Senior Care Coordinator AI Kit — 4 Ready-To-Use AI Agents for Coordinating Care for an Aging Parent

From AGENTORY — ready-to-use AI Task Kits. Drop in. Power up.

Works with the AI you already have. Upload one file, tell it "Start", answer a few questions — then keep one faithful, dated care record built only from what you supply, and turn it, on your word, into a prioritised appointment brief, a family update that says only what the record says, and a kept schedule of aides, services, and refills.

Four specialist agents that take the coordination work around a parent's care from scattered notes, printouts, and family messages to one record everything else is built from — running inside the AI you already use.

No new app. No subscription. These agents work with any AI chat — ChatGPT, Gemini, Claude, Copilot, whichever you have (free versions work).

How it works (about 5 minutes per agent, once):

1. Add the agent file to your AI chat — upload the .md file, or on a phone, open the .txt version, copy it, and paste it in.

2. Type "Start".

3. Answer the agent's questions, one at a time — the name you keep the record under, your parent's living situation in your words, the weekly pattern as it usually runs. That's the calibration, and it's what makes the record fit YOUR parent's care.

4. Save the complete updated Care Record each agent hands back to you — the agent keeps it current in the chat and returns it whole, never as pieces for you to assemble — and the next agent starts from your real record.

Use the agents in order:

1. Care Log Keeper — opens and keeps the record: your observations and reported events filed in your own words, dated and sourced, and documents filed exactly as supplied, with a verbatim check. When something differs from what is already on file, it flags the difference factually — "changed since [date]", both sides verbatim — and drafts the question for the clinician or pharmacist. It never interprets what it files.

2. Appointment Prepper — prepares one appointment at a time from the record alone, and captures it afterwards as you report it: the appointment facts as supplied, dated entries since the last visit in your words, the medication lists exactly as supplied, and a prioritised question list. It also files what the clinician said afterwards, only as you report it.

3. Family Updater — drafts family updates strictly from the record, for one named audience at a time: no reassurance added, no softening, and nothing private to one audience ever entering another audience's update. Shorter versions are made by selecting entries, never by re-wording a fact more gently — and you are shown what was left out.

4. Home & Services Coordinator — keeps the practical machinery: providers and services exactly as supplied, aide and service schedules exactly as stated, provider contacts, your week-at-a-glance, schedule exceptions, your own open coordination list, questions sheets for a provider you are considering, and refill reminders computed only from dates you supply. Scheduling and record-keeping only — it never contacts, books, moves, recommends, or vets anything.

One Care Record, nothing invented. All four agents work from the same shared Care Record — your calibration, dated log entries, documents on file, discrepancies and open questions, appointments, audiences, providers, exceptions, and your coordination list exist once, in one place. No brief, update, or week view may introduce a fact that is not in the record or supplied by you in that session. Anything missing is printed as "To confirm" — never completed from a pattern, never given a plausible date, number, or name.

The boundary, stated plainly — it is a design feature, not fine print. This kit organises records and drafts questions and updates — it does not give medical, care, legal, or benefits advice. No agent diagnoses, interprets a symptom or observation, judges whether a medication is working, advises starting, stopping, skipping, splitting, or changing any medication or its timing, assesses whether a home is safe enough, recommends or vets a provider, states anyone's eligibility for any benefit, or drafts, judges, or interprets a power of attorney, will, advance directive, or benefits application. Existing legal documents can be inventoried only — name, date, where the original is held, who holds copies, who is named — and nothing more. When something you describe sounds like immediate danger, an agent's first line tells you to call your local emergency number now. When it sounds like suspected abuse, neglect, self-neglect, or exploitation, or a legal-financial decision, the agent stops the current task, names the class of help generically, and prepares a facts-only escalation summary for you to carry — it never sends that summary, never drafts a message to the person concerned, and never concludes that abuse has occurred.

Medication lists, reproduced exactly — that fidelity is the point. A medication list you supply is reproduced exactly as supplied: names, strengths, doses, frequencies, prescribers, pharmacy, and dates, with no silent correction, no tidied name, no unit conversion, and no merging into a single "current list" — this kit has no merged list, by design. If two lists you supplied differ, both are shown verbatim, the differing fields are marked, and the difference becomes a question for the pharmacist or clinician — never the agent's call, and never resolved by picking the newer list. A flag closes only when you report the clinician's or pharmacist's answer and it is filed verbatim as their statement. Refill reminders are computed only from a refill date or supply interval you supplied, with the arithmetic shown — never inferred from a dose schedule.

Your parent is a third party — the privacy stance. Your parent did not buy this kit. The record is kept under the name you choose for your parent, and it holds only what you supply. The agents never contact your parent, your family, a clinician, a pharmacy, or a service on their own — the kit's one send workflow is yours: an exact text you approved, to one recipient you named for that update, only where that session's email route is verified. Keep the record where only the people you choose can see it: it holds another person's health information, and anything you paste into a chat is shared with that AI provider under that provider's terms. Every agent tells you this once, plainly, at setup.

Two ways to work — your choice, per session. Run an agent in a regular AI chat (ChatGPT, Gemini, Copilot) and it works as a guide: it creates and edits the complete deliverables right in the chat — the finished documents and complete updated files themselves, never outlines, edit lists, or pieces for you to assemble — and guidance is what covers the steps inside outside tools and accounts, which you perform yourself. Run the same file on an agentic AI — Muse, Claude Code, Devin, and similar — and it can do more where the platform genuinely allows: it can maintain your Care Record as a real file under git, create an event on your own calendar only, with no invitees ever, as the exact block you approved, and — the Family Updater only — send a family update as the exact approved text to one named recipient, only where a send route is verified in that session. Same agents, same rules — what changes is what your platform lets them do. You pick the mode every time; guidance is always available and always complete.

What "connected" means here — stated plainly, with the limits named. Email is draft-first: creating a draft is the standard route, and sending is claimed only after the session verifies a send action — a created draft is never described as a sent update. Google Calendar events carry the same kind of limitation: a route must verify in-session first, and events go on your own calendar only. Apple Calendar is guide-only on every platform: you receive the exact copy-ready event block and create the event yourself. No care platform is connected at all. There is no integration, sync, posting, or checking with CaringBridge, Lotsa Helping Hands, CareZone, Medisafe, or any pharmacy app — the agents prepare the text or entries, and you paste or enter them yourself. Any line implying this kit syncs with your care apps would be wrong, and no agent in this kit will make that claim.

Not sure what your AI can actually do? Each agent starts by telling you which platform it is running on and what it can really do in this session — its actual tools, not the brand name. The kit also includes a short, plain-language guide to AI limitations, with a dated annex listing which platforms can act and which only guide, and what each can really do with this kit's tools — so you always know where you stand.

A realistic first session: with the Care Log Keeper you answer its 8 questions one at a time and reach the first milestone in about 10 minutes: the record opened — its cover page, the weekly pattern in your words, anything missing shown as "To confirm" — plus one faithful entry filed, dated and sourced (verbatim-checked if it is a document). That is the first session — not a finished care system. Briefs, updates, and week views come step by step after that, from the record you build.

The worked example: the materials walk one complete example end to end — Claire, coordinating care for her father Robert, 82, kept in the record as "Robert (Dad)" — so you can see every format before you build your own: two medication lists that differ in two places, both kept verbatim with both differences drafted as questions; a dated entry in Claire's own words, filed uninterpreted; an appointment brief built from those materials; a family update that reports the record without softening it; and a week view with a refill reminder computed from a date Claire supplied. Your parent's record gets your own material; the example is there to show the shapes. Claire and Robert are a fictional example family created for this kit — not a customer story.

What's inside:

- 4 agent files, each in .md AND .txt format (identical content — one of them always works on your device, phone included)

- My Care Record — fill it in once (agents help you), paste it into any new chat, skip the interviews; it is the kit's single source of truth: your calibration for all four agents, plus the registers the agents maintain — entries, documents, discrepancies, open questions, appointments, audiences, providers, exceptions, your coordination list, the escalation record, the document inventory, and update history

- Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases, the escalation phrases, and the phrase that closes a discrepancy on a clinician's or pharmacist's reported answer

- AI Limitations Disclaimer (.md + .txt) — what AI can and cannot do, in plain language, with this kit's tools as the examples and a dated capability annex

- A step-by-step README that gets you running in minutes

- Troubleshooting & FAQ — a list that came back "tidied", a paraphrased observation, a family member asking for a softer update, a chat that cannot send: the known rough edges and their fixes

- Changelog — what changed in this version

Who it's for:

- Adult children coordinating care for an aging parent — keeping track of visits, calls, aide schedules, appointments, medication lists, and family updates across several people

- Coordinators whose parent's paperwork comes from more than one place — a pharmacy printout, a clinician's office list, discharge papers — and who need differences surfaced plainly instead of quietly harmonised

- Anyone who wants family updates that say what the record says: dated, sourced, separated by audience, with nothing private to one person carried into another person's update

Who it's NOT for:

- Anyone looking for medical, care, legal, or benefits advice, a care service, a medical record, or software that contacts providers or family for them — this kit is instruction files for your AI, plus the record work you direct and check

- Anyone who wants an agent to decide which medication list is right, whether a symptom matters, or whether something can wait — those questions are drafted for the clinician or pharmacist, exactly and with the record quoted, and answered by them

- Anyone who wants the record to make a difficult update sound gentler than the facts — a topic can be left out of an audience's update as your editorial choice, with the omission shown to you; a fact an update does cover is never re-worded to land more gently

What you need:

- An AI chat account of your own (ChatGPT, Gemini, Claude, Copilot, or any other — free versions work for the guided work)

- Your own material — your notes in your words, the documents you were handed, appointments as given to you, schedules as they run; the agents use only what you supply, and infer nothing

- A private place to keep the saved Care Record — it holds another person's health information, and only the people you choose should be able to see it

Honest limits:

Each agent is a text instruction file for your existing AI — it is not a trained AI model, not a separate app, not a care service, and not a medical record. What it can do depends on where you run it: in a chat-only AI it guides and drafts — creating and editing the complete deliverables right in the chat — and you perform only the actions inside your outside tools and accounts; on an agentic AI it can act through the tools you choose to connect — always showing you the exact action first, always with your approval before anything is sent, and never unattended. Connections are made through your platform's own secure sign-in and key flows — the agents never ask for, receive, or store a password or secret key, and a secret pasted into a chat gets one answer: change it now. Mode honesty holds throughout: in Connected mode the record is kept as a file under git so a change can be rolled back; calendar work is an approved, invitee-free event on your own calendar where a Google Calendar route verifies, and a copy-ready block everywhere else — always for Apple Calendar; a family update is sent only as the exact approved text, to one named recipient, only where a send route verifies in that session, and a draft is never reported as a send. No care platform is integrated in any mode. The kit's boundary holds in both modes: records are kept exactly as supplied, discrepancies become questions and are never resolved by an agent, updates are never softened, audiences never cross, and escalation summaries are prepared for you to carry and are never sent by an agent. The one finding route printed in this kit is the US Eldercare Locator, named in the agents and the disclaimer for US buyers; outside the US the agents name the class of help only. The agents' worked example, Claire and Robert, is an illustration created for this kit to show the formats end to end — not a customer story. You check every output before you rely on it.

One honest expectation: this kit is a plain-text instruction file, and it loads in any AI you already use — but the AI you run it on sets the quality. The agent's rules, questions, and output formats are fixed in the file; how deeply and consistently your AI follows them depends on your model and on how much it can hold in one session, so a weaker or free-tier model may shorten, skip, or drift where a strong current model stays exact. AI tools, models and context lengths all affect the final results — and trying different tools may help you find the best one for your needs; the same file, unchanged, often does better on a stronger model. The full disclaimer in your download explains this properly and shows how to get the best from whatever AI you have.

Price: $19 — Standalone: all 4 agents, everything included.

Starters (ONE agent, your choice of any of the 4) are $9 each — separate listings below. Starter owners complete the set with the Upgrade, $10 — the difference.