deal-evolution

Deal Evolution — V1 → V2 → V3 (automatic, one prompt)

The skill is the evolution. When someone asks for an analysis, you do NOT hand back a first draft and wait. You run the whole arc yourself — draft it, attack it, finish it — and deliver the V3. The user prompts once.

The discipline (this is the part that matters)

• Finish each version before you plan the next. Do not pre-plan all three. Produce V1 completely → THEN look at what you actually made → THEN decide how to harden it → produce V2 → THEN critique again → produce V3. Plan the next phase only from the finished prior one. (Don't over-plan up front — build, then critique, then build.)
• Each version must already carry full rigor (see bristol-os/reference/rigor-standard.md). V1 is not "sloppy" — it's the honest first pass with best-available data. V2 and V3 raise verification and depth, not basic competence.
• Keep going until V3 meets the bar. Don't stop at V1 or V2 and ask "want me to keep going?" — you already know they do.

V1 — DRAFT (get a real, defensible answer on the page)

• Build the full structure and a first-pass answer using the best data you can pull now (Quarry parcel, FRED/Census live, web/Tavily/Exa, Bristol portfolio calibration).
• Compute the core metrics. Label every estimate as an estimate.
• End V1 when: the deliverable is complete end-to-end and internally consistent — a real answer, not an outline.

Self-critique gate (run between every version — adversarial, in writing to yourself)

Ask, and act on the answers:

1. What's estimated that should be sourced? Replace guesses with real, named, cited comps/figures.
2. What's unverified or single-source? Confirm across 2+ primary sources; flag what can't be.
3. What local detail could be wrong? Jurisdiction, submarket, corridor, school zone, zoning, who owns what — these readers have 20 years here and will catch any off detail. Verify Franklin/Williamson specifics against primary sources.
4. What elite metric is missing? (rigor-standard.md) — untrended/trended yield-on-cost, spread over exit cap AND cost of capital, IRR, equity multiple, cash-on-cash, debt yield, replacement-cost basis, rate-environment context.
5. What would a Berkshire-level sponsor poke? Add the stress case, the rate sensitivity, the supply-pipeline check, the basis-vs-replacement check.
6. Does it reconcile? Every number agrees across model, memo, deck, one-pager; every source resolves.
7. Any error? (e.g., a wrong/mislabeled source, a transposed figure, a mis-attributed project.) Fix it.