How to put together a commercial proposal people buy

How to put together a commercial proposal people buy

A proposal assembled in ten minutes but not from the client's own words is quickly made rubbish. What works here is the order rather than the speed. Below is the whole cycle: reviewing the recording, a brief with a list of forbidden phrases, a check through the client's eyes, and assembling the file.

A proposal assembled in ten minutes but not from the client's own words is quickly made rubbish. What works here is the order rather than the speed. Below is the whole cycle: reviewing the recording, a brief with a list of forbidden phrases, a check through the client's eyes, and assembling the file.

The call went well and then silence for a week

Here is where deals die most often. Not at the application, not on the call — after the call.

You talked, the client is interested, you agreed you would send a proposal. And then it turns out you cannot make a deck, the layout takes an evening, and the result looks like a school essay. Two days pass. Then three. Then you send something in plain text with "this for now, I will format it later", and the client's interest cools along with the conversation.

The second version of the same trouble: you did make the deck. A handsome one. And it does not sell, because it is built around what you can do rather than around what the client fears.

A proposal like this takes me under ten minutes, and it lands with the person because it is assembled from his own words. Here is the whole pipeline.

Where the content comes from

The key thought, without which the rest is merely speed: the content of a proposal is not invented. It is taken from the review of the call.

I record the call, give the audio to the sales assistant and get the review: what the client said about his losses, what he fears, which lever is the main one for him, what will happen if I name a price with no justification.

From the conversation with Zakhar Fomin, owner of a dental clinic, three pains came out: the fear that a bot will lose an expensive patient; manual reactivation of the base through the calendar and a remote administrator; dead social channels producing one patient every two months.

Each of the three became a block of the presentation. Not one "about us" or "our advantages" slide.

Why an ordinary commercial proposal does not work

The root cause: it is written from the contractor's side. What I can do, what tools I have, how many stages my work consists of. The client reads it as a list of your activities and does not find himself in it.

The misconception: "the main thing is to make it look good". Presentation matters, but second. A beautiful deck about something that does not hurt loses to an ugly deck about something that does.

And the systemic factor that decides everything: a proposal has to be written for the type. Zakhar is a Controller. He needs figures, stages, control at every step and a dashboard where everything is visible. The same proposal for a Driver would need a different first slide — about scale and result rather than about losses.

One deck does not work for the same reason one covering letter does not.

The pipeline in ten minutes

Step 1. The brief for the deck — from the assistant

I write to the AI sales assistant: I need a proposal and a quote, I am setting this price, here is what I intend to do for this client.

The same one that analysed the listing and carried the exchange. It already knows this client — his type, his fears, what was said on the call — so the brief comes out specific rather than generic.

It produces a detailed brief for the deck: requirements for the visual style, what to emphasise, which colours and icons to use, recommended typefaces, how many slides there should be, how to structure it. And separately, which phrases to avoid. That matters more than it seems: a list of forbidden formulations saves you from the clichés a proposal usually falls apart on.

Step 2. It checks itself

The assistant then gives feedback on its own answer against its own criteria and offers options: refine against the notes, run a harsher assessment, clarify details.

And the most useful mode is the focus group. The model takes the client's role with his type and goes through the deck slide by slide: what Zakhar would notice, where he would tense up, what he would scroll past. After which it makes the corrections itself.

I did not even read that version. I copied the brief whole and moved on.

Step 3. A skill assembles the deck

Then Claude Code and a ready skill for making presentations.

What a skill is. Not one prompt but a chain of agents where the task is broken into parts and each part is passed on: a copywriter writes the texts → a designer does the visuals → the next agent structures it by slide → a final proofreader checks the work of the first three, makes corrections and delivers the result.

I installed the skill with one link, pasted in the brief and got an editable PowerPoint deck in 5–7 minutes. Saved it as a PDF and sent it.

Under ten minutes in total.

What came out inside

A slide-by-slide breakdown, because the structure matters more than the speed here.

Slide 1 — trust. A striking logo, calm premium colours. One task: the person must see that this is a serious document rather than a letter knocked together on someone's knee.

Slide 2 — where you are losing money. The colours here are already red, and that is deliberate. Three technical breaks in the funnel draining revenue from the most expensive services — implants and veneers. The expensive service is named directly, so the client mentally says: right, I was losing those.

Work modules, three slides. First — the funnel brief: audience segmentation, awareness levels, a loyalty map, positioning, lead magnets, unpacking the expert. Second — content production: ten units across five platforms. Third — a selling site, a knowledge base, an AI receptionist and a mini application.

The owner's dashboard. A separate slide precisely because the client is a Controller: the cost of acquiring one patient, the agent's conversion from conversation to booking, at what times the assistant answered. The person sees he will be able to monitor all of it — and that removes half his fears.

The economics. An in-house team — a marketer, a social media specialist, a remote administrator — costs around $720 a month, plus taxes, holidays and sick leave. The system costs $1 900 a year and works around the clock. The comparison sits beside the price rather than on a separate slide: the figure must not hang in the air.

Three sprints with staged payment. A Controller needs to control each stage, so the result is visible every week. Sprint one — design, analytics, documents, the customer journey map, lead magnets, the agent brief, scripts. Sprint two, ten working days — the site, the mini application, the receptionist logic. Third — an admin panel with analytics, integration with the client's systems and activation of the existing base. The content factory (a bot that turns a voiced idea into an edited video) was not part of this quote: the clinic bought it separately, for about $1 500.

The final slide — what is not being sold now. The CRM is placed in a second step with the phrasing "a considered second step rather than overpaying at the start". The clinic bought it as the next step, for about $3 200, and that is exactly why it is not in the main quote.

The logic is simple: pay for yourself first, reinvest second. The client sees that nobody is trying to sell him everything at once — and trust rises.

What is not in this proposal

No "about us" slide. No company history, no list of tools, no years of experience. A client who has reached the proposal has already decided you can do it — now what matters is what he gets.

No untranslated technical terms. No RAG, no vector base, no agent orchestration. Everything through what a person already understands: a receptionist, a base, a dashboard.

No promises about the business's results. No revenue growth, no patient numbers. What is promised is only what is delivered: a system, documents, timescales. Promising somebody else's sales is the fastest way to fail the handover.

And nothing that can be sold as a second step. The CRM is deliberately left outside. A proposal with everything stuffed in looks more expensive and takes longer to decide on.

What matters most in a commercial proposal

Not the speed. Ten minutes is a pleasant consequence, but a proposal assembled in ten minutes not from the client's words will simply be quickly made rubbish.

And not the tool. The skill can be replaced by any editor, Claude Code by hand. The one thing with no replacement is the review of the call: if you do not know what the client fears, the fastest pipeline will assemble you a beautiful nothing.

What matters is the order. Review the call → a brief for the type → a check by focus group → assembly. Each step consumes the result of the previous, and what comes out is a document the client recognises himself in.

What is needed to repeat this

The sales assistant — reviewing the call, the deck brief, the focus group mode. One of 200+ AI assistants across 14 categories: sales, marketing, media, legal, HR, analytics, creative, engineers.

Skills for Claude Code — the catalogue and descriptions are open to everyone, the files come with the Basic plan, advanced skills with Creator+, or one-off for $9, or for 1 000 experience points.

The ten-lesson sales module in the “Sales” course — objections, rejections, the four client types, shaping an offer to demand.

Registration is free and opens three days of full Basic access — the sales module, all the assistants, the skill files, the prompt texts and six foundational express courses, including “Freelance 2.0” with a prompt library for the whole funnel.

Do one thing on your next proposal. Do not sit down to lay it out. First write down the three things the client said about his losses — and build the deck around them. Even assembled by hand in an ordinary editor, it will work better than a beautiful one.

If you know somebody in their third day of making a deck for a client, forward this to them. His problem is not the layout.

What the deck itself is assembled with

The mechanics above are about content. Presentation remains, and there is a ready route for it.

The first path is a deck builder that turns finished text into a stylish presentation or a clickable mini page. The proposal goes out not as a document file but as something that opens by link. Good when speed matters and no source file is needed.

The second is skills for Claude Code, and it is more powerful. The presentation skill returns an editable file in 5–7 minutes, and inside it is not one prompt but a chain of roles: copywriter, designer, structurer and a proofreader checking the first three.

The catalogue holds over ten thousand such skills, and presentations are only one category. So for a proposal you take not a universal tool but one built for this type of document: with the right structure, the right checks and the right output format.

What the result looks like at full scale. A real proposal on this methodology was delivered as eleven sections across 157 pages: audience research, positioning, a nine-week content plan, lead magnets, three platforms by function, monetisation, sites, funnel and sales scripts.

The client sees not a quote but a whole system — and that is what separates a $1 900 proposal from a $200 one.

The series: one deal step by step

Eight pieces about one real deal — from a listing in a chat to payment received. The client, Zakhar Fomin, owner of a dental clinic, agreed to be named along with the figures.

Who assembles the proposal without you

Assistants, Basic plan, the catalogue:

A structure for the funnel. The express course “Freelance 2.0” is a prompt library of 11 sections, including “Sites and landing pages” (structure and layout) and “Funnels”; the same technique helps a proposal: start from the core messages — the main pain, the key objection, the main proof. $9, Basic plan and above.

The basis for the price in a proposal. The “Sales” course, the lesson “How to create your own premium product”, Basic plan — about a high-ticket product. A proposal defends itself when it states a result rather than a list of activities.

Skills for assembling a proposal

All six are advanced skills (Creator+, or a one-time $9, or 1000 XP); the cards and descriptions are open to everyone.

What to pick for this article's task. The first and the last. A frame of persuasion and assembly from audit data are enough for a ten-minute proposal; the rest is needed once the volume grows.

What to take on the platform for this task

What to read next

An itemised quote instead of buttons — the lines a price is assembled from.

Reviewing a call with AI — where the content of a proposal comes from.

A deal end to end: from a listing to $1 900 paid — the whole path this is part of.

Skills for Claude Code — how the chain that assembles the file works.

Also on AI SKILLS