WHAT WE'VE BUILT
What it looks like
when operations stop
requiring you.
These are first-party systems — designed and deployed inside our own operations before we built for anyone else. The architecture is public. The methodology transfers. External client work is not published without engagement.
CASE 01 — MOVEMENT SOLUTIONS
What it looks like when a practice
stops running on its founder.
A boutique physical therapy practice running on founder presence. Every clinical decision, every communication exception, every scheduling conflict routed to the owner — not by choice, but by default.
There was no system. There was just Lance.
WHAT WAS BUILT
A multi-agent AI operating system: twelve named agents, a 470-rule clinical routing engine, a client communication system, a content pipeline, and a governance layer — built on Google Cloud Platform (GCP) with a HIPAA Business Associate Agreement, Vertex AI, Gemini Gems, and Claude Projects.
THE STACK
Google Cloud Platform — GCP (Vertex AI — HIPAA BAA)
Gemini Gems + Claude Projects (multi-agent routing)
Next.js + Supabase
Constitutional governance layer (470-rule clinical router)
Deployed: Vercel · movement-solutions.com
THE RESULT
Clinical routing, session preparation, client communication, content strategy, and consulting intake now operate with the founder as approver — not executor.
Nothing auto-sends.
Everything passes through a human gate before it reaches a client.
THE ARCHITECTURE
ARTIFACT — System Architecture Diagram — Multi-Agent Ecosystem
Agent-to-agent relationship map, autonomy tiers, and data flow through the governance layer — without exposing clinical data or client records.
CASE 02 — THE MOSO APP
A clinical intelligence layer
built from first principles.
Pattern recognition was happening in the clinician's head across sixty active clients.
Session-to-session continuity depended on memory —
a resource that doesn't scale and doesn't transfer.
The gap wasn't skill. It was the infrastructure.
WHAT WAS BUILT
A web application routing interaction logs through a 25-module clinical communication framework — structured around human behavioral patterns, adaptive communication styles, and nervous system state recognition — to surface longitudinal client patterns and generate session preparation briefs before each appointment.
THE STACK
Google Cloud Platform — GCP (Vertex AI — HIPAA BAA)
Next.js + Supabase Auth
Gemini 2.5 Flash / Pro + Claude (best-fit model routing)
Task-based matrix router (Claude ↔ Gemini switching)
Agent cost monitoring
Constitutional governance layer (clinical inference boundary)
Deployed: Vercel
THE RESULT
The clinician enters a session with a brief already generated — cross-referenced against the client's 6-month history, nervous system state patterns, and prior session progression.
Memory is no longer the bottleneck.
APPLICATION SCREENS
Today — session brief view
Client monitoring dashboard
Screenshots pending — monitoring and session views only. No client records or PHI displayed.
THE FRAMEWORK
ARTIFACT — 25-Module Clinical Communication Framework Map
Visual architecture of the clinical intelligence layer — module relationships, routing logic, and output structure.
CASE 03 — PROOF OF TRANSFER
The methodology applies anywhere
the problem is architectural.
A job search is the same operational problem as a founder-dependent practice — at a different scale. Applications scattered across three platforms with no unified pipeline. Interview preparation ad hoc. Calendar coordination manual. Offer tracking in a mental model that doesn't survive a week of pressure.
The architecture built: unified pipeline across LinkedIn, ZipRecruiter, and Handshake. Interview preparation engine via Claude API generating role-calibrated questions. Native Google Calendar integration. Resume variant management per application. Longitudinal history log.
The point is not the use case. The point is that the same methodology — centralize the data, automate the routing, protect the human's judgment for decisions that require it — applies at any scale and in any domain. When we build for a 20-person firm, the architecture is more complex. The logic is identical.
WHAT WAS BUILT
A unified job search CRM: multi-source application tracking with pipeline stage views across all three platforms, an interview preparation engine generating up to 100 role-specific questions via Claude API calibrated to job type, native Google Calendar integration carrying appointment time, contact information, and location, a longitudinal job history log, and a resume vault with per-application variant management.
THE STACK
Next.js + Supabase
Claude API (interview question generation — role-type classification)
Google Calendar API (native integration)
Multi-source job data ingestion (LinkedIn, ZipRecruiter, Handshake)
General internet search — city radius / zip code targeting
Resume import + per-application variant routing
Deployed: Vercel
THE RESULT
One system from first search to final outcome. Application stage, interview prep, calendar, contact records, and resume version — linked.
The job search is now a tracked process with a history, not a collection of open tabs.
APPLICATION SCREENS
Live app requires login — request access via Lance@LabnoLabs.com
LIVE APPLICATION
→ crm-dashboard-two-pi.vercel.appLogin required. Request access via Lance@LabnoLabs.com
THE ARCHITECTURE
ARTIFACT — Search Intelligence Architecture — Q2 2026
Pipeline stage flow, multi-source ingestion, Claude API interview routing, and Calendar integration map.
CASE 04 — FIRST EXTERNAL ENGAGEMENT
Coming Q3 2026.
The first external Build engagement to complete the Architect and Build phases. Architecture diagram and outcome brief published upon client release. Include a request in your intake form if you want to be notified when this posts.
If you want to understand what we build before applying, these cases show the methodology at full resolution. The architecture diagrams publish Q2 2026. If you want them before they're public, include that request in your intake form.
Work with us →QUICK ANSWERS