AI Systems Architect · Max Birnberg
I design, build, and operate applied AI for small business operations — custom EMR work, CRM automation, AI voice and chat agents, KPI command centers, and autonomous daily agents. Everything here is deployed and in production, not a proposal.
What I Build
Every engagement adapts these to your stack — the medical record, the CRM, the phones, the reports — so the business runs on systems instead of memory.
Custom electronic medical record layers on Canvas Medical: an ambient AI scribe that transcribes locally and drafts notes for clinician review, insurance card OCR with staff verification gates, a branded patient companion app, and controlled-medication inventory tracking inside the EMR.
One hub for the whole business: insurance billing tracked from submission through paid, pending, and blocked; cash-pay revenue current and forecasted; daily and weekly marketing reports on leads, conversion, and cost per lead; and captured SOPs staff can query like a veteran employee.
Inbound and outbound AI phone agents that answer, qualify, and book; website and SMS assistants that work from your full knowledge base with structured staff handoff; and daily reporting on every AI call and message — attribution, conversion, and booking outcomes, delivered every morning.
Custom MCP connectors that give AI direct, governed access to your systems; scheduled daily agents for KPI tracking, cancellation and retention analysis, and inventory follow-ups; and reconciliation workflows that audit billing against the record and surface claims that were never submitted.
Case Study
Sole technical architect for a multi-site interventional psychiatry group in Palm Beach Gardens, Florida — reporting directly to the CEO/COO and owning CRM, EMR, AI agent, and marketing infrastructure end to end across two clinics.
I led the migration off a closed legacy EHR and architected a fully custom medical record layer — provider-specific clinical workflows, medication and EPCS prescribing configurations, scheduling logic — live today with the full patient panel. On top of it: an ambient AI scribe that transcribes on the clinic's own hardware so audio never touches the cloud, a bidirectional CRM-to-EMR bridge that converts qualified leads into patient charts and unifies messaging into a single thread, a branded patient app with mood tracking, journaling, and secure messaging, and a Spravato inventory tracker managing the full lifecycle of a REMS-regulated medication across both locations.
The single place leadership sees how the business is actually doing: insurance claims from submission through paid, pending, and blocked; cash-pay revenue current and forecasted; automated marketing reports across Google, Facebook, and SEO so spend decisions run on this week's data; and an agent runtime where morning leadership briefings, alerting, and call classification run on schedule without a human pressing a button.
An AI communications layer deployed across Allay and its sister clinic NeuPath: phone agents that answer, qualify, book discovery calls, and work lead lists on compliant calling windows; a website and SMS assistant with crisis-language escalation built in; a rebuilt CRM with multi-stage pipelines, automated lead routing, and HIPAA-compliant patient messaging; and a custom CRM connector producing daily attribution and performance reports on every AI call and message. I QA the agents against real transcripts, not vendor summaries, and hold vendors to the numbers.
A custom, read-only AI connector to the EMR runs scheduled daily agents: appointment and KPI tracking, cancellation and retention analysis, and inventory management that generates the day's follow-up tasks. An AI reconciliation workflow audits the billing team's monthly reports against the clinical record and surfaces claims that were never submitted. That is found revenue, every month.
Proof of Practice
I hold my personal systems to the same standard I sell. All of my personal agents run through Jarvis, a private, local-first AI hub I built that orchestrates my custom connectors and daily agents in one place.
A custom Plaid connector — masked account data only — runs daily checks on spend, cash position, recurring charges, and investments. Paired with market data for portfolio analysis and a Sheets connector with guarded writes: an agent can log a transaction but can never corrupt the ledger.
A custom WHOOP connector tracks recovery, sleep, HRV, and strain against my own baselines, combined with a PubMed connector for agentic research support — including an 18-week marathon training block where AI plans each week from live recovery data.
Agentic macOS security diagnostics and remediation on my own machines — firewall hardening, permission audits, credential hygiene — plus agentic coding workflows that let me ship production software as a team of one.
How I Work
Every system ships with living knowledge bases that record how the platform works and every lesson learned — so the AI performs like a veteran employee from minute one and quality compounds instead of resetting.
Connectors give AI governed access to your data; agents run on schedules; briefings surface only what needs a human decision. People stop doing data entry and start doing judgment.
Read-only by default, human confirmation gates on anything consequential, kill switches, and no sensitive data in AI surfaces. Built to HIPAA-grade discipline, because I learned in the hardest industry for it.
The ROI logic is simple: fewer hours on documentation, follow-up, reporting, and reconciliation; faster lead response and higher conversion; revenue that stops leaking through unbilled claims and stockouts; and an owner who sees the whole business every morning without asking anyone for a report.
About
AI systems architect owning the full operational stack for a multi-site interventional psychiatry practice: custom EMR development, CRM architecture, AI voice and messaging agents, and growth automation. Finance and data analytics foundation from two years modeling billions in transaction volume. Builds production systems end to end, from architecture through staff rollout.
Sole technical architect for a 10-person interventional psychiatry and wellness clinic and its sister practice. Custom Canvas Medical EMR and ~1,300-record migration; GoHighLevel CRM rebuilt from the ground up; inbound and outbound AI phone agents with a daily performance dashboard; EMR-to-CRM marketplace app; agentic controlled-substance inventory workflows across two locations; SEO spend and content production for both clinics.
Spearheaded a centralized enterprise data warehouse (SQL, AI-SQL, ETL, dashboards). Engineered an AI-driven lead enrichment system in Salesforce and Clay contributing to a 49% increase in sales. Led a nine-month analysis of $1B+ in transaction volume; built profitability models on $75M+ and ran statistical testing on $2B+ in processing volume for CFO-level pricing and billing decisions.
Corporate Finance, Entrepreneurial Finance, Managerial Accounting, Business Data Analytics, Quantitative Analysis.
Competed at the D1 level alongside a full course load; helped lead the program to the America East semifinals.
Contact
I take on a small number of engagements with owner-led businesses: an AI operations audit to map where agents pay for themselves fastest, followed by build-and-operate work adapted to your stack. If your business runs on people remembering things, I can make it run on systems instead.