Change and Constants Framework

Overview

Every strategy contains elements that must change and elements that must not. The failure mode is misclassification: treating habits as principles, or principles as outdated conventions. The framework sorts on two axes: 变 (Must Change) and 不变 (Must Stay Constant) — they are complements, not opposites.

Skill composition: AFTER [first-principles] to strip convention; WITH [second-order-thinking] to check if "constants" are only temporarily stable; BEFORE [okr-goal-setting] — goals = 变; core values = 不变.

When to Use

• Major environmental shift demands strategic response and the team is paralyzed on what to adapt vs. preserve
• Organizational identity is unclear: cannot distinguish "this is who we are" from "this is what we've always done"
• Leader/board asks: "What should we never compromise on?" or "Is this signal or noise?"
• Retrospective after failure: distinguish bad implementation of a sound constant vs. faithful adherence to an outdated variable

When NOT to use: purely operational decisions (vendor, tool) without strategic identity implications; genuine emergencies (use OODA instead); using the framework to avoid deciding by treating all elements as equivalent.

Coaching Novices (Adaptive Front Door)

• Engine mode: concrete case → run The Process directly.
• Coach mode: unfamiliar user → 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.

1. What-it-is: "变/不变 sorts everything in your strategy into 'must adapt' or 'must preserve' using two explicit tests, not intuition."
2. Check fit: "Is there a situation where you're unclear whether to change something — caught between adapting and staying true to who you are?"
3. Elicit their case: "What are you navigating? Which things feel like they might need to change, and which should never change?"

[WAIT — do not advance until user responds]

4. Run The Process step by step with their input — list elements first, then Test A, then Test B.

[WAIT — do not advance until user responds]

5. Close by naming which things they had been treating as constants that are actually habits.

[WAIT — do not advance until user responds]

The Process

Output artifact: Change-Constants Map

Gate rule: Both tests required for every element. "It feels like a core value" fails the gate.

Step 1 — List all major elements (strategic choices, operations, culture, values, relationships, resource allocation). Target 10–20. No pre-sorting.

Step 2 — Apply two tests to each element.

• Test A (Irreversible damage): "Would changing this violate a bedrock value or cause irreversible damage?" YES → 不变 candidate. NO → 变 candidate.
• Test B (Blind spot): "Would keeping this unchanged leave us blind to environmental shifts?" YES → 变 candidate. NO → 不变 candidate. Both YES = genuine tension → return to first principles. Both NO = stably 不变.

Step 3 — Sort with explicit WHY. Record category, which test, and one sentence why. "Always done it this way" is not a valid why.

Step 4 — Identify dangerous misclassifications. Scan 不变 for habit-based entries. New-entrant test: would a new org call this a foundational principle or outdated convention? At least one element must move from 不变 to 变.

Step 5 — Design adaptation mechanisms. For each 变 element: specific change, timeline, decision owner, observable trigger signal.

Stop-rule: All-elements-in-one-category = framework not applied. Both lists must be populated.

Output: Change-Constants Map

## Change-Constants Map — [Entity] — [Date]
### 不变 | Element | Test | Why it is a constant
### 变    | Element | Test | Why it must change | Mechanism | Trigger | Owner
### Dangerous Misclassifications: [elements moved from 不变 to 变 + reason]
### Tension Points: [elements failing both tests + first-principles resolution]

→ Method in Action: The U.S. Constitution's Design, 1787–Present

Change-Constants Packs

Domain packs extend the framework. Contribution surface — submit via the repo.

• Tech / platform shifts: Revenue model = 变 (unit economics shift). Brand values = 不变; visual language = 变. Core architecture may be 不变 if it encodes hard-won learning.
• Personal career: Ethical principles = 不变 (Test A). Specific skills = 变 (Test B). Practice of continuous learning = 不变; what you learn = 变.
• Org culture / rapid growth: "Move fast" = startup-phase behavior = 变. Customer outcomes commitment = 不变. Specific rituals = 变; their purpose = 不变.

→ Primary sources: references/sources.md

Applying It Well

1. Decompose before classifying — "brand" splits into values (不变), expression (变), architecture (context-dependent).
2. Habit is the enemy — most dangerous misclassifications are always in 不变, for things never questioned.
3. Constants need active maintenance — values not demonstrated erode without a conscious decision.
4. Mechanism as important as classification — vague intentions to "be agile" are not mechanisms.
5. Team artifact, not solo — disagreements reveal absent shared understanding of identity.

Common Rationalizations

[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.

Red Flags

• 不变 has only stated values — no demonstrated behaviors; or every challenged element ends up in 不变
• 变 contains only peripheral items; foundational assumptions never examined
• Team cannot answer "what would we need to see to move this from 不变 to 变?"
• Map not revisited in 12+ months despite significant environmental change

Verification

• All elements listed before sorting; both Test A and Test B applied to each
• Every element has a written "why" — habit-based reasoning flagged
• At least one element moved from 不变 to 变 after misclassification check
• Every 变 element has mechanism, trigger, and owner; both lists populated
• Tension points noted; review cadence set (next inflection or 12 months)

Part of deciqAI Knowledge Skills — 253 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/change-and-constants · Built by deciqAI · github.com/deciqAI · Contributions welcome.

Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/change-and-constants.json