Audit technology diligence evidence integrity

Audit a frozen technology diligence case against buyer-declared system/domain/claim scope, management assertions and fresh, rights-cleared, independently reviewed point-in-time evidence.

What it's for

Creates an evidence-grade technology diligence room: buyers and investors see exactly which target claims are independently supported, qualified, missing, stale or outside the frozen scope.

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
as_of_ms number ≥ 0 Your calibration Yes
diligence_cases array of objects (10 fields) Evidence Yes
diligence_claims array of objects (10 fields) Evidence Yes
domain_requirements array of objects (9 fields) Evidence Yes
evidence_artifacts array of objects (12 fields) Evidence Yes
max_detail_rows integer ≥ 1, ≤ 500 Numerical control Optional
minimum_verified_evidence_fraction number ≥ 0, ≤ 1 Your calibration Optional

Each evidence_artifacts record

Field Type Required
artifact_hash string (non-empty) Yes
case_id string (non-empty) Yes
claim_id string (non-empty) Yes
evidence_verified boolean Yes
id string (non-empty) Yes
independent_of_target boolean Yes
observed_at_ms number (≥ 0) Yes
source_rights_verified boolean Yes
source_system_id string (non-empty) Yes
valid_from_ms number (≥ 0) Yes
valid_until_ms number,null (≥ 0) Yes
verified_by_reviewer_id string (non-empty) Yes
Example input
{
  "as_of_ms": 12000,
  "diligence_cases": [
    {
      "conflict_review_complete": true,
      "cutoff_at_ms": 10000,
      "data_room_snapshot_hash": "sha256:data-room-v7",
      "evidence_verified": true,
      "id": "acquisition-alpha",
      "independent_reviewer_id": "review-firm-a",
      "management_assertion_ledger_complete": true,
      "required_domain_ids": [
        "architecture"
      ],
      "scope_system_ids": [
        "billing"
      ],
      "target_id": "target-alpha"
    }
  ],
  "diligence_claims": [
    {
      "asserted_at_ms": 8000,
      "assertion_value_hash": "sha256:inventory-v2",
      "case_id": "acquisition-alpha",
      "claim_status": "supported",
      "claim_type": "inventory",
      "domain_id": "architecture",
      "evidence_verified": true,
      "id": "claim-inventory",
      "management_asserted": true,
      "subject_system_id": "billing"
    },
    {
      "asserted_at_ms": 8000,
      "assertion_value_hash": "sha256:scalability-v2",
      "case_id": "acquisition-alpha",
      "claim_status": "supported",
      "claim_type": "scalability",
      "domain_id": "architecture",
      "evidence_verified": true,
      "id": "claim-scalability",
      "management_asserted": true,
      "subject_system_id": "billing"

Truncated for display — the full payload is 93 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.

Example output
{
  "assumptions": [
    "The buyer defines the complete system/domain/claim perimeter before review; the frozen data-room snapshot, management assertion ledger, reviewer conflicts and artifact provenance are immutable and tenant-scoped.",
    "Independent evidence means distinct source systems and artifact hashes, observed by the cutoff, effective and fresh at that cutoff, reviewed by the declared independent reviewer and rights-cleared where required."
  ],
  "claim_diagnostics": [
    {
      "case_id": "acquisition-alpha",
      "claim_id": "claim-inventory",
      "claim_type": "inventory",
      "domain_id": "architecture",
      "failed_gates": [],
      "qualifying_independent_evidence_count": 1,
      "subject_system_id": "billing",
      "target_id": "target-alpha"
    },
    {
      "case_id": "acquisition-alpha",
      "claim_id": "claim-scalability",
      "claim_type": "scalability",
      "domain_id": "architecture",
      "failed_gates": [],
      "qualifying_independent_evidence_count": 1,
      "subject_system_id": "billing",
      "target_id": "target-alpha"
    }
  ],
  "counts": {
    "diligence_cases": 1,
    "evidence_artifacts": 2,
    "passing_claims": 2,
    "required_claims": 2,
    "scoped_systems": 1,
    "targets": 1
  },
  "decision": "technology_diligence_evidence_ready_for_investment_committee",
  "evidence": {
    "gate_pass": true,
    "minimum_required_fraction": 0.95,
    "verified_fraction": 1
  },
  "failure_counts": {},
  "integrity_pass": true,
  "limitations": [

Truncated for display — the full payload is 50 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. 1 Freeze each target, data-room snapshot, cutoff, scoped systems, required domains, management-assertion ledger and independent reviewer before evaluating evidence.
  2. 2 Expand domain requirements into every mandatory case- or system-level claim and reject missing, duplicate, late, qualified, unsupported, unasserted or unverified claims.
  3. 3 Count only distinct source systems and artifact hashes that were known, effective, fresh, target-independent, rights-cleared where required and verified by the declared reviewer at the cutoff.

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 buyer predeclares a complete diligence perimeter and retains immutable data-room, assertion, reviewer-conflict, artifact, source-rights and cutoff provenance.
  • Association, instability, or measurement quality is not a causal effect and must not be converted directly into an individual employment decision.
  • Passing establishes evidence readiness for accountable investment review, not truth of all representations, fair value, legal/accounting/tax compliance or authority to transact.

Minimum evidence

  • diligence_cases: required and organization-defined
  • domain_requirements: required and organization-defined
  • diligence_claims: required and organization-defined
  • evidence_artifacts: required and organization-defined
  • as_of_ms: required and organization-defined

How to validate it

Validate on future periods or held-out aggregate units, compare with a simple baseline, and require stability across plausible metric definitions and decision thresholds.

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 case-domain-system-claim matrix joined to the exact data-room snapshot and independently sourced artifacts without future leakage, omitted required claims, duplicate source/hash inflation or management assertions being relabeled as independent evidence
  • buyer-approved transaction scope, diligence cutoff and snapshot, required domains and claim types, per-system applicability, independence and conflict policy, artifact freshness/effectivity, source rights, evidence threshold and remediation ownership

Calibration workflow

  1. 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
  2. 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. 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. 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. 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. 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 a frozen technology diligence case" }
  → finds "audit_technology_diligence_evidence_integrity"

gitrevio_capability_describe
  { "capability_id": "audit_technology_diligence_evidence_integrity" }
  → returns the input schema and agent guidance shown on this page

gitrevio_capability_run
  { "capability_id": "audit_technology_diligence_evidence_integrity", "arguments": { ... } }
  → returns the result shown above

Works in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.

Related tools

Forecast acquisition technology integration economics

Forecast acquisition-technology integration time, cost, stranded cost, synergy realization and economic-shortfall CVaR from pooled lognormal history, dependency paths, finite capacity and shared disruption states.

Forecasting & survival

Optimize post merger technology integration portfolio

Choose retain, bridge, migrate, integrate or retire for every target capability while pricing delayed synergy, retained standalone value, Beta-binomial failures, unique platform loss, resources, budget and CVaR.

Constrained optimization

Allocate budget with CVAR constraint

Maximize expected portfolio return while keeping probability-weighted loss CVaR below a finance-owned tail-risk ceiling across aligned joint scenarios.

Constrained optimization

Audit budget constraint binding

Audit whether a claimed budget constraint genuinely blocks value after dependency-feasible portfolio reallocation, separating current-plan inefficiency from scarcity with scenario CVaR and a discrete budget shadow price.

Constrained optimization

Audit financing term sheet integrity

Audit startup financing terms as exact share, price, proceeds and ownership identities: include pre-money option-pool increases and converting instruments in the pricing denominator, keep secondary purchases out of company cash and post-money share creation, reconcile primary issuance, post-money equity value and reported investor ownership, and retain evidence failures and impossible fees or secondary sales.

Statistical audit & measurement

Audit fundraising pipeline integrity

Audit a fundraising pipeline as point-in-time evidence rather than CRM theater: reconstruct monotone stage events, terminal status and primary proceeds, retain open opportunities as censored, reject forecasts made after resolution, detect duplicate active investor accounts, and gate the portfolio on mature-forecast support, Brier loss and calibration gap.

Forecasting & survival

See every tool in Investment & portfolio choice →

Ready to See Your Engineering work clearly?

Request a free demo