The Teacher's Desk AI Kit — 4 Ready-To-Use AI Agents for Lesson Plans, Worksheets, Feedback & Parent Messages From Your Own Materials Only

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 plan lessons against the standards you supply, build worksheets and quizzes from your source only, write feedback from your own notes, and draft parent messages without ever inventing a student detail.

Four specialist agents that run your weekly paperwork cycle — plan, practise/assess, feedback, parent contact — inside the AI you already use, from your own materials only.

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 — your classes, your materials, your rules. That's the calibration, and it's what makes every output yours.

4. Save the complete updated My Classroom Profile 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 classroom.

Use the agents in order — the weekly cycle:

1. Lesson Planner — plans whose alignment lines quote ONLY standards you supplied, character-for-character, with the code as you supplied it. Where a needed standard was not supplied, the plan says so — "Not supplied, so not claimed" — instead of filling the gap with a plausible-looking invention. Every plan's timings are printed and sum exactly to your period length.

2. Worksheet & Quiz Builder — worksheets and quizzes (with answer keys) in which every question and every key answer traces to the source text or lesson content you supplied — and it prints the source-trace check so you can see it. A fact that is common knowledge but not in your source stays out.

3. Feedback Writer — report-card comments and assignment feedback built only from your per-student notes and marks. It never adds a behaviour, achievement, incident, or trait you did not record — and two students with identical notes get comments of identical substance, because the agent has nothing else to work from and will not manufacture a difference.

4. Parent Comms — parent drafts in your voice: straightforward drafts for routine matters, careful fact-only drafts for sensitive ones, and no draft at all for legal, safety, custody, or child-protection matters — those get an escalation summary for your admin instead. Another student is never named or described in any draft, ever.

Students are worked with by initials or codes only — that is a feature of this kit, not a setting. No agent asks for a surname, student ID, photo, or date of birth. If extra identifying detail arrives inside something you paste, the agent flags it and works with the minimum.

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: if you want, it walks you through connecting your own tools, and then carries out the steps itself, showing you each consequential action for your approval first, verifying as it goes. Same agent, same rules — what changes is what your platform lets it do. You pick the mode every time; guidance is always available and always complete. Connected mode in this kit is real only for the teacher's own tools: the Planner and Feedback Writer stay advisors (Connected mode improves their inputs — they read what you point them to and deliver drafts for you to save), the Builder can save a finished worksheet or key into a document or file you control, and Parent Comms can send — through your own connected Gmail — only the exact draft you approved, one email at a time.

Google Classroom and Microsoft Teams — the plain truth: there is no turnkey route by which these agents post to Google Classroom or to Microsoft Teams for Education, on any AI platform. The kit drafts; the teacher distributes. The agents prepare coursework text, announcements, worksheets, and keys ready to paste or upload in seconds, and you post them. (The one narrow exception the kit itself states: if you have already built Google's Developer Preview / MCP setup yourself and an agent's session check shows live Classroom tools, Connected mode may use them with your approval of each action — the setup was yours, not this kit's. Teams is guide-only in all cases.)

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 Lesson Planner you paste one standard from your own curriculum document and your lesson outline, answer the calibration, and get a plan whose alignment block quotes your standard exactly — plus a visible "To confirm" list for anything you have not supplied yet. That gap list is a feature, not a failure: it is what an invented alignment would have hidden.

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 Classroom Profile — fill it in once (agents help you), paste it into any new chat, skip the interviews; it is the one record every agent works from: your classes and setup, your standards register, your planning rules, your assessment spec and build log, your feedback stance and notes register, your parent-comms facts and log

- Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases

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

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

- Troubleshooting & FAQ — a standard cited that you didn't supply, identical comments, "why won't it post to Classroom?", cut-off pastes, free-tier limits: the known rough edges and their fixes

- Changelog — what changed in this version

Who it's for:

- Classroom teachers (the kit's worked examples follow a grades 4–10 paperwork cycle) who plan against a curriculum they are accountable to, and need the alignment to be real

- Teachers building worksheets and quizzes who need every key answer to trace to the material they actually taught from

- Teachers writing report comments and parent messages for a full class, who cannot ship a detail they didn't observe

Who it's NOT for:

- Anyone who wants a built-in curriculum library — this kit ships no standards for any country, state, or province, by design, and no agent will reconstruct one from memory

- Anyone who wants an agent to post to Google Classroom or Teams for them, or to contact students or parents directly — there is no turnkey route, and the agents never contact students or parents on their own

- Anyone who wants feedback or a parent draft decorated with plausible detail — every agent in this kit refuses that, at any insistence, in both modes

- Anyone who wants advice on discipline outcomes, custody, child protection, or legal matters — those are escalated to your admin, never advised on

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 curriculum documents, source material, and per-student notes and marks — the kit works from what you supply, and from nothing else

- Your school or board's own approved tools and policies for student-related material — this kit's minimisation is a cautious default design, not legal advice, and it does not make any chat "compliant" with any law

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 curriculum library, and not a learning management system. 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, published, deleted, or spent, 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. File work done for you runs through git, so a failed step rolls back to the last verified one; actions that leave your systems (a sent email) can't be undone, which is why they're approved one by one. This kit's spine holds in both modes: no standard, code, or expectation is ever cited unless you supplied its text, quoted exactly, and jurisdictions are never blended; no question or key answer carries a fact that is not in your supplied source; no behaviour, achievement, incident, or trait is ever attributed to a student beyond your own notes and marks for that student; students are referenced by initials or codes only; another student is never named or described in parent-facing text; and legal, safety, custody, and child-protection matters produce an escalation summary, never a parent draft. Two more limits specific to this kit: no turnkey Classroom or Teams posting, ever — the kit drafts and you distribute (see the plain-truth section above for the one narrow, self-built-setup exception for Classroom); and no grader of record — the Builder makes keys from your sources, and marking help uses only marks and answers you supply. The agents' worked examples follow one illustrative teacher created for this kit to show the formats end to end — an illustration, not a customer story. You check every output before it reaches a student, a parent, or a record. Nothing in this kit promises anything about grades, inspections, parent satisfaction, or time saved.

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.