G.E.N.I.E Generative Emergence and Navigation Insight Engine Prime Move Structural Diagnostic Protocol (v2.0)— FULL STRUCTURAL DIAGNOSTIC PROTOCOL

BEFORE YOU BEGIN Answer these four questions before running the protocol. The quality of your input determines the quality of the output. ∙ System: What is the system you are analyzing? Describe it specifically. ∙ Track: What is the desired outcome? Name one primary track. If multiple, list them — each will be run separately. ∙ Current state: Where are you now? Skill level, time invested, specific problem you are experiencing. ∙ Constraints: What is limiting progress? Time, resources, access, context, relationships, tools.

PRE CHECK: Instrument Readiness Check: Before diagnosing the cycle, verify: is the system capable of producing the target output under any conditions? If not, identify what must be corrected before cycle-level diagnosis is meaningful.

STAGE ONE: STRUCTURAL DIAGNOSIS Five-stage cycle analysis. No external data. Structure only. You are operating the Prime Move lens with strict discipline. The Five Stages: ∙ Split — a distinction appears ∙ Tension — an imbalance or pressure forms ∙ Failed Merge — an attempted resolution fails, leaving residue ∙ Scar — the persistent structure or memory ∙ Decay — the release that enables the next cycle Emotional Signatures: ∙ Split: excitement, possibility, overwhelm ∙ Tension: frustration, focus, urgency ∙ Failed Merge: discouragement, repetition, doubt ∙ Scar: relief, stability, sometimes rigidity ∙ Decay: sadness, release, anticipation Rules: ∙ Walk through all five stages in strict order ∙ One concise answer per stage — 1 to 2 sentences maximum ∙ Base answers only on what the user has described ∙ Do not infer beyond what is provided ∙ Do not search for or reference any external data in this stage Stage One Output: ∙ Five stage walkthrough ∙ Dominant stage with sub-stage: Early / Mid / Late ∙ Emotional signature of dominant stage ∙ Single most effective action to move to the next healthy stage ∙ Alternative action with explicit trade-off: speed vs. stability vs. learning ∙ Hidden constraint check: what assumptions are being made? What has not been said that might matter?

STAGE ONE-B: TIER AND PATHWAY IDENTIFICATION Run immediately after Stage One. Still no external data. Using the Stage One diagnosis, identify where the system sits on the complexity ladder and which generative pathway it is following. The Six Tiers:

Tier Identification Questions — ask in order: ∙ Is the system producing simple sequences or nested structures? → Tier 1 vs 2 ∙ Does the problem repeat at multiple scales simultaneously? → Tier 3 signal ∙ Does the system respond to its own outputs — feedback present? → Tier 4 signal ∙ Are multiple pathways available or just one route? → Tier 5 signal ∙ Does the system sustain itself using its own accumulated history? → Tier 6 signal The Three Pathways (active at Tier 3 and above):

Pathway Identification Questions: ∙ Is the system developing in a remembered direction — each cycle building on the orientation of the last? → Spiral ∙ Is the system optimizing toward efficiency under symmetric constraints? → Optimization ∙ Is the system growing through accumulated local decisions with no central direction? → Aggregation ∙ Are multiple mechanisms clearly active simultaneously? → Mixed Stage One-B Output: ∙ Current tier with evidence from the system description ∙ Confidence in tier assessment: High / Medium / Low ∙ Pathway if at Tier 3 or above — with evidence ∙ Next tier the system is moving toward ∙ What the system needs to build at this tier before it can progress to the next ∙ Pathway alignment check: is the current intervention aligned with the system’s natural pathway or working against it? ∙ Tier-specific intervention: what does this stage at this tier specifically require — not a generic prescription but one calibrated to both the stage and the tier

STAGE TWO: EMPIRICAL CALIBRATION Now bring in real world data. Use the Stage One and Stage One-B diagnoses as your search target. The structural diagnosis is now a prediction. Stage Two tests that prediction against empirical evidence. Search for and apply real world data, research, and domain benchmarks that speak directly to the tier, stage, and pathway combination identified. Do not search generally — search specifically for what the structural diagnosis predicted. Five Calibration Points:

1. Stage Confirmation Does empirical research confirm the dominant stage identified in Stage One? Cite the most relevant finding. If research suggests a different stage, note the discrepancy explicitly.
2. Tier Confirmation Does domain-specific evidence confirm the tier identified in Stage One-B? What does research say about systems at this tier in this domain? Does the complexity level match what the tier description predicts?
3. Timeframe Calibration What does domain-specific research say about realistic timeframes for the transition the lens predicted? Replace any generic estimates with empirically grounded ones. Distinguish between ideal conditions and typical conditions — they are usually significantly different.
4. Intervention Refinement Does research support, refine, or contradict the tier-specific intervention identified in Stage One-B? If research contradicts it, note the discrepancy explicitly and explain which to trust and why.
5. Hidden Constraint Surfacing Does the data reveal any domain-specific constraints that the structural analysis could not see from the description alone? Constraints that only appear in the empirical literature — not inferable from the system description. Discrepancy Log List every point where the empirical data contradicts the structural diagnosis. Do not suppress contradictions. A contradiction is the most valuable output the protocol produces — it reveals either a framework limit or a domain-specific exception worth understanding. Format each discrepancy as: ∙ What the lens predicted ∙ What the data shows ∙ Which is more likely correct and why Stage Two Verdict: Confirmed / Refined / Contradicted — one sentence explaining which and why.

INTEGRATED FINAL OUTPUT Single consolidated output. One answer per field. No alternatives. No menus. Structural Position: ∙ Stage: [dominant stage and sub-stage] ∙ Tier: [current tier] ∙ Pathway: [if at Tier 3 or above] ∙ Emotional signature: [of dominant stage] Trajectory: ∙ Where this system is going: [next stage and next tier] ∙ What it is building toward: [what the accumulated scar is becoming] ∙ Natural development direction: [what the pathway predicts about the system’s long-term form] Prescription: ∙ Single action: [one specific intervention calibrated to this stage at this tier on this pathway] ∙ Timeframe: [empirically calibrated — distinguish ideal from typical conditions] ∙ What to preserve: [which current scars are useful substrate for the next tier] ∙ What to release: [which current scars are blocking the transition] Forecast: ∙ Next stage: [what comes after the prescribed action takes effect] ∙ Next tier: [what the system is becoming at a complexity level] ∙ Steering instruction: [one specific thing to do to move toward the desired track] ∙ Warning: [one specific thing that would derail the transition] Confidence Assessment: ∙ Overall confidence: High / Medium / Low ∙ Strongest evidence: [what the diagnosis rests on most firmly] ∙ Weakest point: [where the diagnosis is most uncertain] ∙ Recommended cross-analysis: [which domains or research areas would most usefully challenge this diagnosis] Discrepancy Summary: [List any contradictions between structural diagnosis and empirical data — or state “No contradictions found” if none emerged]

CROSS-ANALYSIS RECOMMENDATION After receiving the integrated output, run the system description through at least three additional AI systems or domain experts using the same five input fields. Compare: ∙ Does the stage diagnosis converge or diverge? ∙ Does the tier assessment converge or diverge? ∙ Does the prescribed intervention converge or diverge? Convergence across independent systems strengthens confidence. Divergence flags uncertainty and identifies where the diagnosis needs more information or where the framework may be reaching its application limits. Note: Cross-analysis catches AI variance. It does not catch framework error. If all systems converge on the same wrong answer because the framework itself is mapping the system incorrectly, cross-analysis will not reveal this. The best protection against framework error is domain expertise — someone who knows the system well enough to evaluate whether the structural diagnosis matches what they actually observe.

PROTOCOL LIMITS — READ BEFORE USING This protocol produces structural illumination not certainty. It is most accurate when: ∙ The system has enough history to have completed at least one cycle ∙ The user can provide specific concrete description rather than vague general description ∙ Empirical research exists in the domain for Stage Two calibration ∙ The user has enough domain knowledge to evaluate whether the output matches reality It is less accurate when: ∙ The system is very new and has not completed a cycle ∙ The description is vague or the constraints are unstated ∙ The domain has weak empirical research base ∙ The user has no independent way to evaluate the output The confidence level field exists for a reason. Low confidence output should be treated as hypothesis not diagnosis. High confidence output should still be treated as one input among several — not as definitive prescription.

Version 2.0 | March 2026 | Prime Move Theory | github.com/chrissabo1975 prompt design by Cm Sabo share copy use extended. Detroit Michigan