Agents will be adopted in healthcare at the pace of trust
Priyanka Agarwal, MD, MBA

Soon, clinic front desks will field a new kind of call: an AI agent asking to reschedule a patient’s cardiology follow-up and offering to share her latest labs before the visit. Just as a growing number of retailers have pushed back on AI agents they can’t verify, many clinics will defer or block these requests. The staff member answering may have no way to confirm that the patient is behind the request, that the patient asked for this exact task, or that the labs being offered are accurate. The patient goes back on hold, and a follow-up that could have been booked in seconds slips another week. Saying no to every agent feels like the safe choice. For a patient waiting on that follow-up, it isn’t.
As a hospital medicine attending at UCSF, I saw where those slipped weeks can lead: a woman whose breast cancer had advanced until it broke through her skin, leaving hospice as her only option; a patient with diabetes who could never get their blood sugar under control and now faced an amputation. Neither became that sick overnight. Somewhere along the way, a referral went unscheduled, a lab result never reached the right doctor, or a medication list fell out of date. That is why I co-founded HealthEx, so that people, and the agents they trust, can act on their full health history safely, confidently and in time to make a difference.
Today a person can ask an AI model a health question and get a thoughtful answer in seconds. But the moment they want to see their own doctor, find out what a procedure will cost, or get a specialist the history behind a new diagnosis, they are back on the phone or in a portal.
AI agents can carry people across those gaps: booking the follow-up, confirming coverage, gathering the records, filling out the intake form. The personal agents people already use can do this work, across every doctor and health plan, not just inside one portal. Healthcare isn’t ready to let them, because a doctor’s office or health plan has no reliable way to know who an agent represents, what the person has authorized it to do, or whether the health context behind the request can be verified. Today, trust is the bottleneck.
That bottleneck matters more every month. KFF polling shows nearly three in ten U.S. adults now turn to AI for health information at least once a month, up from one in six just two years ago. The records those tools need are moving, too: more than a billion health records have now been exchanged nationally through TEFCA, according to HHS/ONC. Demand is here, and so is the data. What’s missing is a framework that lets an agent act on both. That work has started. This month, HealthEx joined Sierra’s Personal Agent Protocol (Poppy) as a design partner, alongside more than 100 companies, to help bring healthcare’s requirements into an open standard for how personal agents work with businesses.
The promise of agents in healthcare
I believe agents are the future of how Americans manage their health. They can take on the work that keeps people from care, the calls, the forms, the follow-ups that slip through the cracks, so people can focus on what they’re working toward: keeping their diabetes in check, getting back to running after an injury, or staying healthy enough to keep up with their grandkids. The best ones won’t just find the next available appointment with whoever is free. They’ll get people to their own doctor, the one who knows their history, or to the best specialist for their condition.
Much of AI in health still stops at insights or the virtual visit. Agents can be the bridge to the rest of the system. For someone managing a chronic condition or caring for a parent, continuity is the care, and that connection is the difference between intending to get care and actually getting it. Getting there is work for the whole industry.
What healthcare needs to know before it says yes
In healthcare, there can be no anonymous agents. An agent that signs in to a patient portal with your password isn’t acting for you; it’s pretending to be you, and passwords can be stolen or breached. Before a provider or plan acts on an agent’s request, it needs answers it can verify to three questions.
Who does this agent represent? A verified individual, at a known level of identity assurance, rather than whoever happens to be logged in. Identity verified with an ID check and a biometric match is a different level of assurance altogether, and it lets the agent act openly on the person’s behalf.
What has the person authorized the agent to do on their behalf? Consent that names the organization, the data and the action, and that the person can revoke at any time. Think of sending a family member to pick up your prescription: the pharmacy confirms who they are and that you sent them, and they can pick up that one prescription, nothing more. An agent should work the same way. When a request goes further, the agent comes back to the person.
Is the health context behind the request verifiable? The person’s own health context, drawn from the places they have received care and traceable to a verified source. A medication list typed from memory is a starting point; one drawn from the person’s records is something a clinician can act on.
The person decides what their agent can and can’t do, and the organization receiving the request decides what it will accept and keeps its relationship with the person.
Shared rules of trust have to come first. Get it right, and every health system and plan has a reason to say yes to an agent, without building a separate integration for each one, and every person can choose whichever agent they want to act for them. Skip it, and each organization has to be convinced one at a time.
For a health system or plan, that yes is worth having. An agent that arrives verified, authorized and carrying the person’s records can mean fewer staff touches per request, intake that arrives complete, and patients who make it to the follow-up. The concerns are real, too: an agent impersonating a patient, an agent that is confidently wrong, unclear accountability when something goes wrong, and staff fielding a flood of agent calls. Those concerns are exactly why trust has to be built in from the start, not added later. The same safeguards that protect patients, verified identity, clear consent and records traceable to their source, are what give a health system the confidence to say yes.
Getting time back
Nobody should have to spend hours on hold, carry CDs of images from office to office, or guess what their care will cost. When an agent a person trusts can reach their doctor, their plan and their records, with their permission and on their terms, they get that time back, and their care team can work as one. At its heart, healthcare is deeply human. Agents can handle the logistics, but the decisions about care stay with the patient and their doctor. The more we automate, the more room there is for human connection.
These three questions belong to everyone who wants agents to help patients, whether you run a health system, a health plan or a health and wellness platform, or build the agents themselves: Who does this agent represent? What has the person authorized it to do? Is the health context behind the request verifiable? When every agent can answer all three, the front desk can say yes, and the patient gets her follow-up with her own cardiologist booked in seconds instead of weeks. Multiply that moment across the country, and agents can help usher in a new era of health abundance, where every person has what they need to reach their own health goals.
At HealthEx, we help people bring their health context into the AI tools they already use. We’re working with health plans, health systems, electronic health record companies, health and wellness platforms and agent builders to help shape how agents earn trust in healthcare. If you want to be part of it, reach out at healthex.io.






