Skip to content
Curious Context Labs

Healthcare · Agent

Patient message reply drafts

AI-drafted replies to patient portal messages

Portal messages are sorted by type, and routine ones get a draft reply in the clinic's voice, which a clinician or nurse edits and sends.

01 today

The problem

Patient portal messages have become a second workload for clinicians and nurses. Many are routine, such as refill questions, appointment changes or how to prepare for a test, but each one still needs reading and a careful reply. Inboxes spill into evenings.

02 the run

What the AI does

  1. Step 1: Reads new portal messages and sorts them: administrative, medication, results questions, symptoms or other.
  2. Step 2: Sends administrative messages, such as booking changes, to the front desk queue.
  3. Step 3: Drafts a reply for clinical messages using the patient's record and your clinic's approved wording, in plain language.
  4. Step 4: Highlights any message that mentions worrying symptoms so a clinician sees it first.
  5. Step 5: Places the draft in the clinician's inbox for review; nothing is sent automatically.

paused: waiting for a person to approve

03 human in the loop

Where a person approves

A clinician or nurse reads, edits and sends every clinical reply. Messages describing new or worsening symptoms are always handled by a clinician, never by a draft alone.

04 after

What changes

Clinicians start from a sensible draft instead of a blank box, and routine admin messages go straight to the right team. Studies so far show less mental load rather than big time savings, so this is about easing burnout.

Case studyEasing the patient inbox without letting AI answer clinical questions aloneThe rollout, what to measure, a worked example and the research behind it.

see also

All healthcare use cases ->
  • Healthcare

    Ambient clinical notes

    With the patient's consent, the consultation is turned into a draft note in your template, which the clinician checks, edits and signs in the record.

    Custom app
  • Healthcare

    Clinical coding support

    Coders get a ranked list of candidate codes with the supporting text from the record, looked up in the official code sets, for them to accept or change.

    Custom app
  • Healthcare

    Prior authorisation packets

    Prior authorisation requests are assembled from the record against each payer's criteria, with missing evidence flagged, then submitted by staff.

    Agent

Tell us how your business runs. We'll tell you where AI fits.

A free 30-minute call. You talk, we ask questions, and you leave with a few concrete ideas — or an honest answer that AI isn't the right fix yet.

Working with teams around the world.