Podcast Producer Studio — AI Task Kit (4 Agents)

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

Not a prompt pack, not a podcast host, and not a blank template — a filled, faithful Show Book: your bio and show description recorded exactly as you state them, your outlines and recorded material reproduced exactly as you pasted them, your timestamps only where your material carries them, your guest bios verbatim and never strengthened, your sponsor disclosure only as your recorded line verbatim, and every deliverable gated by a named completeness check, kept current every time a fact changes. No audience, download, or listener figure is claimed anywhere in this kit — a figure exists only where you paste one from your own dashboard, attributed and dated, reproduced exactly. Works with the AI you already have: upload one file, tell it "Start", answer a few questions, and the Book starts filling with YOUR show, your episodes, and your dates.

This is not a prompt pack, not a blank template, and not a podcast host or distributor. Four specialist agents fill one Show Book with your facts — your bio exactly as you state it, your show title, description, format, cadence, tone, and subject scope exactly as you record them, your episode pipeline and release dates exactly as you state them, your outlines and recorded material exactly as you paste them — build production sheets and show-notes packages only from the material recorded for that episode, under a claim-trace rule, check each deliverable against a named completeness gate, and keep the whole Book current when a release date is reported moved, material is added, or a status is reported. Nothing in the Book is invented, no pasted material is corrected or tidied, no conflict between your own materials is resolved, no timestamp is created, and nothing leaves it as a send or a publish. "Producer" in this kit means production records and drafts from your material: the kit produces no audio, books no guest, and secures no sponsor. A blank template holds whatever you type, errors included, and checks nothing; a bracketed prompt holds none of your facts and enforces no rule. This kit is the other thing: the Book is built — from your material, with its claim-trace gate applied to every sheet, package, and draft.

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 (one agent 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 — your bio exactly as you state it, your show exactly as you record it, your outlines and material pasted exactly as you have them, your guests as you state them and their bios as you paste them, your sponsor disclosure line exactly as you recorded it. That's the calibration, and it's what makes the Book fit YOUR show.
4. Save the complete updated Show 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 show and material.

Use the agents in order:

1. Show Planner — the Book's front door, and the kit's lead agent (the flagship Starter). It opens the shared My Show Book, owns your host record and show record (name, bio, title, description, format, cadence, tone, and subject scope, all as stated), the episode pipeline and release dates as stated, and pipeline-level conflict flags — material reproduced exactly as pasted, and where two of your own materials disagree, both standing with the conflict flagged, never resolved. It runs GATE-P. It creates no Gmail draft, and it performs no podcast-platform act of any kind.
2. Episode Producer — the Book's production bench. It builds a per-episode production sheet only from that episode's recorded outline, recorded material, and production record: dates as stated with weekdays derived and intervals recomputed, material coverage counted from the pasted text with its parts shown, and gaps listed on every sheet. An episode with no recorded material gets no sheet beyond its recorded row — not from the model's own knowledge, not at any level of insistence. It runs GATE-S. It creates no Gmail draft, produces no audio, and performs no podcast-platform act of any kind.
3. Show Notes Writer — the Book's notes desk. It builds one episode's show-notes package under claim-trace: every factual line traces to a named recorded source, quotes are reproduced character-for-character as the material carries them, timestamps appear only where the material carries them and in the material's own form, guest bios are verbatim as pasted, and the sponsor disclosure section is your recorded line verbatim or prints "none recorded". A disputed fact is never stated as the episode's fact. It runs GATE-N. It creates no Gmail draft, publishes nothing, and performs no podcast-platform act of any kind.
4. Guest & Sponsor Coordinator — the Book's outreach desk, on a short leash. It keeps guest records exactly as you state and paste them — identity as stated, bio verbatim, contact details private in the Book and never printed — and drafts guest outreach and sponsor drafts only from recorded facts, each with a complete per-line fact ledger. Sponsor work rests only on your recorded disclosure line, reproduced verbatim: the kit invents no sponsor, rate, term, or endorsement, and gives no legal advice about whether a disclosure is sufficient. It runs GATE-O. Where a Gmail draft route verifies in a session, it — and only it — may create its own outreach and sponsor drafts in your own Gmail drafts, after you approve that exact text — a draft, never a send. It sends nothing, books no guest, and performs no podcast-platform act.

One Show Book, nothing invented. All four agents work from the same shared My Show Book — 23 fields (F01–F23) filled from 23 calibration questions across the four agents, plus the registers the agents maintain: the change log, the source index, the conflict register, gate results, the open "To confirm" list, the draft log, professional questions filed unanswered, and the escalation log. No pipeline, sheet, package, or draft 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 credential, figure, date, timestamp, or claim. There is no audience figure field anywhere in the Book at all: no downloads, listeners, subscribers, ranking, or growth figure is recorded, computed, or printed as a standing fact. A figure you paste from your own host dashboard for one output is reproduced exactly in that one output only, attributed "as shown on [source], [date as supplied]" — never summed, averaged, converted, or compared across platforms.

What this kit does NOT do — stated plainly, not in fine print. This kit sends nothing and publishes nothing — no episode, no show-notes package, no outreach draft, and no sponsor draft is sent, published, uploaded, or posted by any agent, in either mode, at any level of insistence. Every outbound text it prepares is a draft or a document: the agent shows you the exact text, you approve that exact text, and you send or publish it yourself. Where a Gmail draft route verifies in a session, the Guest & Sponsor Coordinator — the only agent with that route — may create its own draft in your own Gmail drafts — a draft, never a send: no send step exists in this kit. No podcast-platform act is performed by the agents on any platform: uploading an episode, publishing show notes, and updating a show are steps on checklists you execute yourself, in your own accounts, from the kit's gated documents — official routes for Podbean and Descript do exist, and this kit does not use them (see the annex summary below, with their limits named). The kit produces no audio, edits nothing, transcribes nothing, books no guest, and secures no sponsor. It invents no audience, download, listener, subscriber, ranking, or growth figure — and it refuses to write one when asked, in any wording, including "as an example". It corrects no pasted material — not a year, not a quote, not a timestamp — and it resolves no conflict between your materials: both sides stand, flagged, until you state a resolution as your fact, which is then recorded with the originals unchanged. It never strengthens a guest bio — no added distinction, honour, or superlative, in wording, implication, or layout. It gives no legal advice — disclosure sufficiency, guest releases, defamation, and licensing questions are drafted for your counsel or the platform and filed unanswered, and no rule is stated as fact.

Complete, or declared incomplete — the four completeness gates. Each of the kit's four main deliverables runs a named completeness check against your recorded Book before it is presented as finished, and the result is printed with the deliverable: GATE-P for the episode pipeline, GATE-S for the production sheet, GATE-N for the show-notes package, and GATE-O for the outreach / sponsor draft. The pipeline check requires the host and show header as stated, verbatim, every stated episode in order with its release date as recorded or printed "To confirm", pipeline counts recomputed and reconciled on the page, and every conflict flagged with both sides standing; the production-sheet check requires all seven sections at substance — the episode identifier and pipeline position, the recorded dates bloc with intervals recomputed, the outline and material as pasted, material coverage counted from the pasted text with parts shown, and the gaps printed; the notes check requires all nine sections at substance — the episode header with its release date as recorded, the description traced line by line to recorded material, quotes and timestamps only as the material carries them, the guest bio verbatim as pasted, any conflict flagged in place and never stated as the episode's fact, the disclosure as your recorded line verbatim or "none recorded", links and credits only as pasted, and no audience figure anywhere; the outreach check requires a complete per-line fact ledger — every factual line in the draft listed with the recorded fact it rests on — guest identity and bio exactly as stated and pasted, show facts as stated, dates as recorded with weekdays derived, no contact detail printed, no audience figure claimed (the ledger prints the gap where reach would ordinarily be cited: "audience figure: none recorded — none claimed"), the disclosure, where a sponsor draft carries it, as your recorded line verbatim, and the draft marked draft-only on its face. If you ask for "just the highlights," the check still runs and still fails by name: a short version may be produced only as a separate extract labelled with the failed gate and its gaps named — it is never titled, formatted, or sold to you as the deliverable. The complete deliverable remains the offer.

Timestamps and quotes exist only as your material carries them. A timestamp is never estimated from episode length, never interpolated into a chapter grid, and never rounded; a quote is reproduced character-for-character, with its attribution as the material carries it, and is never tidied. What the kit does compute, it recomputes with the parts shown: pipeline counts from the recorded pipeline, weekdays derived from their dates, intervals and countdowns from two recorded dates, and material-coverage counts — quotes and timestamps — counted from the pasted material itself. If two of your own materials print different years or facts for the same item, both are printed and the disagreement is flagged — never silently resolved, never harmonised, and never settled by preferring the guest over the host or the newer over the older. In the kit's materials, one pasted outline prints 1962 and a guest's quoted words in the pasted notes print 1963 for the same ferry closing, and both stand in exactly that way (see the worked example below — a fictional example, labelled as such).

Your Book holds other people's information — the privacy stance. The Book holds your show texts and guest information you supply, including guest contact details — the Book's most sensitive data, held in the private Book only and never printed in any deliverable, draft, or rendering; only its existence state ("recorded — private" / "none recorded") may be displayed. The agents never publish, post, or share your Book anywhere; guest detail appears outside the Book only inside the exact draft you approved, as that draft's purpose requires — and you send that draft yourself. Passwords, account numbers, payment details, API keys, and identity-document numbers are never recorded in the Book at all and never pasted into a chat — a secret pasted into a chat gets one answer: refuse, do not use it, change it now. Keep the Book where only the people you choose can see it, share only the part a person needs — a guest who needs their draft never needs your guest register — and know 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 Show Book as a real file under git, with a commit before the first edit and one per verified step. The route fences are exact, and they do not widen by platform: Gmail drafts — the Guest & Sponsor Coordinator only, its own drafts only, in your own Gmail drafts, after you approve that exact text — a draft, never a send, on every platform. No podcast-platform act is performed by any agent in either mode — on Podbean, Descript, and every other host or editor alike, the platform steps are checklists you execute yourself from the gated documents, and the annex language below records what each official route allows, with its limits named: Podbean's and Descript's official routes exist and are not used by this kit. Dates are Show Book records, not calendar acts — no calendar step is designed in this kit. 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. Capability depends on your platform and on what you choose to connect, and the official routes are limited (capability annex checked 2026-10-31): Gmail — executes with limitations, draft-only: Google's Gmail route lists a draft-creation tool and lists no send tool on the surfaces checked — in this kit, only the Guest & Sponsor Coordinator creates its own drafts that way, only where the route verifies in-session, only on your approval of the exact text; limits include Google Workspace Developer Preview Program membership and, from Claude, an Enterprise/Pro/Max/Team plan. Google Calendar — executes with limitations, NOT designed in this kit: an official route exists for your own calendar, with attendee/invitee support not documented on the pages checked and never claimed — this kit designs no calendar act; recording and release dates are Show Book records, and you add a date to your own calendar yourself if you want one there. Podbean — executes with limitations, EXISTING BUT NOT DESIGNED by this kit: Podbean operates an official MCP server (episode drafts, publish, show updates, analytics via Claude Desktop, ChatGPT desktop, Cursor), with limits named on Podbean's own page — Unlimited Audio plan or above, a public podcast, Podbean AI processing consuming Podbean AI credits, and file access/upload options depending on the AI client — this kit does not use that route: no agent performs any publish or platform act on any host. Descript — executes with limitations, EXISTING BUT NOT DESIGNED by this kit: Descript operates an official API + MCP (import, edit, publish from Claude, ChatGPT, Codex, or Cursor), with limits — authentication is a personal API token scoped to a specific Drive, and tools differ by surface — this kit does not use that route: the kit works only from material you paste and produces no audio. Buzzsprout — guide-only: an official public API exists (a developer route), and the only MCP found for it is third-party, never presented as official. Transistor — guide-only: an official public API exists (a developer route); no official MCP was found. Captivate — guide-only: API credentials for connected apps are verified; no official MCP was found. Spotify for Creators — no route, guide-only: no official MCP, and its Web API covers catalogue retrieval only — no episode upload, no show-notes edit, no creator analytics. Apple Podcasts Connect — no route, guide-only: no official MCP and no general creator API for stats or show management was verified. Libsyn — guide-only: a Stats API at Pro/enterprise level is stated on its own Pro page; no official MCP was found. Riverside — no verdict claimed: nothing was verified from an official Riverside page, so this kit claims nothing about a Riverside route. Any line implying this kit uploads your episodes, publishes your show notes, sends your email, books your guests, or secures a sponsor 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, because brand is not a guarantee and plans change; the in-session check governs over every statement in this listing and in the kit's dated capability annex. The kit also includes a short, plain-language guide to AI limitations, with that dated annex (checked 2026-10-31) 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 Show Planner you answer its 10 questions one at a time and reach the first milestone: the Book opened — its cover with you and your show exactly as you stated them, your episode pipeline with every stated episode, dated rows with weekdays derived, undated rows printed as "To confirm" and never dated from your cadence, every conflict between your own materials flagged unresolved, and anything missing shown as "To confirm" — plus a gated episode pipeline with its counts reconciled, a change log opened with its first entry, and one faithful first tracing demonstrated live: a stated text you name, returned character-for-character, as it will always appear. That is the first session — not a produced season. The production sheets, the show-notes packages, and the outreach come step by step after that, from the Book you build.

The worked example: the materials walk one complete fictional example end to end — Ruth, who states her bio herself: "Ruth has lived on Main Street for thirty years and records Main Street, Remembered from her front room, one story at a time." She opens her Book on Friday 2027-04-30 with her show as she states it — "Main Street, Remembered" — her show description, format, and subject scope recorded in her own words, her cadence stated as "I release a new episode weekly, on Fridays.", and her tone ("Unhurried, warm, and exact about names and dates.") recorded as her preference. Her stated pipeline is 3 episodes: Ep. 11, "The Carnegie Library Steps", releasing Friday 2027-05-07; Ep. 12, "The Ferry Landing at the Foot of Main Street", releasing Friday 2027-05-14 — 7 days after Ep. 11, and 14 days after the Book opened; and Ep. 13, "The Winter the River Froze", with no release date, no outline, and no material — the counts reconciled on the page as 3 rows stated, 2 dated, 1 undated, and no date assigned to Ep. 13 from her weekly cadence. For Ep. 12 she pastes an outline and, after recording, her post-recording notes: the outline states ferry service ended in 1962; her notes carry exactly two timestamps — 00:14:20 and 00:31:05 — and exactly one verbatim quote, Dr. Ortiz's at 00:14:20: "The last ferry crossed in 1963, and half the town came down to watch it go." The 1962-vs-1963 conflict is flagged wherever either year is used, both years standing, never resolved — no show note states a closing year as the episode's fact. At 00:31:05 her notes record that she read the 1958 ferry timetable aloud, times and fares as printed on it — the notes do not print those times or fares, so no output states a sailing time or a fare. Ep. 12 is recorded Monday 2027-05-03 (3 days after the Book opened), its show notes are due Monday 2027-05-10 (7 days after recording, 4 days before release), and it releases Friday 2027-05-14 (11 days after recording). Her guest for Ep. 12 is stated as "Dr. Lena Ortiz, curator at the Harborview Museum", and her pasted bio is reproduced verbatim, everywhere: "Dr. Lena Ortiz is curator at the Harborview Museum, where she oversees the maritime collection. She grew up two streets from the ferry landing." — a request to make the guest sound more impressive is refused, and no distinction is added in the bio, in an introduction drawn from it, or in outreach. No guest contact detail exists in her Book — none is printed, and she addresses and sends outreach herself. Her one recorded sponsor fact is her disclosure line, reproduced verbatim wherever a disclosure is called for: "Support for Main Street, Remembered comes from Harborview Books on Main Street." — there is no second sponsor fact, no rate, and no terms in her Book, and no output adds one. Her show-notes package for Ep. 12 carries no audience figure of any kind, because none exists in her Book and none was pasted from her host dashboard in this example. Her outreach draft to Dr. Ortiz is drafted from the Book as it stood after opening (Friday 2027-04-30), inviting her to the recording Ruth states for Monday 2027-05-03, with its fact ledger printing "audience figure: none recorded — none claimed". Ep. 13 gets no production sheet beyond its recorded row and no show notes at all, until she pastes material for it. Your Book gets your own material; the example is there to show the shapes. Ruth is a fictional example persona created for this kit — not a customer, not a real podcaster using this kit, and not a result story of any kind; Dr. Ortiz appears only inside the guest material Ruth supplies in the example.

If a legal or platform-policy question comes up: if you ask whether a disclosure line is sufficient, what a guest release requires, what a term means, or what a platform's policy allows, the agent stops, gives no answer and no reassurance, and drafts the question — resting on your recorded facts — for your counsel or the platform, filed in the Book unanswered. Sponsor work in this kit uses only your recorded disclosure line, verbatim — never rewritten toward sounding more compliant, more enthusiastic, or more complete. The kit never sends that question and never states a rule for your jurisdiction or for any platform as fact.

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 Show 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: 23 fields (F01–F23) from the four agents' 23 calibration questions, plus the registers the agents maintain — host and show records, episode pipeline and release dates, episode outlines and material as pasted, production records, notes records and links/credits as pasted, guest records with bios as pasted and contact details private, the sponsor disclosure as recorded, the source index, the conflict register, gate results, the open-items list, drafts logged as drafts, professional questions filed unanswered, the escalation log, and the change log. There is no audience figure field in it, by design
• Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrase for Gmail draft creation (there is no approval phrase for a send, a publish, an upload, or a booking — this kit performs none of them)
• 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 (checked 2026-10-31)
• A step-by-step README that gets you running
• Troubleshooting & FAQ — a timestamp that appeared where your material carries none, a quote that came back tidied, a conflict that came back resolved, a bio that came back sounding grander than you pasted it, a show note asserting a fact your material does not carry, a figure showing where you recorded none: the known rough edges and their fixes
• Changelog — what changed in this version

Who it's for:

• A solo podcaster whose show lives in several places at once: episode ideas and release dates in fragments, outlines in documents, post-recording notes in another, guest details in messages, a sponsor line remembered rather than recorded — and who needs one Book built only from those materials, with any disagreement between their own materials shown to them instead of quietly settled
• Podcasters who want every show note traceable to material they recorded, every timestamp exactly where their material carries it, every guest bio exactly as pasted, and an episode with no material named as such rather than written from general knowledge
• Podcasters whose facts change mid-season — a release date reported moved, material pasted for the episode that lacked it, a guest status reported changed — and who want the Book re-issued from the updated facts, with every interval re-derived, dependent drafts marked stale, and every change logged, instead of documents drifting apart

Who it's NOT for:

• Anyone looking for a podcast host, a distributor, an audio editor, a transcription service, or software that uploads, publishes, sends, books, or sells anything for them — this kit is instruction files for your AI, plus the Book work you direct and check; "Producer" here means production records and drafts, not audio production
• Anyone who wants an agent to invent local history or episode content from its own knowledge, correct a pasted year, settle a disagreement between their materials, estimate a timestamp, strengthen a guest bio, or write an audience, download, or listener figure — those inventions are exactly what this kit refuses; the kit records your facts, traces your material, does the date and count arithmetic, and drafts your questions
• Anyone who wants legal advice about a disclosure, a release, or a licence — the kit drafts such questions for your counsel or the platform and files them unanswered; it answers none of them itself
• Anyone who wants a Book that looks complete whether or not the material is in — an incomplete record is delivered with its gaps showing, and a completeness gate that fails is stated, never waived

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 bio and show description exactly as you state them, your title, format, cadence, tone, and subject scope exactly as you state them, your pipeline and release dates as you state them, your outlines and recorded material pasted exactly as you have them, your guests as you state them with their bios pasted exactly as you have them, and your sponsor disclosure line exactly as you recorded it; the agents use only what you supply, and infer nothing
• A private place to keep the saved Show Book — it holds your show texts and guest information you supply, including private guest contact details, 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 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 and workspaces are easy to find too. What this kit adds is the Book those products never build — filled only from your supplied facts and pasted material, with every show note traced to its recorded material under a claim-trace gate, every timestamp held only where the material carries it, every conflict flagged and left standing, every deliverable passing a named completeness gate, and the whole record kept current by re-issue and change log when your facts change.

What the agents can do depends on where you run them: in a chat-only AI they guide and draft — 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 they 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; email is draft-only in both modes — where a Gmail route verifies, a draft may be created in your own Gmail drafts only, by the Guest & Sponsor Coordinator, its own drafts only, and a draft is never reported as a send, because nothing in this kit is ever sent by an agent; and no podcast-platform act is performed in either mode — Podbean's official MCP route and Descript's official API + MCP route both exist and are not used by this kit, Google Calendar's route exists and no calendar act is designed, and every other host checked is guide-only or has no route — on every platform the deliverable is the gated document you place yourself. The kit's boundary holds in both modes: the Book is built only from what you supply, unknowns are printed as "To confirm", pasted material stands exactly as pasted and is never corrected or tidied, conflicts are flagged and never resolved by the kit, timestamps exist only as the material carries them, guest bios are verbatim and never strengthened, sponsor content rests only on your recorded disclosure line verbatim, no audience, download, listener, or ranking figure is ever invented or claimed, statuses change only when you report them, and a confirmed change re-derives everything resting on it and flags what it conflicts with instead of rewriting the record. The agents' worked example, Ruth, is a fictional example persona created for this kit to show the formats end to end — not a customer story. You check every output before you rely on it. This kit promises no outcome for your show — not a release on any date, not an audience, not a booked guest, not sponsorship: what it offers is checkable, namely fidelity to your stated facts and pasted material, recomputation with parts shown, and a completeness gate on every major deliverable.

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: $49 — Standalone: all 4 agents, everything included. Starters (ONE agent, your choice of any of the 4) are $19 each — separate listings below. Starter owners complete the set with the Upgrade, $30 — the difference.