The patient advocate
The cornerstone of healing relies heavily on the experience of being seen and deeply heard. When a physician has forty-five minutes to divide among a dozen patients, the overwhelming influx of unfamiliar diagnoses, complex prescriptions, and dense lab results often leaves a profound void in understanding. Frequently, the constraints of time prevent both the patient and the doctor from synthesizing the complete narrative from the available data. Every appointment becomes a fleeting opportunity that demands precise preparation.
Patient advocates step into this space to serve as a vital second set of eyes and ears. They provide a second mind that recalls conversations from months prior, connects scattered data points, and independently researches the gaps left unexplained during a brief clinic visit. Because most individuals navigate this system alone, we must explore how to construct this dedicated second mind as an autonomous agent.
the anatomy of a second mind
Each of the advocate’s core duties corresponds directly to a specific component of agent architecture:
Recall relies entirely on long-term memory. Following a session, the system distills the transcript into structured records, each carrying its date, its source, its exact values with units, and its current status: [FACT | 2026-07-03 | src: discharge orders | active] metoprolol tartrate 25 mg twice daily. These records are embedded as vectors and securely stored, and the structure lets the record evolve. A correction from the patient supersedes the old entry, retiring it to inspectable history rather than deleting it. When a new question arises, the agent retrieves the most clinically relevant history through three channels at once: semantic similarity, the index keys a record is filed under, and the dates it is about.
Connection emerges naturally from this accumulation. A historical record allows the agent to recognize trends, understanding that a specific creatinine level holds different meaning if it marks a third consecutive rise.
Research requires delegation to a specialized subagent that accesses current and fully sourced clinical information. Relying on the static training data of a language model for medical dosing introduces unacceptable risk.
the two jobs, worked through
This architecture elegantly serves two primary patient-facing objectives.
First, it facilitates understanding symptoms and diagnoses. If a patient receives a prescription for metoprolol following a heart event, the advocate clearly translates the function of a beta-blocker. It delineates expected side effects from genuine emergencies and prioritizes critical safety protocols, such as the danger of abrupt cessation. The numbers themselves stay where they belong: any hold-the-dose cutoff or when-to-call threshold appears only as a quote from this patient’s own record, attributed to the clinician who set it, with its date. When no such instruction exists in the record, the advocate says so and drafts the exact question that gets one.
Second, it ensures thorough preparation for follow-up care. The system drafts precise questions tailored for the upcoming appointment, ensuring maximum utility of the physician’s time. Here is a demonstration of this process from a live cold-started session; watch the recalled records arrive with their sources attached, and watch a correction supersede the old dose:
The operational boundaries are strictly enforced within the prompt to guarantee safety and compliance:
- EMERGENCY OVERRIDE: If symptoms indicate a potential emergency, the FIRST sentence must direct the user to call 911 or seek immediate care.
- YOU PREPARE, THEY PRESCRIBE: Never instruct the user to start, stop, or alter a medication. Provide the exact questions for the clinician who holds that authority.
- NUMBERS BELONG TO THEIR CLINICIAN: Numeric thresholds appear only as quotes from this patient's record, attributed and dated. An invented threshold is a prescription in disguise.
- Maintain strict honesty regarding absent records; never invent a remembered fact.A properly designed second mind enhances the physician-patient relationship. It elevates the quality of the conversation rather than offering a competing medical opinion.
build it yourself
The complete system prompt — identity, memory doctrine, communication laws, research rules, safety boundaries, deployment notes — is yours: download the full prompt (markdown). It assumes only a persistent fact store, a search tool, and a date binding; the reference implementation runs on melchizedek’s long-term tier — config, memory pipeline, and schema all in the public repo. One non-negotiable: memory siloed per patient, deletable by the patient — a record this intimate belongs to the person it describes, or the agent shouldn’t exist.
Being heard, it turns out, has an architecture. It is someone who remembers what you said, connects what you couldn’t, and walks into the room already holding your questions. Most people never get that someone. Now you know how to build one.