Proof library
The work behind the claims
The projects and results behind what is on this site, each with where its evidence comes from.
Browse all topics (10)
Flagship proof
ADHD-first design, shipped across 3 specs and a public repo
A binding, portfolio-wide UX constraint set naming ADHD and dyslexia as design disabilities, applied against three shipped design specs and carried into a public open-source memory toolkit (jitneuro).
Live productjitneuro.ai
Verified — attestedAI Field Support: voice-first, offline-first, Entra SSO, confidence-gated AI
Voice-first, offline-first, multi-tenant PWA with real Microsoft 365/Entra SSO, confidence-gated AI diagnosis, and multi-vendor AI failover — every release passes automated checks before it ships.
Live productaifieldsupport.com
Evidence pending
Shipped products
- No. 15
jITSecure: 4-sector risk scoring, 9-phase parity-before-cutover port
Multi-sector security scanning platform with industry risk multipliers, mid-migration to a cross-platform .NET binary.
delivered-artifact Verify →Details
Live product jitsecure.com
Evidence pending - No. 19
Scanner Platform: one engine, two shipped products
One scan orchestrator, live on Azure Container Apps, powering an AEO/SEO product and a security domain-scan product.
delivered-artifact Verify →Details
Powers a live product jitsecure.com
Evidence pending - No. 14
JitPlatform: one locked contract retiring duplicate code across 7 products
Shared provider-services contract — locked schema, versioned API, and a working adapter reference implementation for one real consumer.
delivered-artifact Verify →Details
Public site jitai.co
Evidence pending - No. 02
AI Boat Mechanic: a new vertical in weeks, not months
A second commercial vertical launched via a frontend branding skin, vertical-specific AI prompts, and light API additions on an unchanged engine — a ~13-week scaffold-to-live-launch span, verified from commit history.
demonstrated-capability Verify →Details
Live product aiboatmechanic.com
Evidence pending
Governance and measurement discipline
- No. 11
Discovery pipeline: 5-level architecture, 10+ documented runs
A five-level (L0-L4) governed multi-agent discovery architecture, run across 10+ documented passes against real committed source material.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 17
Precision measurement: full census of 176 candidates, 2 defects fixed
A full-census (not sampled) precision measurement by independent judges, refusing to compare a stricter new figure to a stale, easier one.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 18
Recall measurement: 9.6% headline, reported without softening
The first recall measurement for this scanner, built from an independent expert inventory read before the scan output was ever opened.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 08
Redaction gate: 4 real leak paths found, fixed, and re-verified
A real adversarial red-team of the system’s own secret-redaction mechanism, four leak paths found, fixed, and re-verified with a full regression run.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 16
Model routing: ladder-based selection, verified from raw score files
A measured, ladder-based model and effort escalation discipline, including a case where raising effort made the same model perform worse.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 09
Source isolation: git-object-only reads, byte-identical replay
A scanner that reads only pinned, committed Git objects, never a dirty working tree, with independently re-run byte-identical replay.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending
More proof records
- No. 21
Building the technology proof discovery pipeline
A queue-driven scanner that grounds every portfolio fact in an exact commit before it ever reaches public copy.
documented-statement Verify →Evidence pending - No. 04
Chunking: 20-candidate operating point, 14-of-14 validated
A previously-recommended chunking rule, validated at real scale (14 of 14 acceptable), including a self-correction to its own sizing model.
documented-statement Verify →Details
Public site jitai.co
Evidence pending - No. 05
Content factory design: 8-state lifecycle, 3-tier risk review
A designed eight-state record lifecycle and three-tier risk classification for continuous evidence publication; evidence-pending by the record’s own account.
documented-statement Verify →Details
Public site jitai.co
Evidence pending - No. 07
Content gate: 10-stage blocking contract, named judges per stage
A canonical, currently binding multi-stage editorial quality-gate contract that every content asset must pass before it ships.
documented-statement Verify →Details
Public site jitai.co
Evidence pending - No. 10
Delivery exemplar: one governed standard across real products
A deliberately restrained cross-product exemplar of governed AI-enabled delivery; evidence-pending by the record’s own account.
documented-statement Verify →Details
Public site jitai.co
Evidence pending - No. 20
Designing an externalized interrupt cadence for long-running AI work
A scheduler-owned wakeup pattern that keeps long-running automation checked-in without relying on continuous unaided attention.
owner-attested Verify →Verified — attested - No. 13
Gated backlog governance across parallel AI work streams, tooling defect caught
A multi-lane ticket roster gated by an explicit duplicate sweep, which caught a real tooling defect before it produced a false result.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 06
L3 audit readiness: 1 source shape ready, 1 blocked and named
A mechanical L3 evidence-audit readiness check that found and reported a real, reproduced blocked source shape rather than assuming coverage.
demonstrated-capability Verify →Details
Public site jitai.co
Evidence pending - No. 12
Strategy trace: every ruling SHA-pinned, staleness self-disclosed
Every execution ruling traces to a specific hashed strategy commit, with an explicit alignment table and a self-disclosed staleness flag.
documented-statement Verify →Details
Public site jitai.co
Evidence pending