was not disrupted. True lateral output changes what is done, not only how. |
| [D] Skipping concept extraction and jumping straight to new solutions. | Without abstracting to the functional concept layer, new solutions remain tethered to the original implementation frame. |
| [D] Evaluating PO statements as proposals. | "PO: the hospital should not have beds" is a provocation. Evaluating it as a proposal wastes the technique. |
| [D] "How might we build a better X" as a reframe. | That is the original problem restated. A successful reframe removes X from the question entirely. |
| [D] Selecting random words from the problem domain. | "Efficiency" for an operations problem is not random stimulation. Use a dictionary or date-indexed method. |
| [D] Running lateral thinking once and concluding "it didn't work." | Iterative: if the first challenge set yielded only incremental candidates, target a different assumption tier. |
| → Add [O] entries here after each real use — paste the actual failure pattern | What went wrong and why |
Red Flags
- All directions improve the existing solution — no frame change occurred
- Team evaluated ideas during divergence; random words chosen from problem domain
- How-Might-We reframe still contains the original solution type
- PO statements rejected as absurd rather than used as springboards
- Session ended without naming what pattern was broken
Verification
- Reframed as How-Might-We removing the original solution type
- 15+ assumptions listed; top 5 explicitly challenged with "what becomes possible if false?"
- 3+ genuinely unrelated random words used; forced connections recorded without evaluation
- Concept extraction: at least one direction abstracted and re-instantiated 3+ ways
- 2+ PO springboards used (not evaluated as proposals); broken pattern named at close
Part of deciqAI Knowledge Skills — 237 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/s/lateral-thinking · Built by deciqAI · github.com/deciqAI · Contributions welcome.
Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/lateral-thinking.json