Course Creator Studio — AI Task Kit (4 Agents) — Starter: Lesson Writer

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

One agent from the Course Creator Studio kit — complete, nothing cut down. Not a blank template and not a prompt pack: this agent fills your Course Book with your own facts and pasted sources, gates its deliverable by name, and keeps that record current when your facts change. Works with the AI you already have: upload the file, tell it "Start", answer a few questions, and get to work.

One specialist course-building agent — filling a faithful Course Book, not handing you a blank template — running inside the AI you already use.

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

The Lesson Writer is the Book's drafting bench (2 calibration questions): for each lesson, what drafting notes you state for it, in your exact words — or "none recorded", notes that are your instructions about your lesson and never supply subject content the mapped source does not carry; and, for each lesson draft, what status you are reporting (draft / approved / needs changes — in your words) and on what date you are reporting it, the standing question for every later status report. Its lesson draft is built only from the source or sources mapped to that lesson in the Book, under a claim-trace gate: every substantive line traces to a mapped source, and anything the sources do not carry goes to the draft's gap list, not into the lesson. The draft runs a named completeness check (GATE-L) before it is presented as finished: the overview traced to the mapped source; the steps complete from that source, in its order, with none added, dropped, or reordered; the figures exactly as printed; the common-mistake section present, source-only, or declared absent in its exact form — "none in source — not supplied"; the check-for-understanding answerable only from the lesson's own content; and the gap list present. A lesson with no mapped source is never drafted: it is listed as source-needed until you supply and map a source, and a request to write it from general knowledge is refused. A thin draft fails GATE-L by name, with its gaps listed — insistence does not waive the check. In the kit's worked example, Elena's Lesson 1.2, "Feeding and Keeping Your Starter" — Elena is a fictional example persona, labelled as such wherever she appears — is drafted only from its mapped source: six steps reproduced in full, in source order; the feeding ratio 1:2:2 and the schedule twice daily exactly as printed (a request to "fix" the ratio to the one everyone else uses is refused — common practice is not a source); its common-mistake section printing "none in source — not supplied", because the mapped source carries no such note; its check questions answerable only from the lesson itself; and a gap list that includes the flagged, unresolved conflict between her two sources on a figure this lesson does not print, rather than borrowing a figure from another lesson's source. This agent creates no Gmail draft, sends nothing, publishes nothing, and performs no course-platform act in either mode — its deliverable is the gated lesson draft, a document you place yourself. If the Book's cover fields are missing, this agent names them and sends you to the Course Architect first — the Course Architect opens the Book every other agent reads. You need: the Book opened first (the Course Architect, full kit / Upgrade, opens one — or bring a Course Book you already have), and a mapped source for each lesson you want drafted.

How it works (one question at a time, 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. That's the calibration, and it's what makes the output fit YOUR course.
4. Done — ask for what you need.

This kit builds and keeps a Course Book from your own facts and pasted sources — it sends nothing, publishes nothing, uploads nothing, corrects no source figure, resolves no conflict, invents no student, result, income figure, or testimonial, and upgrades no promise. That boundary is part of the design of every agent in this kit, in this Starter as much as in the full kit: facts, figures, statuses, and notes are recorded only as you supply them, and a credential, figure, date, or claim you have not supplied is printed as "To confirm" or "not recorded" — never invented, never estimated, never completed from a pattern.

This is the Starter edition: ONE agent, complete — the same file as in the full kit, nothing cut down. It includes the shared Course Book (fill it once, paste it into any new chat, skip the interview), a prompt sheet with the exact phrases for this agent, a plain-language guide to what AI can and cannot do, and troubleshooting help.

Your Course Book holds your course texts and, later, student questions you supply — other people's information. The agents never publish, post, or share your Book, and passwords, account numbers, payment details, API keys, and identity-document numbers are never recorded in the Book at all. Keep the Book where only the people you choose can see it, and share only the part a person needs.

Two ways to work — your choice, per session. Run this 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: the Book kept as a file under git, with a commit before the first edit and one per verified step. This agent creates no Gmail draft in either mode, and no agent in this kit performs a course-platform act in either mode: on Teachable, Thinkific, Podia, Gumroad, and Payhip alike, platform steps are checklists you execute yourself from the gated documents — Teachable's official route is experimental, limited, and Claude-only with lesson creation not verified; Thinkific is guide-only; Podia's route carries actions that cannot be undone; Gumroad's route is Claude-only and product-based rather than lesson-based; Payhip has no route. Same agent, same rules — what changes is what your platform lets it do, and the agent verifies its actual in-session tools at the start of every session, because brand is not a guarantee and plans change; the in-session check governs. You pick the mode every time; guidance is always available and always complete. Every message is draft-only in both modes, and no send, publish, upload, or enrolment route is claimed for any platform.

What's inside:

• The one agent, in .md AND .txt format (identical content)
• Prompt Sheet for this agent — the exact phrases for every job
• My Course Book — the full Book; the sections for the other agents are already in it, so upgrading later means no new setup
• AI Limitations Disclaimer (.md + .txt), with the dated capability annex
• Starter README — step-by-step setup
• Troubleshooting & FAQ

What you need:

• An AI chat account of your own (free versions work for the guided work)
• Agent-specific notes are in the per-agent paragraph above

Want the rest of the set later? The other three agents complete the kit (Standalone, $49). Starter owners upgrade for $30 — the difference — and the Course Book you fill in here already covers the other agents, so there is no new setup.

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 course platform, and not a human course-building service. Prompt packs for this work exist cheap, and generic course prompts are easy to find free; blank course templates are easy to find too. What this adds is the Book those products never build — filled only from your facts and pasted sources, its figures held exactly as printed, its conflicts flagged and left standing, its deliverable gated, and the record kept current when your facts change — not a blank template or a bundle of prompts. 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 agent never asks for, receives, or stores a password, API key, or login, and a secret pasted into a chat gets one answer: change it now. This kit's spine holds in both modes: one shared Course Book that no output may contradict, facts recorded only as you supply them, unknowns printed as "To confirm", source figures exactly as printed and never corrected or averaged, conflicts flagged and never resolved by the kit, the recorded promise never upgraded, no student, result, income figure, or testimonial ever invented, statuses changed only on your report, and each main deliverable passing its named completeness gate against the recorded Book — a "just the highlights" version is labelled as an extract that failed the gate, never as the deliverable. (Agent-specific limits are in the per-agent paragraph above.) 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 — Starter: ONE agent, your choice.