Freelancer Studio AI Kit — 4 Ready-To-Use AI Agents for One Faithful Studio Book

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

Not a prompt pack and not a CRM — a filled, faithful Studio Book: your prospects recorded exactly as you describe them, your scopes priced only from your own rate card with exclusions printed as OUT, your invoices recomputed line by line from your own session log with every logged session accounted for, and every deliverable gated by a named completeness check, kept current every time a fact changes. Works with the AI you already have: upload one file, tell it "Start", answer a few questions, and the Book starts filling with YOUR clients, rates, and sessions.

This is not a prompt pack, not a blank template, and not a CRM or invoicing app. Four specialist agents fill one Studio Book with your facts — your rate card exactly as you state it, your prospects exactly as you describe them, your briefs and templates exactly as you supply them, your sessions exactly as you log them — check each deliverable against a named completeness gate, and keep the whole Book current when a rate is corrected, a session is marked unbilled by you, or a status is reported. Nothing in the Book is invented, no price comes from a market, no discount is ever negotiated, and nothing leaves it as a send. 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 facts, with its money recomputed and its sessions reconciled.

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 rate card exactly as you state it, one prospect exactly as you describe them, your intake questions in your own words. That's the calibration, and it's what makes the Book fit YOUR practice.
4. Save the complete updated Studio 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 clients and sessions.

Use the agents in order:

1. Client Intake Coordinator — the Book's front door, and the kit's lead agent. It opens the shared My Studio Book and its cover page, owns your freelancer record, your rate-card record, and the prospect/client register — prospects exactly as you describe them, your intake questions verbatim, answers as you report them, requests as made, and fit decisions verbatim when you state them. It scores nothing, ever. It produces intake summaries and first-reply drafts from recorded facts only, and runs GATE-I. Where a Gmail draft route verifies in a session, it may create its own first-reply drafts in your own Gmail drafts, after you approve that exact text — a draft, never a send. It creates no calendar event and no Stripe draft.
2. Scope Builder — the Book's assembly bench. It assembles scopes only from the brief you supply, your recorded rate card, and timelines you state: deliverables one per line in your words, exclusions printed as an OUT list at the same prominence, price lines recomputed with the parts shown, and agreement text reproduced exactly as you pasted it — never drafted, never interpreted. It runs GATE-S. It touches no external route at all: no calendar, no Gmail draft, no Stripe draft, and no invoicing platform, in either mode.
3. Work Log & Invoice Keeper — the Book's ledger. It logs sessions exactly as you report them, computes invoice figures only from your log × your recorded rate card with the parts shown, records payments only as you report them, and attaches the uninvoiced-work reconciliation to every invoice: every logged session invoiced, marked unbilled by you, or listed as an open question — nothing silently dropped. It runs GATE-V. It is also the kit's only calendar writer and its only Stripe drafter, each under its own exact-approval gate and each described below with its limits named.
4. Follow-Up Drafter — the Book's voice, on a short leash. It builds the follow-up queue with statuses exactly as you report them, and follow-up and check-in drafts resting only on the recorded facts you name for each draft — no invented promise, discount, or date. Tone is your recorded preference; content is the Book's recorded facts. It runs GATE-F. Where a Gmail draft route verifies in a session, it may create its own follow-up drafts in your own Gmail drafts, after you approve that exact text — a draft, never a send. It creates no calendar event and no Stripe draft.

One Studio Book, nothing invented. All four agents work from the same shared My Studio Book — your calibration for all four agents, your rate card, your prospect and client register, your scopes with their briefs, deliverables, OUT lists, stated timelines, pasted templates, and price bases, your work log, your invoice ledger with payments as reported and a disposition for every session, your follow-up requests, tone preference, and draft statuses, your open "To confirm" list, and the change log exist once, in one place. No intake summary, scope, invoice, queue, 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 rate, term, figure, or date, and one client's pricing decision never surfaces in another client's documents.

What this kit does NOT do — stated plainly, not in fine print. This kit sends nothing — no reply, no follow-up, no scope, and no invoice is sent, finalised, submitted, or collected by any agent, in either mode, at any level of insistence. Every outbound text it prepares is a draft: the agent shows you the exact text, you approve that exact text, and you send it yourself. Where a Gmail draft route verifies in a session, the Client Intake Coordinator or the Follow-Up Drafter may create its own draft in your own Gmail drafts — a draft, never a send: no send tool exists in this kit. It gives no legal advice, drafts no agreement or contract language, and interprets no clause — agreement text enters only as your own pasted template, reproduced as pasted, and a legal question becomes a drafted question for your lawyer. It gives no tax advice and computes no tax — a tax line exists only where your supplied facts or pasted template carry one, reproduced as such, and a tax question becomes a drafted question for your accountant. It never negotiates: a discount request is recorded as asked, and the kit proposes no price, no discount, no counter-offer, and no payment plan — including by computing a discounted figure from a requested percentage. It states no market rate ever — no typical price, no benchmark, no "freelancers usually" figure, in any wording, as a suggestion or as a sanity check. It scores, grades, ranks, and characterises no prospect or client. It generates no leads and runs no campaign.

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-I for the intake summary, GATE-S for the scope document, GATE-V for the invoice + reconciliation, and GATE-F for the follow-up queue. The intake check requires every intake question listed with its answer as reported or shown as not reported, every request recorded as made with no figure derived from it, and the fit field present with no score; the scope check requires the brief as supplied, deliverables in your words, the OUT list present and explicit — a scope with no recorded exclusions fails by name rather than passing silently — every price line traced to your rate card or template with its total recomputed, the deposit shown as its own attributed line, and no legal language drafted; the invoice check requires every line traced to a logged session or a recorded flat item and recomputed, and the reconciliation accounting for every logged session — invoiced, marked unbilled by you, or an open question, with no fourth state; the queue check requires every open item with its status as reported and its report date, every draft tied to the recorded facts it rests on, and the statement that nothing in it was sent by the kit. 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.

Figures are arithmetic, not atmosphere. Every figure printed anywhere is recomputed from recorded parts, with the parts shown: logged hours × your recorded hourly rate; flat items as recorded; a template's printed percentage × the recorded price it applies to. Every weekday in the Book is derived from its date, and every interval is recomputed. If a total you state disagrees with the recomputation of its own parts, both figures are printed and the disagreement is flagged — never silently resolved, never explained, and never attributed to any cause. In the kit's materials, a stated total of $1,116.52 stands beside the recomputed $1,116.25 for the same three sessions, with the $0.27 difference flagged in exactly that way. A deposit or payment is applied against a total only as you state that application, recorded as your stated application with both parts shown — never by pattern.

Your Book holds other people's information — the privacy stance. The Book holds your prospects' and clients' names, the answers you report about them, your rate card and your per-client pricing decisions, unissued invoice drafts, and payment states. The agents never publish, post, or share your Book anywhere; client detail appears outside the Book only inside the exact draft text you approved, as that draft's purpose requires — and you send that draft yourself. Passwords, account numbers, payment details, and identity-document numbers are never recorded in the Book at all — at most, that an arrangement exists and who holds it. Keep the Book where only the people you choose can see it, share only the part a person needs — a client who needs their scope never needs your prospect 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 Studio 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 Client Intake Coordinator and the Follow-Up Drafter only, each its own drafts only, in your own Gmail drafts, after you approve that exact text; calendar events and Stripe drafts — the Work Log & Invoice Keeper only: calendar events on your own calendar only, as the exact block you approved, one by one, with no invitees by default (an invitee is added only when you name that invitee and approve that exact block including the invitee list), for dates recorded in the Book; and, only where creating an invoice draft itself verifies as possible in that session, a draft invoice in your own Stripe, after you approve that exact invoice, verified by re-read — never finalised, never sent, and never a created or edited customer, product, price, or payment setting. The Scope Builder touches no external route at all in either mode — its deliverables are documents you place yourself. 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. FreshBooks, Wave, Bonsai, HoneyBook, and Dubsado are not connected at all. There is no integration, sync, checking, or login with any of them, in either mode — no agent route into any of them is claimed — and the agents prepare copy-ready artefacts for you to carry into whatever system you already use. For Stripe, the claim is draft-level only, and it carries its qualification wherever it is stated: a draft invoice may be created in your own Stripe only where that creation verifies as possible in the session itself — where it does not verify, the deliverable is the gated invoice document for you to enter yourself, stated as such. Any line implying this kit sends your messages, finalises or sends your invoices, chases a payment, or syncs with an invoicing or client platform 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. 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 Client Intake Coordinator you answer its 8 questions one at a time and reach the first milestone: the Book opened — its cover with you as you stated yourself, your rate card exactly as stated, your first prospect exactly as described, anything missing shown as "To confirm" — plus a gated intake summary with its first-reply draft, a change log opened with its first entry, and one faithful first computation demonstrated live: the deposit line from your own pasted proposal template, recomputed against your rate-card package with its parts shown, and attributed to your template. That is the first session — not a filled pipeline. The scope, the invoice, and the queue come step by step after that, from the Book you build.

The worked example: the materials walk one complete fictional example end to end — Sam, a freelance brand designer, opening her Book on Monday 2027-02-22 with a rate card she states herself: a logo package at $1,800 flat and an hourly rate of $95, and no other rate. She records one prospect, Crumb & Craft Bakery, on Tuesday 2027-02-23, from an inquiry she reports: the need, as she reports it, is a new logo for the bakery, for the shopfront and packaging; the timeline answer is not reported and is printed as "To confirm"; the prospect asked for 20% off the logo package, recorded as asked, with Sam's decision not recorded and no discounted figure computed or offered anywhere. On Wednesday 2027-02-24 she builds the scope from her supplied brief — a rebrand, new logo and brand marks for the shopfront and packaging — with deliverables in her words ("One primary logo"; "One secondary mark"; "Colour palette"), exclusions recorded as OUT in her words ("Packaging design — OUT"; "Shopfront signage — OUT" — the logo is for the shopfront and packaging; the design of packaging and signage themselves is OUT, and both lines stand as supplied), her stated timeline wording ("First concepts two weeks after the deposit is recorded as received") with no calendar date derived from it, the price at $1,800 flat from her rate card, and a deposit from her own proposal template: her template prints 50%, recomputed as 50% × $1,800 = $900, attributed to the template and applying to the flat package. She logs three sessions — Monday 2027-03-01, 6.5 hours, "Rebrand discovery and concept sketches"; Wednesday 2027-03-03, 3.25 hours, "Logo concepts — round one"; Friday 2027-03-05, 2 hours, "Logo concepts — refinement" — hourly work outside the flat package, invoiced on Monday 2027-03-08 at her recorded rate: 6.5 + 3.25 + 2 = 11.75 hours × $95, with lines of $617.50, $308.75, and $190.00 and a total of $1,116.25, the $900 deposit not credited against that hourly invoice because the record applies it to the flat package only, no due date recorded, no tax line recorded, and no payment reported. Her follow-up draft of Wednesday 2027-03-10, in her recorded tone "short and friendly", rests only on that invoice record — no due date, no delivery promise, no discount, and no contact person's name, because none of those is recorded — so you can see every format before you build your own. Your Book gets your own material; the example is there to show the shapes. Sam is a fictional example created for this kit — not a customer story.

If a legal or tax question comes up: if you ask what a clause in a pasted agreement means, what a term requires, or how a tax line should be worked out, the agent stops, reproduces the pasted text exactly as you pasted it where there is pasted text, gives no answer and no reassurance, and drafts the question — resting on your recorded facts — for your lawyer or your accountant, filed in the Book unanswered. It never sends that question, never states a rule for your jurisdiction, and never confirms a rule or a rate you suggest.

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 Studio 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 — rate card and prospect register, scopes and pasted templates, work log and invoice ledger, session dispositions, follow-up requests and draft log, disagreement and conflict flags, lawyer/accountant questions, drafts logged as drafts, the open-items list, the connected-mode record, gate results, and the change log
• Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases for calendar entries, Stripe draft creation, and Gmail draft creation (there is no approval phrase for a send — this 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
• Troubleshooting & FAQ — a discounted figure that appeared from a discount request, a market rate that was suggested, a scope that came back without an OUT list, a logged session missing from an invoice, a tax line that appeared from nowhere, a clause that came back summarised: the known rough edges and their fixes
• Changelog — what changed in this version

Who it's for:

• A solo freelancer — designer, developer, writer, or consultant — whose paperwork lives in several places at once: prospects in one thread, a scope in another, hours held in memory, invoices assembled at month-end — and who needs one Book built from those materials, with any disagreement between their own figures shown to them instead of quietly smoothed over
• Freelancers who price from a rate card they set themselves and want every scope price traced to that card and every invoice line re-derived from the sessions they actually logged
• Freelancers whose facts change mid-project — a corrected rate, a session marked unbilled, a status reported changed — and who want the Book re-issued from the updated facts, with every change logged, instead of documents drifting apart

Who it's NOT for:

• Anyone looking for a CRM, an invoicing app, a lead-generation service, or software that sends, finalises, or collects anything for them — this kit is instruction files for your AI, plus the Book work you direct and check
• Anyone who wants an agent to say what to charge, benchmark a rate against a market, negotiate a discount, score a prospect, draft or interpret a contract, or work out a tax line — those calls belong to you and to your lawyer or accountant; the kit records your facts, does the arithmetic, and drafts your questions
• Anyone who wants a Book that looks complete whether or not the facts are 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 rate card exactly as you state it, your prospects as you describe them, your intake questions in your words and answers as you report them, your briefs, deliverables, exclusions, and stated timelines, your proposal or agreement templates as you paste them, and your session logs and payment reports; the agents use only what you supply, and infer nothing
• A private place to keep the saved Studio Book — it holds client information, your rate card and per-client pricing decisions, and unissued invoice and payment states, 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 bookkeeping service, and not a human freelancer service. Prompt packs for this work exist cheap, and generic freelancer prompts are easy to find free; blank freelancer 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, with every scope price traced to your rate card, every invoice recomputed from your log with every session reconciled, 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; calendar work is an approved event on your own calendar with no invitees by default, created by the Work Log & Invoice Keeper only, where that route verifies, and a copy-ready block everywhere else; a Stripe draft is created only by the Work Log & Invoice Keeper, only as a draft, and only where creating an invoice draft itself verifies as possible in that session — everywhere else the deliverable is the gated invoice document; and every message is a draft in both modes — where a Gmail route verifies, a draft may be created in your own Gmail drafts only, by the Client Intake Coordinator or the Follow-Up Drafter, each its own, and a draft is never reported as a send, because nothing in this kit is ever sent by an agent. No route into FreshBooks, Wave, Bonsai, HoneyBook, or Dubsado exists in any mode. The kit's boundary holds in both modes: the Book is built only from what you supply, unknowns are printed as "To confirm", figures are held only as supplied and recomputed with their parts shown, no market rate or negotiated figure is ever stated, no prospect is scored, no agreement is drafted or interpreted and no tax is computed, 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, Sam, is an illustration created for this kit 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: $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.