Audit decision execution fidelity
Audit whether approved decisions actually became verified implementation at the promised aggregate-unit and component grain, with whole-unit bootstrap uncertainty and simultaneous gates for fidelity, overdue scope, unverifiable evidence, exceptions and critical gaps.
What it's for
Closes the gap between executive approval and operational reality: Gitrevio can show which decisions were actually implemented, what remains overdue, and whether apparent completion rests on unverifiable evidence or expanding exceptions.
What you give it
Inputs split into evidence read from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.
| Field | Type | Role | Required |
|---|---|---|---|
| bootstrap_draws | integer ≥ 200, ≤ 20000 | Numerical control | Optional |
| confidence_level | number ≥ 0.5, < 1 | Your calibration | Optional |
| max_detail_rows | integer ≥ 1, ≤ 500 | Numerical control | Optional |
| maximum_approved_exception_weight_fraction | number ≥ 0, ≤ 1 | Your calibration | Optional |
| maximum_critical_gap_fraction | number ≥ 0, ≤ 1 | Your calibration | Optional |
| maximum_overdue_gap_fraction | number ≥ 0, ≤ 1 | Your calibration | Optional |
| maximum_unverified_weight_fraction | number ≥ 0, ≤ 1 | Your calibration | Optional |
| minimum_fidelity_fraction | number ≥ 0, ≤ 1 | Your calibration | Optional |
| minimum_implementation_unit_count | integer ≥ 5, ≤ 100000 | Your calibration | Optional |
| observations | array of objects (12 fields) ≥ 20 items | Evidence | Yes |
| seed | integer ≥ 0, ≤ 2147483647 | Numerical control | Optional |
Each observations
record
| Field | Type | Required |
|---|---|---|
| approved_exception | boolean | Yes |
| as_of_period | integer (≥ 0, ≤ 1000000000) | Yes |
| component_id | string (non-empty) | Yes |
| critical | boolean | Yes |
| decision_id | string (non-empty) | Yes |
| due_period | integer (≥ 0, ≤ 1000000000) | Yes |
| evidence_verified | boolean | Yes |
| id | string (non-empty) | Yes |
| implementation_unit_id | string (non-empty) | Yes |
| observed_fraction | number (≥ 0, ≤ 1) | Yes |
| required_fraction | number (> 0, ≤ 1) | Yes |
| weight | number (> 0) | Yes |
{
"bootstrap_draws": 200,
"confidence_level": 0.8,
"observations": [
{
"approved_exception": false,
"as_of_period": 10,
"component_id": "production-rollout",
"critical": true,
"decision_id": "roadmap-funding",
"due_period": 8,
"evidence_verified": true,
"id": "roadmap-rollout-0",
"implementation_unit_id": "team-00",
"observed_fraction": 1,
"required_fraction": 1,
"weight": 1
},
{
"approved_exception": false,
"as_of_period": 10,
"component_id": "production-rollout",
"critical": true,
"decision_id": "roadmap-funding",
"due_period": 8,
"evidence_verified": true,
"id": "roadmap-rollout-1",
"implementation_unit_id": "team-01",
"observed_fraction": 1,
"required_fraction": 1,
"weight": 1
},
{
"approved_exception": false,
"as_of_period": 10,
"component_id": "production-rollout",
"critical": true,
"decision_id": "roadmap-funding",
"due_period": 8,
"evidence_verified": true,
"id": "roadmap-rollout-2",
"implementation_unit_id": "team-02",
"observed_fraction": 1,
"required_fraction": 1,Truncated for display — the full payload is 286 lines.
What you get back
This is the actual output of running the example above — computed by the same function the platform calls, not an illustration.
{
"configuration": {
"bonferroni_one_sided_tail_probability": 0.04,
"bootstrap_draws": 200,
"confidence_level": 0.8,
"maximum_approved_exception_weight_fraction": 0.1,
"maximum_critical_gap_fraction": 0,
"maximum_overdue_gap_fraction": 0.1,
"maximum_unverified_weight_fraction": 0.05,
"minimum_fidelity_fraction": 0.9,
"minimum_implementation_unit_count": 10,
"seed": 0,
"simultaneous_gate_count": 5
},
"decision": "represented_decisions_clear_execution_fidelity_gates",
"decision_diagnostics": [
{
"approved_exception_weight_fraction": 0,
"approved_exception_weight_fraction_simultaneous_upper_bound": 0,
"as_of_period": 10,
"commitment_count": 20,
"critical_gap_fraction": 0,
"critical_gap_fraction_simultaneous_upper_bound": 0,
"decision": "decision_execution_fidelity_supported",
"decision_id": "roadmap-funding",
"due_commitment_count": 20,
"failed_gates": [],
"fidelity_fraction": 1,
"fidelity_fraction_simultaneous_lower_bound": 1,
"implementation_unit_count": 20,
"overdue_gap_fraction": 0,
"overdue_gap_fraction_simultaneous_upper_bound": 0,
"unverified_weight_fraction": 0,
"unverified_weight_fraction_simultaneous_upper_bound": 0
}
],
"guardrails": [
"The audit evaluates due aggregate implementation commitments against a frozen decision contract. Future commitments are not treated as failures, and approved exceptions remain visible rather than silently rewritten as completion.",
"Whole-unit bootstrap preserves dependence among components implemented by the same aggregate unit but cannot repair missing offline work, unverifiable evidence, changed component definitions or selective exception logging.",
"Execution fidelity is neither proof that the underlying decision was good nor a person-performance score. Diagnostics support process remediation and accountable review, never automated employment action."
],
"method": "whole_implementation_unit_bootstrap_execution_fidelity_audit_v1",
"summary": {
"action_required_decision_count": 0,Truncated for display — the full payload is 52 lines.
How it works
Statistical audit & measurement — Check whether a number is fit to decide on: coverage, timing, reconciliation, and the gaps a dashboard hides.
- 1 Freeze each decision's implementation contract, due period, required fraction, evidence standard, approved exceptions, critical components and aggregate implementation-unit boundary before inspecting outcomes.
- 2 For due commitments, reconcile observed-to-required completion without over-crediting, preserve exceptions as visible scope, and calculate weighted fidelity, overdue, unverified, exception and critical-gap metrics.
- 3 Resample whole implementation units and apply family-wide one-sided Bonferroni bounds so correlated component rows and multiple represented decisions cannot manufacture gate clearance.
Before you trust it
Every tool in the catalog ships with the conditions under which its answer is meaningful — and the conditions under which it should abstain instead of guessing.
Assumptions & guardrails
- Metric definitions, weights, aggregate grain, sampling, missingness, dependence, and comparison windows correspond to the management claim being audited.
- The frozen contract contains all consequential implementation work; due dates and required fractions were not rewritten after outcomes; aggregate units are independent enough for cluster bootstrap; evidence verification and exception approval are governed; offline work and failed attempts are retained.
- Association, instability, or measurement quality is not a causal effect and must not be converted directly into an individual employment decision.
- Execution fidelity evaluates a governed decision-to-implementation process, not whether the original strategy was correct and never an individual's effort, trustworthiness or employment suitability.
Minimum evidence
- observations: at least 20 rows/items
How to validate it
Backtest the chosen action against simple feasible baselines on held-out scenarios, sweep costs/constraints/risk tolerance, and require constraint feasibility under adverse inputs.
Calibrating it to your org
Same for everyone
The mathematical kernel, validation rules, method version, and JSON output semantics are organization-independent; no tenant-trained coefficients or company benchmark is embedded in the function.
Specific to you
- point-in-time decision implementation ledger joining the frozen approval contract to aggregate delivery evidence without dropping zero-completion components, offline work, failed attempts, future commitments or approved exceptions
- decision/component perimeter, aggregate implementation-unit boundary, cadence, due and required semantics, evidence verification, exception approval, criticality, weights, minimum support, simultaneous confidence and practical fidelity/gap gates
Calibration workflow
- 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
- 2 Build a tenant-scoped historical cohort using only information available before each prediction or decision; preserve zero periods, censoring, assignment probabilities, and unresolved outcomes when the method requires them.
- 3 Estimate statistical parameters on training history, but obtain costs, utilities, risk tolerance, practical-effect thresholds, capacity, and policy constraints from accountable decision owners.
- 4 Validate on later time windows or held-out aggregate units at the deployment grain, against a simple baseline and the function-specific validation strategy.
- 5 Deploy only if the returned decision clears evidence, overlap, calibration, robustness, and guardrail checks; warning, unsupported, schema-gap, and fallback decisions are abstentions.
- 6 Monitor realized outcomes, data drift, coverage, and decision regret; recalibrate at a governed cadence or after a detected regime/definition change, never merely because a stakeholder dislikes the result.
Call it from your AI
You don't wire up 388 tools in your MCP client. The GitRevio MCP server exposes 18 tools, three of which let an agent search the catalog, read a tool's schema, and run it — so the assistant finds this one on its own.
gitrevio_capabilities_search
{ "q": "audit whether approved decisions actually became" }
→ finds "audit_decision_execution_fidelity"
gitrevio_capability_describe
{ "capability_id": "audit_decision_execution_fidelity" }
→ returns the input schema and agent guidance shown on this page
gitrevio_capability_run
{ "capability_id": "audit_decision_execution_fidelity", "arguments": { ... } }
→ returns the result shown aboveWorks in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.
Related tools
Calculate execution value leakage
Translate incomplete scope, delay-driven value decay, rework and approved-exception costs into coherent expected, reserve-quantile and tail-CVaR execution leakage, with exact decision-level reconciliation to net realized value.
Estimate causal value of execution fidelity
Estimate how much outcome value an additional unit of implementation fidelity causes by using randomized enablement as an encouragement instrument, with whole-cluster arm bootstrap, first-stage, balance, negative-control and ratio-stability gates.
Audit commercial technical commitment integrity
Audit signed commercial promises against explicitly allocated technical scope, dependency order, funded capacity, acceptance criteria and evidence; expose orphan scope, double allocation, cycles, late plans and maximum contractual penalty without interpreting legal rights from engineering activity.
Audit KPI threshold bunching
Detect a post-target excess concentration immediately above a governed KPI threshold: compare within-unit pre/post local mass and above-versus-below mirror asymmetry, bootstrap whole units, report density bins and a smoothed log-density jump, and explicitly refuse to equate bunching with individual gaming or intent.
Audit release risk prediction integrity
Audit a complete eligible-change release-risk cohort for point-in-time prediction lineage, exact change-to-deployment linkage, mature mutually exclusive outcomes, selective labels, score-triggered intervention contamination, calibration and false alarms before the score influences a release decision.
Audit sunk cost escalation
Audit whether cumulative sunk cost predicts aggregate project continuation after project fixed effects, checkpoint time, forward value, success probability, remaining cost, and future irreversibility, with project-cluster bootstrap uncertainty.