tour · 2 · Finding workOpen Inbox

Proof grading model

Intelligence Layer · judgment methodology

Work → Artifact → Outcome → Confirmation. Story & Trace Assembly drafts the 30-second read and nine-layer Trace in that grammar. Grades are derived from value-form-specific evidence thresholds, not from narrative confidence.

v2026.08.16-v16Algorithm evidence-coverage-v3LLM schema outcome-candidate-v1C3 judgment-motion-c3-v1P2 directed-discovery-p2-v2

Processing pipeline

1 · LLM extract

Proposes value form, claim, evidence flags, and alignment confidence from raw text. Conservative — flags only when text supports them.

2 · Algorithm score

Evidence coverage (0–100) measures progress toward Established threshold. Confidence blends coverage + LLM alignment.

3 · Rule authority

deriveGrade sets the legal grade. LLM never inflates above what JUDGMENT_RULES allow. Witness attestation can cap or contest.

C3 · public-surface contract

Fail closed on shared Traces

A candidate enters private review only at ≥90% confidence with exact AI and user quotes verified against captured turns. It renders on a shared Trace only after explicit user approval.

5 · Value Mining · P2

Two triggers, one discovery engine

Passive capture scans automatically. Directed mining parses the user's time window, topic, and value form. Both enter shared-discovery-v3 and produce the same pre-built draft Trace shape.

Passive trigger

Captured conversations arrive automatically.

Directed trigger

“Mine my Q1 chats for vendor negotiation.”

3 tosses suppress a cluster type · Mining share of confirmed Traces is tracked from day one · Mining dominance warns that passive discovery is underperforming.

6 · Story & Trace Assembly

30-second story + nine-layer Trace

Template-driven assembly (story-trace-assembly-v2) drafts situation → key decisions → outcome and the full Trace document. Every field is editable at confirm. Voice stays plain and specific — never AI marketing copy. Heavy edits train later drafts as style corrections.

Story

Situation · key decisions · outcome. Tools fold into the sentences.

Nine layers

Claim through contribution, including Work → Artifact → Outcome → Confirmation.

Voice + corrections

Banned hype phrases · ≥30% edits become drafting style signals.

Proof trace

Work

Judgment and decisions before the outcome moved

Artifact

The thing that shipped or changed

Outcome

Measured delta or value form claim

Confirmation

Witness, audit, or external system

Work → Artifact → Outcome → Confirmation. Story & Trace Assembly drafts the 30-second read and nine-layer Trace in that grammar. Grades are derived from value-form-specific evidence thresholds, not from narrative confidence.

C3 · Judgment-motion extraction

The evaluative layer · an anti-slop fingerprint

An LLM pass detects explicit correction, rejection, and divergence patterns in captured conversations. Candidates remain private until the user confirms the exact quoted context.

Override

Human explicitly rejects or replaces the AI recommendation.

Error caught

Human identifies a factual, logical, technical, or source error.

Divergence

Human chooses a materially different approach and explains why.

Before a judgment moment can be shared
  1. 1.90% confidence
  2. 2. Source quotes verified
  3. 3. User explicitly approves

5 · Value Mining · Directed discovery · P2

Point the same engine at what passive capture missed

Prompt in, pre-built draft Traces out — then Story & Trace Assembly fills the 30-second read and nine-layer Trace. Mining changes the filter—not the shared clustering, drafting, assembly, grading, or review pipeline.

Prompt intent

Parse time window, topic, and value form.

Shared discovery

Same filter → cluster → draft path as passive capture.

Draft Traces

Never a blank form: Work → Artifact → Outcome → Confirmation.

Learn + measure

Confirm, split, or toss; track mining share of confirmed Traces.

3 similar tosses suppress that cluster type

Health: mining-confirmed ÷ all confirmed Traces

Guardrail: mining is the power tool, never the front door

Grade ladder

Contested: a dispute overrides the positive ladder.
Qualified witness: caps an otherwise Established outcome at Supported.
ClaimedDefault

Structured assertion — limits visible, minimum evidence not met.

A structured professional assertion with its limits visible.

SupportedMinimum

Correct minimum evidence for this value form.

The correct minimum evidence for this value form is present.

EstablishedFull

Full evidence threshold for this value form.

Full evidence threshold for this value form is met.

Evidence dimensions

Temporal precedence
Artifact lineage
Counterfactual baseline
Contribution attestation
Independent corroboration
Adoption telemetry
Reinvestment documented

Thresholds by value form

Amber = Supported minimum · Green = Established full threshold

Revenue generated

Supported

Artifact lineageBaseline or corroboration (either)

Established

Artifact lineageCounterfactual baselineIndependent corroborationContribution attestation

Cost reduced or avoided

Supported

Baseline or artifact (either)Contribution attestation

Established

Artifact lineageCounterfactual baselineContribution attestation

Time saved

Supported

Artifact lineageCounterfactual baseline

Established

Artifact lineageCounterfactual baselineContribution attestationReinvestment documented

Quality improved

Supported

Counterfactual baselinePlus artifact, attestation, or corroboration (any one)

Established

Counterfactual baselineArtifact lineageContribution attestation

Risk / compliance

Supported

Artifact lineageContribution attestation

Established

Artifact lineageContribution attestationIndependent corroboration

Durable asset

Supported

Artifact lineageContribution attestation

Established

Artifact lineageContribution attestationAdoption telemetry

Matrix

S = Supported · E = Established · OR rules in cards above

FormTemporalArtifactCounterfactualContributionIndependentAdoptionReinvestment
Revenue·EEEE··
Cost avoided·EEE···
Time saved·EEE··E
Quality·EEE···
Risk·E·EE··
Durable asset·E·E·E·

Markdown reference: docs/grading-model.md · Sync rule: .cursor/rules/grading-model-sync.mdc