Add 'status-quo enumeration' step to genesis prompt

council rejected PROMPT reversible: simple 3h proposed 20 Jun 2026

What is the proposed change?

Modify genesis prompt to require, before stating the proposed hypothesis, an explicit JSON sub-field status_quo with 3-5 entries naming what the buyer currently uses (named tool / manual process / in-house script) for the workflow under consideration. Reject (in-prompt) any generation where status_quo is empty or contains only generic terms ('manual', 'spreadsheets'). Emit status_quo into the proposal record so v2_a12 can score against it deterministically.

Target files

hypothesis_engine/moves/genesis.js hypothesis_engine/prompts/genesis.md

Expected effect

Genesis output will carry a structured status_quo field on ≥95% of proposals after change; v2_a12 scoring will be deterministic against this field rather than NLP-inferred. Expect fewer 'invented problem' proposals (estimated 20-30% reduction in council-stage 'no buyer would pay' kills).

Falsifier — what would prove this wrong?

Compare council-stage kill reasons for the 50 cycles pre/post change. If 'invented problem' / 'no acute pain' / 'candy not vitamin' kill counts do not drop by ≥20%, prompt change is ineffective.

Evidence that triggered the proposal

E — kill reason distribution shows concentration in pain/displacement-related rejections (a6 acute_pain_not_candy)
D — S161 LENS_SET Tier 1 — status_quo_displacement is upstream of acute_pain

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

Axis	Score
specificity	3
falsifier	3
solo feasible	3
blast radius	2
composability	3
reversibility	3

Disposition

Rejected at the council verdict. The two-judge council did not find the case strong enough to advance to Commander review.

Evaluation history

When	Move
2026-06-20 04:11	meta_council_verdict
2026-06-20 04:09	meta_argument
2026-06-20 04:05	meta_filter_score
2026-06-20 04:03	meta_genesis