Hold the operating file for one body of water — the permit lodged against its authority's lead time, the logs it pulls, and a clock per guard — for a named operator to sign.
A site-level authority-register figure can read clean while one class of authority absorbs the corrections. Nestack reports the operator-correction rate by authority type, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
District-board-of-health sites
6.5%
3.6×
Review
City-health-code sites
4.7%
2.6×
Review
County-supplemented sites
3.2%
1.8×
Watch
Single-code state sites
2.0%
1.1×
Normal
Bar: operator-correction-rate lift vs. single-code-site baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
No cycle ends until the rule is retested
A cycle closes when the lapsed certification is a regression case. That suite is what the next season opened is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Operator-correction rate rises at one authority.
02Diagnose
The guard whose card said two years and whose state said one is traced back to one cause.
03Improve
The change carries a number, and the sites behind it are filed beneath it.
04Verify
Nothing files while one touched site case is still red.
05Learn
It is kept for good, and the authority rules are amended in the same commit.
Learn → DetectThe return edge. The next season opens against a suite one case longer.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, file assembly, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Permit workflow discovery and boundary definition.
02Roster and log source assessment.
03Authority-register and retention-schedule mapping.
04Log and roster ingestion and normalisation.
05Assembly logic and authority binding.
06Clock tracking and review routing.
07Operator sign-off workflow.
08Roster and log-system integration.
09Currency and lead-time cases.
10Guardrails and application controls.
11Permit-trail instrumentation.
12Deployment, documentation and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne site, one authorityProductionProduction roster and log systemsAdvancedMultiple authorities / estates
Introduced at Pilot
Assembly to your authority rules✓✓✓
Operator gating✓✓✓
Authority-register baseline✓✓✓
Introduced at Production
Reporting by site—✓✓
Review workflow in your systems—✓✓
Approved write-back—✓✓
Roster-and-log integration—✓✓
Introduced at Advanced
Complex multi-venue estates——✓
Multi-stage operator approvals——✓
High site count——✓
Multi-authority permit controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01Your sites and the authority for each→Register build and rule source mappingWeek 1
02Representative files behind past permits→Assembly baseline, rule extraction and authority bindingWeek 2
03Your safety plans, logs and certification roster→Authority register, rule and retention mapping, and the boundaryWeek 1
04Access to relevant APIs, feeds or exports→Roster, log and controller assessment, then integration setupWeek 2
05Logs you would not want inspected→Expiry cases and failure-mode testingWeek 4
06What no permit file may omit→Clock tracking, review routing, guardrails and gating controlsWeek 3
07Named operators to sign the application→Operator sign-off workflow, then pilot and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Every width comes from the weeks that phase truly needs, which is why the fifth carries a pair.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Permit discovery, authority mapping and the automation boundaryW2Source integration and the assembly baselineW3Assembly workflow, clock logic and completeness controlsW4Evaluation suite, retention cases and failure-mode testingW5Roster and log integration, pilot sites and targeted correctionsW6One pool season run under the named operator, then Agent Care handover
Reading the bandA bar sits on the weeks its work is named in and no others. The fifth week really does carry two phases.
At the end of W6Validation closes on live sites, and Agent Care picks up monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Sports & Fitness agent
Build a permit agent around the authority that administers each site.
Show us where your water is and who signs for it. The next step is a register — one row per site, the authority that administers it, the code it applies and the date we last verified it, with the clocks that fall out of it.