Blog/Healthcare & Clinics

AI agents for clinics and healthcare practices

Clinics use AI agents on administrative load rather than clinical decisions: patient intake, insurance eligibility checks, prior authorisation packets, referral coordination and claim denial triage. Every one of these touches protected health information, so the architecture has to establish a BAA-covered processing path before anything ships. Clinical judgement stays with clinicians.

Start with the paperwork, not the medicine

The administrative burden in a small practice is the problem worth solving. Prior authorisation alone consumes a substantial share of clinical staff time, and it is almost entirely form-filling, document assembly and telephone follow-up — repetitive, high-volume, and requiring context from several systems at once. That is a precise description of what agents are good at.

Clinical decision support is a different product with a different regulatory posture. An agent that drafts a prior auth packet is an administrative tool. An agent that suggests a diagnosis may be a regulated medical device. Keep the line bright, and build on the administrative side of it.

HIPAA comes before the workflow design

Any agent touching patient data is handling PHI, which means the model provider is a business associate and you need a BAA in place with them. Both major providers offer this on their enterprise tiers; consumer API tiers generally do not carry one. Sending PHI to an endpoint with no BAA is a reportable disclosure.

Beyond the BAA: minimum necessary applies to prompts, so send the smallest slice of the record that answers the question rather than the whole chart. Log every access at the field level. Zero data retention should be contractual, not assumed. This architecture is not optional decoration around the agent — it is the first thing to build.

Where agents earn their keep in a practice

WorkflowTypical burdenAgent scope
Prior authorisationHours per week of staff time, high denial-on-technicality rateAssembles the packet from the chart, checks it against the payer's published criteria, flags what is missing before submission
Eligibility and benefitsRepeated per appointment, often on holdQueries the clearinghouse, reconciles the response against what the patient reported, surfaces mismatches at booking rather than at check-in
Referral coordinationChased manually, frequently droppedTracks the loop from order to consult note received, escalates the ones that go quiet
Claim denial triageDenials sorted by hand, many never reworkedClassifies the denial reason, routes the reworkable ones with the correction already drafted
Appointment no-showsRevenue lost, slots wastedPredicts likely no-shows from history, runs the confirmation sequence, offers the slot onward when a cancellation lands
Clinical documentationDifferent product, different regulatory question. Out of scope here.

The integration reality: EHRs are hard

This is where healthcare agent projects actually stall. Epic, athenahealth, eClinicalWorks, NextGen and Cerner all support FHIR to some degree, and US regulation has pushed real progress on read access. Write access is another matter, and vendor-specific app review processes can add months to a timeline before a single call is made in production.

Plan for it. Scope the first agent around what you can read plus what a human can commit, and treat deeper write integration as a later phase with its own schedule. A project that assumes day-one write access to the EHR is a project that will be late.

A prior authorisation agent, traced

  1. Detects the trigger

    An order is placed for a service the patient's plan requires authorisation for. The agent picks this up from the order rather than waiting for someone to notice.

  2. Retrieves the payer's criteria

    Looks up the current medical policy for that plan and procedure — these change, and stale criteria are a common denial cause.

  3. Assembles evidence from the chart

    Pulls only the elements the criteria call for: the relevant diagnoses, the conservative treatment already tried, the specific imaging. Minimum necessary, by design.

  4. Identifies the gap

    If the criteria require six weeks of documented physical therapy and the chart shows four, it says so now — before submission, while it can still be fixed.

  5. Queues for clinical sign-off

    A clinician reviews and submits. The agent never asserts medical necessity on its own behalf.

FAQ

Questions people ask about this

Is it HIPAA compliant to use AI agents with patient data?

It can be, but only with the architecture in place first. You need a Business Associate Agreement with the model provider, which enterprise tiers offer and consumer API tiers generally do not. Beyond that: send the minimum necessary data in each prompt rather than whole charts, contract for zero data retention, and log access at field level.

Can an AI agent make clinical decisions?

No, and it should not be built to. An agent that assembles an authorisation packet or triages a denial is an administrative tool. An agent that suggests diagnoses or treatment may meet the definition of a regulated medical device, which is a different product with a different approval path. Keep the boundary explicit in the system design.

Which EHRs can AI agents integrate with?

Epic, athenahealth, eClinicalWorks, NextGen and Cerner all support FHIR to varying degrees, with read access considerably better supported than write. Vendor app review processes can add months before production access. Scope the first agent around read plus a human commit step, and treat write integration as a later phase.

What is the highest-value first agent for a small practice?

Prior authorisation, in most practices. It is high volume, consumes clinical staff time disproportionately, has a high denial rate on avoidable technicalities, and the criteria are published — which means the agent has something concrete to check the packet against before submission.

Got a workflow that looks
like one of these?

Tell us which one eats your team's week and we'll tell you what an agent can take off their plate, and what should stay with a human.