I was a retail pharmacist for 5 years. Independent pharmacies are getting squeezed by PBMs and thin margins, and owners drown in manual work: chasing prior authorizations, re-checking claims for underpayments, calling patients who never picked up. Most of it is repetitive and rules-based, so I automate it. What gets installed: - A Command Center — a local dashboard staff open: today's fills, aged will-call, margin alerts, PA queue. - The AIOS underneath — scheduled automations that ingest the pharmacy's data, run the tools (margin recovery, PA autopilot, patient win-back), and push reports. Nobody has to click anything. The Hardware: Each pharmacy gets a Mac Mini in the back office. I set it up at home, then drop it in. It runs the automations on a schedule and holds all data + dashboards locally, encrypted (FileVault). BestRx is the first pharmacy management system we're working with (Windows-only, can't run on a Mac), so the two machines stay separate. The only thing that crosses is an exported CSV of prescription/claims data: manual export to a watched folder on day one, then BestRx's built-in Scheduled Reports auto-delivers it. BestRx also has an API integration program we're pursuing, so the plan is to move off the manual drag-and-drop CSV entirely and pull the data directly. And before that, if the Playwright CLI can drive BestRx's export screen, we'll try that first to kill the manual step with zero dependency on their side. I run and update every box remotely over Tailscale (WireGuard VPN) — SSH in, deploy a new automation, no site visit. Locked down so only my device reaches any box. Where Claude runs. Claude can't run on the Mini (cloud-only), so I call it through AWS Bedrock under a BAA, billed per token (~$30–150/mo per pharmacy). Two BAAs gate everything: pharmacy↔me, and me↔AWS (so PHI can legally touch Bedrock). The consumer Claude plan is excluded from BAAs, so it never touches patient data. How I stay HIPAA compliant: - PHI stays on the box. The only PHI that leaves goes to Bedrock, legal under the AWS BAA. - Tailscale carries me and my code, never bulk patient files. WireGuard is end-to-end encrypted; Tailscale can't read the stream (the HIPAA "conduit" position). Fallback if needed: self-hosted Headscale. - Human-in-the-loop. The AI reads docs, auto-fills forms, and flags issues. It never submits. A prior auth still needs pharmacist review and prescriber attestation under their NPI. The tool prepares, a licensed human decides. - Claude builds and tests on synthetic data; only fixed, tested code runs on real PHI. No live AI improvising on patient data in production. - Plus audit log, encrypted off-site backups, retention floors.

I'm a pharmacist (5 yrs) building an AI agency that installs an AI Operating System into independent pharmacies. Here's my approach — tear it apart. The model: build here → deploy there. I build and test the whole AIOS in my own workspace first, then deploy it on-site onto a Mac Mini that lives at the pharmacy. Their system runs locally on that box, 24/7. Why a local Mac Mini? -Pharmacies hold protected patient data (HIPAA). Running everything locally means no patient data ever leaves the building — no cloud. That one promise kills the biggest objection when I'm selling door-to-door. -The installer is Mac/Linux only, and a Mini matches my own setup — so what I build transfers cleanly. -One-time hardware + disk encryption = a clean compliance story I can stand behind. The stack: -Claude Code — the engine. Plain English in → it builds tools, wires automations, and fixes issues. How a non-coder ships real software. -Layers, installed one at a time: Context (it learns the business) → Data → a daily intelligence brief → Automate tasks away → Build. -Connectors: Fireflies (meeting notes/action items) + Google Workspace. -Telegram bot — control the AIOS from my phone (text, voice, photos). -Pharmacy tools I built: Reimbursement tool to increase revenue directly + an audit-prep tool Both of those are current and ready while I have other automations and workflows to set up as well. Automations + tech issues all route through Claude Code — describe it in plain English, it gets built or fixed on the spot. No vendor tickets. Scaling: first install I'm doing the careful manual way (it tells me what to standardize). After 1–2, I package it into a one-command installer so every future pharmacy is fast and repeatable. As far as a one command installer, it's something I'm still working on, but that's the general idea as of now. Where I want input: As far as implementation, that AI operating system, is the Mac Mini route overdoing it, or do you recommend going some alternative route?

I’m looking to connect with someone who has experience building AI solutions, automations, workflows, or operational systems for healthcare, preferably within independent or community pharmacies. My background is in pharmacy, including working in independent pharmacies and helping build operations from the ground up. I understand the workflow gaps, compliance considerations, operational challenges, and limited revenue opportunities that independent pharmacies face. I have several ideas I’d like to implement, especially around improving pharmacy operations, patient engagement, medication adherence, refill workflows, administrative processes, clinical service workflows, and creating new revenue opportunities for independents. Ideally, I’m looking for someone who has direct experience with pharmacies. However, if you have broader healthcare automation experience and believe your solutions can transfer well into the pharmacy space, I’m open to connecting. Because this involves healthcare workflows, patient data, and compliance-sensitive systems, I prefer working with U.S.-based professionals. That said, I’m open to working with someone outside the U.S. if they have proven experience in the independent pharmacy niche. Please only reach out or comment if you have a portfolio, LinkedIn profile, website, case studies, or examples of relevant healthcare/pharmacy automation work that I can review. I’m looking for someone who understands practical healthcare operations, compliance-aware workflows, and revenue-focused solutions for independent pharmacies.

I’m currently building an AI OS / AI automation consulting service for businesses across different industries. My strengths are client communication, networking, workflow discovery, and identifying where AI can improve operations. I already have potential clients interested and have started auditing their businesses to find automation opportunities. The main gap is technical implementation. I’m still learning that side, but I want to make sure I deliver high-quality systems and build a reputable name. I’m considering two routes: 1. Technical partner — lower upfront cost, but requires finding someone skilled, reliable, and trustworthy. 2. Structured program/agency support — higher upfront cost, but provides implementation help, execution support, and guidance while I build. For both routes, I have already scheduled and spoken with potential technical partners, along with programs that offer the services I'm looking for. But if there are any recommendations or input on partners or services people have worked with previously in the past, I highly recommend. I'm very open to scheduling a call. For those who have been in this position, which route would you recommend? Are there other approaches, companies, or technical operators you’d suggest for AI OS implementation?

I’m currently helping develop an AI operating system for a mutual friend’s company, and I’m trying to better understand the right architecture for one of my first use cases. Specifically, I’m trying to determine when it makes more sense to build something as an agentic skill versus breaking it down into separate workflow automations. My current use case is an outbound lead generation system. The goal would be to: 1. Identify or organize potential leads 2. Send outbound emails to prospective clients 3. Track and interpret email responses 4. Move qualified responses into a lead funnel 5. Trigger an outbound lead qualifier to call or follow up with verified leads My current understanding is that an agentic skill may be best when the goal is to create a more complete capability that can use multiple tools and make decisions across a defined process. However, I’m unsure whether this use case should be built as one larger agentic skill or as a series of smaller workflows that each handle a specific task. Would the better approach be to first break this down task by task, build individual workflows for each step, and then combine those workflows into a broader skill that manages the full lead generation and qualification process? Basically for an outbound lead generation system that includes email outreach, response tracking, lead qualification, and follow-up calls, should I structure this as one agentic skill or as multiple workflow automations that are later combined into a larger skill? Since this is one of my first AI projects and I’m building it as part of my portfolio, I’d appreciate any input on the best structure, how to think through workflows versus agentic skills, and any useful resources, videos, or frameworks that could help me build this correctly.