Command Center
Built in a living room after shifts. Verified by the creator of hexagonal architecture. Independently evaluated against the patterns used by Segment, Palantir, and Stripe.
In 2021, the CDC published a number that should have stopped the automotive service industry cold. 2.5 times the national male average. Higher than mining. Higher than farming. Higher than construction. I’m a lead transmission specialist at a GMC dealership in Florida. I did not leave. I built something instead.
of entry-level technicians leave within a year. Most leave the industry entirely.
unfilled technician positions nationwide. 76,000 needed annually—training programs produce 39,000.
average warranty claim denial rate. 78% of claims kicked back at least once before payment.
per-dealership annual bleed from warranty denials, comebacks, and turnover—per rooftop.
annual industry bleed across 16,990 franchised dealerships nationwide.
comeback rate—vehicles return for the same repair. J.D. Power 2025 CSI Study.
The knowledge walks out the door with every retiring master technician. The tools sold to fix this stream customer VINs and repair histories to consumer-tier AI APIs with no PII scanning. The industry has sold “AI” as a word. Command Center ships it as architecture.
Built using hexagonal architecture — not because it was clever, but because the bay demanded it. The scan tool eats the only Ethernet port. The Wi-Fi password is on a sticky note from three years ago. It has to run offline. It has to work with whatever database the shop already licenses. It can’t care which AI provider sits behind it.
No cloud dependency. No internet required to function. Bidirectional sync queues offline and pushes when connectivity returns. The system doesn’t brick when the network goes down — it degrades gracefully to local SLM inference.
Deterministic. Temperature locked at 0.2. Won’t fill a gap with a guess. PII-scanned before anything touches a network. Post-generation pin verification cross-references every connector and pin against the vehicle’s actual netlist database.
SQLite with WAL mode. 18 versioned migrations. Eight databases per vehicle. SHA-256 audit hash chains. sqlite-vec for semantic search. A schema scanner auto-discovers and maps unknown OEM database formats without manual configuration.
AI providers, databases, vision engines, sync targets — all swappable through a single JSON config file. The swappable proxy hot-swaps AI backends live, with a smoke-test atomic commit. No restart. No degraded state.
Structured output enforcement. Controlled generation parameters. Database-grounded context injection. Token budget enforcement. Post-generation audit with a separate system prompt. Auto-search feedback loop so the model requests data instead of guessing.
Independently evaluated against the architecture patterns used by Segment, Palantir, Stripe Radar, Linear, VS Code, GitHub Copilot, and Shopify. Held up against every comparison.
~$3/month AI inference cost per dealership. Cloud sync $0–$25. Hardware: $0–$800 one-time (runs on existing bay machines). No enterprise DMS pricing. No per-seat licensing. No hidden infrastructure fees. The cost model matches the floor it was built on.
omg, that’s amazing… sweet — that’s exactly what it is supposed to do :)
Alistair Cockburn — creator of Hexagonal Architecture
Turn-by-turn chat that queries 10 local databases per request — DTC definitions, TSBs, pinouts, harness routing, component locations, flowcharts, symptom bytes, and symptom-based procedures. Pulled from the vehicle’s actual OEM databases. Cites sources so the tech can verify.
Generates OEM-compliant 3Cs narratives (Complaint, Cause, Correction) with measurements, TSB citations, and the specific language auditors look for. OEM-specific compliance rules auto-loaded from VIN. Structured-output enforcement. Labor code suggestion post-generation.
Pattern-based rules engine and semantic AI audit run in parallel. Catches missing measurements, vague language, logical flow gaps, undocumented tools. Results merged and sorted by diagnostic impact. Interactive correction workflow preserves the full audit trail.
Master tech diagnostic reasoning preserved through LoRA fine-tuning. Trains on approved stories AND rejected ones — with admin reasoning. Dealership-owned AI models. The OEM’s own chargeback window serves as the quality signal. Auto-training during idle.
Local WebSocket server connects the desktop to a phone with no cloud intermediary. Phone-based diagnostic chat, VIN scanning, document capture. Live PID streaming from OEM scan tool. Three-tier consent gate. Rolling token auth every 120 seconds.
Self-healing vision pipeline captures claim codes from legacy scan tools through screen OCR. Filesystem polling for binary claim data. Thread-safe deduplication. Schema-agnostic OEM database ingestion auto-discovers and maps unknown formats.
Architecture diagrams prove structure. Video proves existence. Two recordings of the desktop application running on a machine in a transmission bay — not a mockup, not a prototype, not a slide deck.
Interactive Diagnostic Foreman
Turn-by-turn AI-guided diagnosis. Queries multiple OEM databases per request. Sources cited in every response. Live state cards populate from each AI turn. Running offline with local SLM inference.
Warranty Narrative Engine
3Cs narrative generation (Complaint, Cause, Correction). OEM-specific compliance rules loaded from VIN. DTC auto-extraction. Labor code suggestion. PII-scanned. Dual-audited. Saved with tamper-evident hash chain.
Every claim on this page is verifiable against actual source code — not a pitch deck, not a whiteboard diagram. Below are the call graphs, port boundaries, and data flows traced directly from the codebase. The flow is verified. The port boundaries are real. The code is the documentation.
Why this is defensible: PII is scrubbed before the story touches any network. Post-generation verification cross-references every connector and pin against the vehicle’s actual netlist database. The AI is constrained to structured output with controlled generation — it cannot “fill a gap with a guess.” The audit trail is cryptographically tamper-evident. If an OEM charges back, the dealership has a hash-verified chain of every edit, every prompt, and every audit flag — not a Word document.
8 database categories per vehicle: DTC definitions, flowcharts, TSBs, pinouts, harness routing, component locations, symptom bytes, symptom procedures. All read through abstract ports — zero OEM-specific imports exist in the domain layer. The schema scanner means a new OEM database format is discovered and mapped without new code. The diagnostic shell queries all databases in parallel per user question and cites the specific source in every response.
Self-healing: When vision confidence degrades — due to a tool update, UI change, or resolution shift — the system runs on-device calibration. A validation gate measures whether calibration improved accuracy. If it made things worse, the system rolls back automatically. No cloud retraining pipeline. No manual intervention. The system monitors itself and fixes itself.
Failure is visible, not silent: The dual-storage pattern (local vault + remote storage) means no data is lost when offline. The sync outbox is a durable database, not an in-memory buffer — a power loss during an offline period loses nothing. The health indicator shows sync health in real time so ops can see degradation before it becomes data loss.
Hexagonal at every layer: The capture service is constructed fresh per capture — zero persistent state. All dependencies are injected through abstract ports: vision extraction, local persistence, and remote storage. Processing runs in a background thread so VLM inference never blocks the UI. Every captured document passes through PII scanning before persistence or sync.
PII scanner alone is a competitive moat: Of 16 competitor products analyzed, zero perform PII scanning before data leaves the device. Most stream VINs and repair histories to consumer-tier AI APIs with no sanitization. The three intercept points (save, sync, training export) mean PII is caught at every egress boundary — even if one check is somehow bypassed, the next one catches it.
-
Alistair Cockburn — Creator of Hexagonal Architecture
Responded personally and posted public endorsement to 31,497 LinkedIn followers. “That’s exactly what it is supposed to do.” Cockburn co-authored the Agile Manifesto and published the definitive hexagonal architecture reference in 2025.
-
Independent Architecture Evaluation
May 2026. 21 source files read directly — no documentation, no pitch. Verdict: “Genuinely well-architected application.” Hexagonal pattern confirmed as “implemented, not just named.” Dependency injection auditable and explicit. Degradation strategy consistently applied.
-
Evaluated Against Segment, Palantir, Stripe & Linear
Architecture compared against Segment (multi-source normalization), Palantir (ontology layer), Stripe Radar (audit-grade ML), Linear (local-first sync), VS Code (extension architecture), GitHub Copilot, and Shopify. Held up against every comparison.
-
D. Richard Hipp — Creator of SQLite
Responded personally: “I do enjoy hearing about unusual uses for SQLite.” Full architecture post published and approved on the SQLite Forum. Eight databases per vehicle, WAL mode, SHA-256 hash chains.
sqlite.org/forum -
14 Provisional Patent Filings — 22 Patentable Ideas
Warranty narrative generation. Diagnostic state capture. Self-healing vision pipeline. Multi-OEM schema normalization. Distributed local AI training. Dual-provider live hot-swap. 204 claims mapped to specific code paths. Independently validated against prior art.
-
47 Features Code-Verified. Competitors: ~7 (Marketing Claims Only)
16 companies forensically analyzed. Categorized as AI Wrappers, Marketing Renames, or Vaporware. No competitor has offline capability, local inference, PII scanning, database agnosticism, AI provider hot-swap, or hexagonal architecture — not even as a marketing claim.
The data room exists to answer every question a technical team would ask. No marketing. No white paper written in reverse. Just source-level evidence.
Software engineering degree. Same hands in the bay.
I’m not a startup founder. I’m not looking for press. I’m a transmission guy who got tired of watching the knowledge walk out the door. I built something because nobody else was going to.