The offer

The Baseline Assurance Sprint

Four weeks. Your agent’s real SQL, tested against invariants compiled from your own dbt manifest and schema, inside your perimeter. You end with a pre-frozen coverage denominator, a calibrated severity model, a first dual-signed audit bundle and a number — Incremental Consequential Finding Yield — that tells you whether we found anything your native evaluation did not.

Last updated 13 September 2026 · Protocol v9.3

4
weeks from kickoff to signed bundle
75–100
invariants and adversarial challenge queries
0
raw rows leaving your perimeter (Mode 1)

What you get

During the sprint

  • Consequence tier and threat model for the agent, agreed in week one
  • The pre-frozen assurance coverage denominator, signed by your owner and our lead methodologist before anything runs
  • Invariant suite: automated synthesis for the standard relational families plus authored fixtures for your proprietary logic
  • Challenge-suite hash committed and nonce issued before execution
  • A shared channel and a 30-minute call each week

At the end

  • A dual-signed audit bundle in your S3 bucket or Snowflake stage, with a notary record you can check publicly
  • The three-tier readout: board scorecard, engineering triage, scientific appendix
  • Every finding in one of four states, with reproducible trace and counterfactual proof for each DEFECT_CONFIRMED
  • ICFY against your native evaluation, with a 95% Wilson interval
  • The invariant suite itself, versioned, in your repo — it is yours whether or not you continue

How it runs

WeekWhat happensWhat we need from you
030-minute readiness review. Which agent, which schema surface, which consequence tier. We say whether a sprint is worth your money.30 minutes, and someone who knows the agent
1Kickoff. Metadata extraction (dbt manifest.json, INFORMATION_SCHEMA). Threat model. Denominator frozen and signed. Automated invariant generation runs; we report how many rules it produced and how long it took.Read-only catalog access or one run of the local extractor; the exec sponsor, a technical lead and the Business Definition Owner in one room
2Targeted human authoring of Type B/C fixtures for your proprietary logic. Challenge suite committed by hash. First in-perimeter execution via CLI or stored procedure.A staging branch or sandbox the suite can run against
3Sequential trials complete. Adjudication: Tier-3 review on exceptions, Tier-4 blinded pair on any Sev-1. INDETERMINATE items go to your Business Definition Owner (48-hour SLA), then re-run.Definitions, within 48 hours
4Bundle signed. CDAO readout. ICFY reported. A binary conversation about the platform, on the date we fixed in week one.A decision

What it costs, and why

One fixed fee. Billed by corporate card or Stripe so procurement is not on the critical path. Kickoff is gated on 100% upfront receipt. Fixed fees, agreed before we start. No hourly billing, no success fee, no scope surprises.

The fee is anchored to the work, and the work is mostly authoring. A 100-case suite is about 50 hours of senior assurance engineering in Sprint 1 — adapting archetypes, verifying custom cases against your dbt models, and writing the bespoke fixtures for your proprietary logic — plus intake validation, execution, adjudication and the readout. The number that has to fall for this to be a software business rather than a consultancy is that authoring figure: targeted at under 5 hours by Sprint 10 as manifest-driven synthesis takes over. We report the actual hours in every readout, whether or not they flatter us.

Authoring typeWhat it coversMinutes per caseShare of a suite
Type A — adapted archetypeStandard failure patterns from the reusable catalogue (join fan-out, basic SCD-2 logic)15–2050%
Type B — validated custom caseTest queries verified against your dbt models and schema relationships30–4530%
Type C — net-new bespoke fixtureEdge fixtures for proprietary stored procedures, multi-table rollups, custom UDFs60–9020%

Success criteria, agreed before we start

Numeric, written into the agreement, reported whether or not we hit them:

A sprint that ends “the native evaluation already catches this” is a real outcome. We would rather write that than pad a number; our own kill rule depends on it being true.

What this is not

Where we are, honestly

We are running the first sprints under a 90-day falsification programme with a cohort of 3 design partners. If you engage at this stage you get founder-led delivery, the design-partner terms, and direct influence on the invariant catalogue. What you do not get is a list of logos to check. There is none, and we will not borrow one.

Book a readiness review → Read a sample report first