Preserve first
Long critiques, investor notes, advisor comments, and user dictation land in data/inbox/ before atomization. Then they become feedback, claims, decisions, research goals, and version trace.
internal diligence ledger / compiled from data/*.json
This is the private control surface for the project. It is not public collateral. New critiques and information become atomic feedback, decisions, research goals, evidence receipts, or version changes before they become prose in any external artifact.
| ID | Source | Source status | Confidence | Severity | Type | Summary | Implication | Status | Targets | Claims | Disposition |
|---|
| ID | Claim | Category | Source status | Confidence | Status | Sources | Verification needed | Risk if wrong |
|---|
| ID | Case | Posture | Status | Cash to control / close | Annual no-revenue burden | 12-mo survival capital | Evidence | Inputs | Actions | Kill conditions | Investable if |
|---|
| ID | Scenario | Posture | Price / option | Loan | Equity + closing | Debt service | Tax sensitivity | Other carry | Annual burden before revenue | Monthly break-even | Status |
|---|
No line item becomes underwriting until the required evidence is received. These are the missing variables that decide whether the idea is investable, merely poetic, or dead.
| ID | Input | Category | Current assumption | Evidence required | Owner | Status | Blocking actions | Blocks | Decision use | Next action |
|---|
| ID | Name | Variable | Current model position | Test range | Why it matters | Method | Source checks | Status |
|---|
| ID | Bucket | Purpose | Acceptable sources | Exclusions | Adjustment questions | Source checks | Status | Next action |
|---|
These gates are not approvals. They are current decision posture: red means do not underwrite or buy; yellow means possible diligence/control only; green requires received evidence.
| ID | Gate | Status | Scenario | Required inputs | Blocking actions | Why | What would flip it | Public posture |
|---|
| ID | Received | Title | From | Authority | Action | Input | Summary | Replaces | Outcome | Status |
|---|
| ID | Seat | Wave | Status | Owner | Why it matters | First questions | Proof | Clears / kills | Checks | Actions | Next action |
|---|
| ID | Gate | Status | Owner | Proof required | Kill condition | Source checks |
|---|
| ID | Category | Question | Authority | Status | Needed evidence | Decision effect | Blocks | Target claims | Next action |
|---|
| ID | Check | Priority | Type | Owner | Ask | Status | Can do now | Blocked by | Kill / clear effect | Output |
|---|
| ID | Date | Claim | Category | Authority | Status | Confidence | Sources | Implication | Next verification |
|---|
| ID | Date | Decision | Rationale | Status | Affects |
|---|
| ID | Date | Agent | Task | Status | Summary | Mapped to |
|---|
Long critiques, investor notes, advisor comments, and user dictation land in data/inbox/ before atomization. Then they become feedback, claims, decisions, research goals, and version trace.
| ID | Date | Title | Source | Status | Path | Next action |
|---|
Owns repo truth, compiles ledgers into HTML, updates version trace, runs verification, rejects incoherent agent output.
Maintains task state under docs/goals/field-house-project-mind. Scout/Judge/Worker receipts must land back in the data model.
Useful for slop-judge, investor red-team, language surgery, and alternate framing. Outputs receipts, not canonical prose.
Useful for web, exa, firecrawl, commercial-real-estate skepticism, and council passes. Outputs claims and gaps for Codex to vet.