The agent that runs automated post-discharge follow-up.
The OneDose Follow-up Agent runs the structured check-ins a patient needs after leaving hospital. It reads the discharge summary, schedules the next 30 days of contact, and calls or messages the patient on Day 1, Day 7, Day 14 and Day 30 — recording each answer against the patient record and paging a clinician when something needs one.
The schedule is derived from the discharge summary, the prescription and the risk profile, so a complex cardiac discharge and a routine day-case do not get the same calendar.
How does the Follow-up Agent actually work?
What follows is the mechanism — what the agent does, in what order, and where a human stays in the loop.
It builds the plan from the discharge summary
The agent parses the summary and the prescription and derives the follow-up calendar from them. Nobody sits down and builds a schedule per patient, which is the step that normally means only the highest-risk cohort gets one.
It asks the same questions every time
Each check-in is a structured instrument, not a chat. The same questions in the same order means the Day-7 answer is comparable to the Day-30 answer, and both are comparable across patients — which is what makes the data worth collecting at all.
It escalates on signal, not on schedule
A system that pages the care manager after every check-in trains them to ignore it. The agent routes a case to a human when an answer crosses a threshold, when confidence is low, or when the patient asks for one — and stays quiet otherwise.
It writes back where the patient already lives
Each contact is recorded against the patient record in the systems the hospital already runs, so the follow-up history is in the chart rather than in a vendor dashboard someone has to reconcile later.
What will the Follow-up Agent not do?
The limits matter more than the capabilities when the subject is medication, so they are stated plainly rather than left to be discovered in a pilot.
- It does not make clinical decisions. It collects and escalates; a clinician decides.
- It does not diagnose. Symptom answers are triaged against thresholds a clinician sets, and anything ambiguous goes to a human rather than being resolved by the agent.
- It does not replace the care team. It removes the dialling and the charting so the team spends its time on the patients who need attention.
How does this agent fit with the others?
The Follow-up Agent is one of six OneDose agents that share one patient context and one audit log. That shared context is the difference between a workforce and six tools: the voice agent already knows what the follow-up agent asked yesterday, so the patient is not asked to repeat themselves and the care team reads one history rather than six.
Frequently asked
- What is an automated post-discharge follow-up agent?
- An automated post-discharge follow-up agent is software that runs the scheduled check-ins a patient needs after leaving hospital — confirming they collected and understood their medication, capturing side-effects and recovery signals, and flagging deterioration to a clinician — without a nurse placing each call by hand.
- When does the OneDose Follow-up Agent contact a patient?
- On Day 1, Day 7, Day 14 and Day 30 after discharge by default. The exact calendar is derived from the discharge summary, the prescription and the patient risk profile, so a complex discharge is contacted more often than a routine one.
- What happens when a patient reports a worrying symptom?
- The case is routed to a human — a pharmacist or care manager — with the full conversation attached. The agent does not triage the symptom to a conclusion on its own authority, and it does not close a case a clinician has not seen.
- Does the follow-up agent work by phone or by text?
- Both. The agent calls by voice or messages by SMS or WhatsApp depending on the patient and the deployment. Which channels are live for your region is worth asking us directly.