charmthirteen.com
    Build · Training

    Keep the humans.

    charmthirteen designs AI for good. Some companies sell AI as a way to need fewer people. We build it so the people you already have get sharper, and we prove that in healthcare and government, where getting it wrong has a cost.

    Schedule a Vibe CheckSee how we build →
    services.exe
    BuildTraining
    status.txt
    Booking builds and training
    Limited spots open

    "AI that makes people more capable and keeps them in charge."

    Schedule a Vibe Check →
    problem.txt
    The real problem

    You don't have an AI problem. You have a systems problem.

    Most teams:

    • Use too many disconnected AI tools
    • Don't know what should (or shouldn't) be automated
    • Risk data privacy, compliance, and accuracy issues
    • Waste time on workflows that don't scale

    That's where I come in.

    Safe, efficient, and usable. In that order.

    how_it_works.exe
    How it works

    A clear process from vibe check to working system.

    Step 01Vibe CheckTwenty minutes, free. We establish your baseline. Where you are, what is already working, and what is not.
    Step 02DiscoveryWe go deeper. I learn your context, your constraints, and your gaps, and we find the real problem before anything gets designed.
    Step 03Blueprint, then BuildDiscovery decides what the work is. A Blueprint you own, then a build that runs on your accounts, or training for your team.

    Three things it can turn into:

    • Training your team
    • A Blueprint you own
    • A build that runs on your accounts

    You do not get sold a service. You get matched to a solution, and the scope comes after discovery instead of before it.

    who_this_is_for.txt
    Who this is for

    Built for teams where a wrong AI output reaches a patient, a claim, or a citizen.

    Compliance, accuracy, and trust aren't optional. Neither is structure.

    Health systems and clinical teamsDeploying ambient scribes, agentic workflows, or AI in clinical and revenue cycle operations.
    Federal health agenciesAdopting AI inside locked-down environments where the tooling, the data, and the oversight are all constrained.
    Healthtech foundersBuilding products that have to survive clinical review, procurement, and a security questionnaire.
    orinyx.exe
    Healthcare · Design partners open

    Orinyx. Independent verification for clinical AI, before it reaches a patient.

    Orinyx is the first product out of the charmthirteen studio, built from a question the advisory work kept running into. Hospitals wanted an independent way to test clinical AI before deployment, and no one could give them one. Orinyx checks every AI assertion against authoritative sources instead of another model's judgment, so each verdict is deterministic and arrives with a citation.

    • Phase 1 runs in a sandbox on synthetic data, no PHI, no EHR connection
    • Deterministic verdicts with citations showing what was checked
    • Findings documented for governance review
    • Design partner pilots open now
    Learn more about Orinyx ↗
    claude_loves_lovable.exe
    Workshop series

    Claude Loves Lovable

    A founder-focused vibe coding series on shipping real product with Claude and Lovable. Five live sessions, and every one ships a Claude skill you keep.

    See sessions, pricing, and FAQs →
    Build

    Discovery, then a Blueprint, then a build you own.

    Two lanes. Published prices.
    See the Build ladder →
    different.txt
    What makes this different

    Most AI consultants have never watched a clinical workflow break in production.

    EHR solution and configuration analysis
    Healthcare data product management
    Clinical AI governance research

    That background is why the recommendations hold up after I leave the room.

    Final call

    If your team is serious about AI, you need a system.

    Let's build it right.
    Schedule a Vibe Check ↗