Podcast Producer Studio — AI Task Kit (4 Agents) — Starter: Show Notes Writer

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

One agent from the Podcast Producer Studio kit — complete, nothing cut down. Not a blank template and not a prompt pack: this agent fills your Show Book with your own facts and pasted material, 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 podcast-production agent — filling a faithful Show 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 Show Notes Writer is the Book's notes desk (3 calibration questions): what show-notes format you state — the sections you want, in your exact words — or "none recorded", a format that governs layout only, never content, and never creates a timestamp; for each show-notes draft, what status you are reporting, in your words, and on what date — also the standing question for every later status report; and, for each episode, each link or credit pasted exactly as you have it, or "none supplied" — a URL is never guessed, shortened, completed, or "corrected". Its show-notes package for one episode is built under a claim-trace gate: every factual line traces to a named recorded source in the Book, and anything the recorded material does not carry goes to the package's gap list, not into the notes. The package runs a named completeness check (GATE-N) before it is presented as finished: all nine sections present at substance — the episode header (number, title as stated, show title, release date as recorded with its weekday derived); the description traced line by line to the recorded material; quotes reproduced character-for-character as the material carries them; timestamps only where the material carries them, in the material's own form — never estimated, interpolated, or rounded; the guest section carrying the guest's identity as stated and bio verbatim as pasted, never strengthened; any conflict flagged in place, with no disputed fact stated as the episode's fact; the sponsor disclosure section as your recorded disclosure line verbatim, or "none recorded"; links and credits only as pasted; and no audience, download, or listener figure anywhere. A thin package fails GATE-N by name, with its gaps listed — insistence does not waive the check. In the kit's worked example, Ruth's Ep. 12 package — Ruth is a fictional example persona, labelled as such wherever she appears — is for "The Ferry Landing at the Foot of Main Street", releasing Friday 2027-05-14, with its notes due Monday 2027-05-10, 4 days before release: it carries exactly the 2 timestamps her pasted notes carry — at 00:14:20 Dr. Ortiz said: "The last ferry crossed in 1963, and half the town came down to watch it go." (the package's one verbatim quote, reproduced exactly as her notes carry it), and at 00:31:05 Ruth reads the 1958 ferry timetable aloud, with no sailing time or fare stated anywhere because her notes do not print them; it flags the standing conflict in place — her pasted outline states ferry service ended in 1962, the quote above states 1963, both standing, neither asserted as the episode's fact; it prints Dr. Ortiz's bio verbatim as pasted — "Dr. Lena Ortiz is curator at the Harborview Museum, where she oversees the maritime collection. She grew up two streets from the ferry landing."; it prints her recorded disclosure line verbatim — "Support for Main Street, Remembered comes from Harborview Books on Main Street."; and it prints no audience figure, because none exists in her Book and none was pasted from her host dashboard. For Ep. 13, which has no recorded material, this agent produces no show notes at all. This agent creates no Gmail draft, sends nothing, publishes nothing, and performs no podcast-platform act in either mode — its deliverable is the gated show-notes package, a document you publish yourself. If the Book's cover fields are missing, this agent names them and sends you to the Show Planner first — the Show Planner opens the Book every other agent reads. You need: the Book opened first (the Show Planner, full kit / Upgrade, opens one — or bring a Show Book you already have), recorded material for the episode, and any links or credits pasted exactly as you have them.

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 show.
4. Done — ask for what you need.

This kit builds and keeps a Show Book from your own facts and pasted material — it sends nothing, publishes nothing, uploads nothing, produces no audio, books no guest, secures no sponsor, corrects no pasted material, resolves no conflict, creates no timestamp, strengthens no guest bio, and claims no audience, download, listener, or ranking figure anywhere. 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, dates, statuses, and texts are recorded only as you supply them, and a credential, figure, date, timestamp, 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 Show 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 Show Book holds your show texts and guest information you supply, including guest contact details — held in the private Book only, never printed in any deliverable or draft, and shown outside the Book only as an existence state ("recorded — private" / "none recorded"). 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 sends anything in either mode. No agent in this kit performs a podcast-platform act in either mode: on Podbean, Descript, and every other host or editor alike, platform steps are checklists you execute yourself from the gated documents — Podbean's official MCP route and Descript's official API + MCP route both exist (capability annex checked 2026-10-31, with their limits named in the full listing and the kit's disclaimer) and are not used by this kit; Google Calendar's route exists and no calendar act is designed; every other host checked is guide-only or 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 booking 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 Show Book — the full Book (23 fields, F01–F23); 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 (checked 2026-10-31)
• 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 Show 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 podcast host, and not a human production service. Prompt packs for this work exist cheap, and generic podcast prompts are easy to find free; blank show templates are easy to find too. What this adds is the Book those products never build — filled only from your facts and pasted material, its timestamps held only where the material carries them, 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 Show Book that no output may contradict, facts recorded only as you supply them, unknowns printed as "To confirm", pasted material exactly as pasted and never corrected or tidied, conflicts flagged and never resolved by the kit, timestamps only as the material carries them, guest bios verbatim and never strengthened, sponsor content only as your recorded disclosure line verbatim, no audience, download, listener, or ranking figure ever invented or claimed, no legal advice given, 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.