New Parent Coordinator — AI Task Kit (4 Agents)

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 Baby Book built only from what you state and supply, and turn it, on your word, into a gated Weekly Log Summary that only counts your log, a Care Brief that carries only your own instructions, an Appointment Prep Sheet that answers nothing, and family updates drafted per audience from the record only.

Four specialist agents that take your baby's scattered first months — a visit summary in a drawer, feed times in a notes app, caregiver instructions rewritten from memory, family updates retyped for every grandparent — to one faithful Baby Book 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 (once per agent):

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 — your baby recorded as you state her, your contacts exactly as you supply them, your documents exactly as you paste them, your instructions in your exact words. That's the calibration, and it's what makes the Book fit YOUR baby.
4. Save the complete updated Baby Book 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. Baby Log Keeper — the flagship; opens and keeps the Book: the parents and baby as you state them, the pediatrician and emergency contacts exactly as you supply them, the caregivers as you state them, and the daily log — entries verbatim, dated, times as stated, corrections as new entries, and the Weekly Log Summary as counts only, with their parts shown, never a reading of the week. It runs the Weekly Log Summary Check (GATE-LK).
2. Appointment & Questions Prepper — the Book's appointment desk: documents you paste filed verbatim and complete, your questions for the pediatrician kept verbatim and unanswered, appointments only as you state them, clinician answers only as you report them, your own notes verbatim and dated, and conflicts flagged with both sides standing. It runs the Appointment Prep Sheet Check (GATE-AP).
3. Care Brief Builder — builds the Care Brief for a caregiver, only from recorded facts and your own stated instructions: feeding, settling, and contact instructions in your exact words, and a medication section that prints only an instruction you yourselves stated — or "not recorded — ask the parents." It runs the Care Brief Check (GATE-CB).
4. Family Updater — drafts one update per family audience, from the record only: each audience gets its own draft under its own instructions, audiences never cross, and no draft characterises your baby's health or progress in either direction. It runs the Family Update Check (GATE-FU).

One Baby Book, nothing invented. All four agents work from the same shared Baby Book — the parents and baby as stated, contacts and caregivers, the daily log and its corrections, documents on file, questions, appointments, reported answers, notes, conflicts, care occasions and your own instructions, brief and update statuses as you report them, audiences, and the change log exist once, in one place. No summary, brief, sheet, or update may introduce a fact that is not in the Book or supplied by you in that session. Anything missing is printed as "To confirm" or "not recorded" — never completed from a pattern, never given a plausible date, number, name, or amount.

The boundary, stated plainly — it is a design feature, not fine print. This kit keeps records; it is not medicine, and it is not baby-care advice. It does not diagnose, does not interpret a symptom or a concern, and does not advise on medication, feeding amounts or schedules, sleep, or development of any kind — no starting, stopping, repeating, skipping, or changing anything, no dose in any form, no "what's normal," no milestone verdicts, reassuring or alarming. It is records, not a medical service: not a doula, nanny, or health-visitor service, not a tracker app, not a booking or messaging service, and not a prompt pack. A document you paste — a clinic visit summary, for example — is filed verbatim and stays a record: its printed medication/vitamin line is reproduced only inside that document and is never turned into an instruction, a schedule, a reminder, or an answer to any question, in any output, including the care brief. A worry you want answered becomes a question drafted for your pediatrician, quoting the recorded facts it rests on, and filed unanswered — never accompanied by the kit's own suggested answer. When your own words describe a possible emergency, the agent files your entry verbatim and, in the same output, puts your words, the recorded facts they rest on, and your recorded contacts — your pediatrician's and emergency contact's numbers exactly as you supplied them — in front of you, and directs you to contact your pediatrician, urgent care, or emergency services now. It offers no judgement about how serious anything is, in either direction — no alarm and no reassurance — and it makes no contact itself. One verified official line — US Poison Control, named here for poisoning help only — is printed in the Book's contacts in its own labelled block, separate from your supplied contacts, and in that same labelled form in a care brief's contacts and in an escalation only where poisoning is the subject. It appears in no other output: never in a log summary, never on a prep sheet outside that scoped escalation, and never in a family update.

Documents and care facts, reproduced exactly — that fidelity is the point. Your log entries stand in your exact words, times as stated — never merged, paraphrased, or read as a pattern. Your instructions stand verbatim — a log pattern is never restated as something a caregiver is to do. A pasted document stands exactly as pasted — every line, never tidied, shortened, re-ordered, or "cleaned up." Where two recorded facts disagree, both stand, flagged, in every output that touches them: never reconciled, never averaged, never silently preferred because one is newer. An appointment exists only as you state it — never derived from a document, a typical schedule, or your baby's age. A brief's status, an update's status, is what you last reported, dated to your report — a care occasion having arrived settles nothing.

Completeness is checked, by name — and "just the highlights" does not waive it. Each of the four major deliverables carries its own named check, run before it is presented as finished, with the result printed on it: the Weekly Log Summary Check (GATE-LK), the Appointment Prep Sheet Check (GATE-AP), the Care Brief Check (GATE-CB), and the Family Update Check (GATE-FU). A section carrying its honest gap in place — "not recorded," "To confirm," "not recorded — ask the parents" — passes with the gap printed: a printed gap is the kit working. A gap filled by invention, a gap hidden, or a section missing fails the check by name, with the failing sections listed. If you ask for "just the highlights" or "just the short version," the check still runs: the only shorter artefact available is a separate extract labelled as an extract that failed its named gate, with the gaps named — never the deliverable itself, however often the request is repeated.

Your baby's people are third parties in this record — the privacy stance. Your baby cannot supply her own record, and the Book also holds facts about other people — your emergency contact, your caregivers, family members — all supplied by you. The Book holds only what you supply, exactly as you supply it. The agents never contact your pediatrician, your caregiver, or anyone else on their own — this kit sends nothing, in either mode. Share the Book by part: a caregiver receives the Care Brief, not the whole Book. Keep the Book where only the people you choose can see it, and remember that 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 Baby Book as a real file under git, or as a Google Doc where that route verifies 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. Drafts are the ceiling: no agent in this kit sends anything, in either mode — no send tool exists in this kit. Where a Gmail route verifies in-session, two agents only may each create their own drafts in your own Gmail drafts, on your approval of the exact text: the Care Brief Builder's draft carrying the gated Care Brief, and the Family Updater's draft carrying one audience's approved update — one audience per draft. A created draft is never described as sent — you send it yourself from Gmail. Calendar holds belong to the Appointment & Questions Prepper only: your own calendar only, no invitees ever, for appointments you stated only, each hold's title and date exactly as you stated them — a hold is not a booking with your clinic. That same stated-appointment list, and only that list, may be mirrored to Todoist on your approval; the Book stays the source of truth. Apple Calendar is guide-only on every platform: you receive the exact hold as finished text and add it yourself. No baby-tracker app, clinic, or health platform is connected at all. There is no integration or sync with any tracker app or clinic portal — records from an app enter the Book only as text you paste in yourself, filed as pasted text, and no agent in this kit will claim otherwise.

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 Baby Log Keeper you answer its questions one at a time and reach the first milestone in about 10 minutes: the Book opened — the opening record checked by GATE-LK, your facts and contacts exactly as you stated and supplied them with their gaps printed — plus one faithful first filing, demonstrated live: paste in one real document, for example a visit summary, and receive it back filed word-for-word, with its medication/vitamin line kept as a record inside the document only; state one of your own notes that disagrees with it, and the conflict is flagged with both figures standing rather than settled. That is the first session — not a finished baby-care system. Briefs, sheets, summaries, and updates come step by step after that, from the Book you build.

The worked example: the materials walk one complete example end to end — Hannah and Ben, first-time parents, and their baby Ella (Hannah, Ben, and Ella are a fictional example created for this kit — not a customer story) — so you can see every format before you build your own: a Book opened on Monday 2027-02-15 with the parents' and baby's facts as stated and the contacts as supplied, gaps printed; one pasted document, the clinic's visit summary of Friday 2027-02-12, reproduced verbatim — it prints Ella's weight as 4.9 kg, and it prints exactly one medication/vitamin line, which stays a record inside that document and appears on no brief; Hannah's own later note of Wednesday 2027-02-17 (Hannah is fictional, as above), "about 5.2 kg" — so both weights stand, flagged, neither averaged nor preferred, and no combined figure is ever computed as Ella's weight; her concern of Thursday 2027-02-18 filed verbatim, dated, uninterpreted, with the escalation shape issued in the same output and no severity wording either way; a Care Brief for Diane for Saturday 2027-02-20 (Diane is a fictional character in the same example) whose medication section prints "not recorded — ask the parents," because Hannah and Ben (fictional, as above) stated no instruction themselves; an Appointment Prep Sheet for Monday 2027-03-01 carrying their 3 filed questions verbatim and unanswered; a Weekly Log Summary for Monday 2027-02-15 to Sunday 2027-02-21 — all 7 days verbatim, feeds, sleep ranges, and diaper entries counted with their parts shown (56 / 59 / 59), and no reading of the week added; and a Family Update Pack drafting separately for Diane and for Margaret (both fictional characters in the same example), each under her own register instruction, neither draft carrying the other's material. Your baby's Book gets your own material; the example is there to show the shapes.

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 Baby Book — 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 — the change log, the source index, conflict flags, gate results, the "To confirm / not recorded" list, the draft log, and the escalation log
• Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases for draft creation, calendar holds, and the Todoist mirror — and the plain statement that no approval phrase for a send exists, because the kit sends nothing
• 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 log summary that came back with a pattern label, a document that came back tidied, a brief carrying document wording as an instruction, a draft reported as sent, a chat that cannot create a draft: the known rough edges and their fixes
• Changelog — what changed in this version

Who it's for:

• New parents whose baby's first months are scattered — a visit summary in a drawer, feed times in a notes app, caregiver instructions rewritten from memory — who want one faithful record they can answer from, in exact words
• Parents whose baby's paperwork comes from more than one place and who need differences surfaced plainly, both sides standing, instead of quietly harmonised into one tidy figure
• Anyone handing their baby to a caregiver who wants the brief to carry only recorded facts and their own stated instructions — with every gap printed as "not recorded — ask the parents" instead of filled in helpfully
• Anyone drafting updates for family who wants each audience's update kept separate, under its own instructions, with nothing characterised in either direction

Who it's NOT for:

• Anyone looking for baby-care or medical advice, a diagnosis, a symptom reading, medication or feeding guidance, a medical service, a tracker app, or software that contacts a clinic or caregiver 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 recorded weight is right, whether a symptom matters, what a baby should eat or be given, or what is normal for a baby's development — those questions are drafted for your pediatrician, exactly and with the record quoted, and answered by them
• Anyone who wants a pasted clinic document turned into instructions for a caregiver — a document's printed line is a record, and only an instruction you state yourself, in your own words, can ever appear on the brief

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 baby as you state her, your contacts as you have them, the documents you were handed exactly as you have them, your instructions in your exact words; the agents use only what you supply, and infer nothing
• A private place to keep the saved Baby Book — it holds facts about your baby and about other people, 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 medical service, not a tracker app, and not a baby-care or medical record for your baby. 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 created, 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 Book is kept as a file under git so a change can be rolled back, or as a Google Doc where that route verifies; Gmail work is draft creation only, by two agents for their own drafts only, and no send tool exists in this kit; calendar work is an approved, invitee-free hold on your own calendar, for appointments you stated only, by the Appointment & Questions Prepper only, where a Google Calendar route verifies — and a copy-ready hold everywhere else, always for Apple Calendar; the Todoist mirror copies that same stated-appointment list and originates nothing. No tracker app, clinic, or health platform is integrated in any mode. The kit's boundary holds in both modes: records are kept exactly as supplied, documents are never turned into instructions, conflicts stand flagged and are never resolved by an agent, appointments exist only as you state them, statuses change only on your dated report, and escalation puts your recorded facts and your recorded contacts in front of you and directs you to your pediatrician — it never contacts anyone and judges nothing. The kit's agents use only the fictional worked example named in this listing 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.