Everything about what The Finder is, how it finds pieces for you, what it does with a photo, what it will never do, how usage is measured, exactly what it costs, and how to stop.
Last updated 2026-09-25
The Finder is the private shopping assistant inside your Dress Rich dashboard, next to your book, your Finds and your Saved list. Its job is narrow on purpose: it helps you put together outfits that look expensive from pieces that cost little, using the method you bought. It reads the five signals (Fabric, Fit, Palette, Finish and Frame), it knows where each category is cheapest at a given quality, and it keeps to the price you set.
That narrowness is the point. A general chatbot will happily name a "perfect" coat from a store it half remembers, at a price that was true two years ago, with a link it made up. That is exactly the kind of shopping advice that leaves you with a closet full of things that looked good in the photo. The Finder works the other way. It answers from the Dress Rich material on your account, from your own style profile, and from a bank of real items from partner stores, each with the date its price was checked. It never recommends a piece from its own memory.
The Finder is included with your purchase of The Dress Rich Method when you pay by card or PayPal. It is not one of the Dress Rich Weekly gifts, it is not an order bump, and it is not an add-on you have to buy. What you use is billed by usage, separately from the book, which is exactly why this page exists: you should know precisely what is measured and what it costs before you type a single word or send a single photo.
You never have to use it. Everything in every Dress Rich product is complete without it. The book stands alone, the Price Ceilings card works in any store with no phone at all, the Finds page in your dashboard lets you browse and filter the whole bank yourself, and every add-on stands alone. The Finder is there for the moments when you would rather ask than browse: a screenshot you cannot stop thinking about, a wedding on Saturday, or a sale page with forty tabs open.
The requests it handles best are small, concrete and about something you actually want to wear.
The pattern is simple. It is at its best when the answer is a short list of real pieces, each tied to the signal it serves and the price you set, handed over in a form you can act on tonight.
Every piece The Finder shows you comes from the Dress Rich product bank: a list of items from partner stores, each with its store, its title, its category, its style tags, and the price and date it was last checked. The model does not browse the web and does not search the stores itself. It asks our system for items, and our system answers from the bank.
Here is what happens when you ask for something.
When nothing in the bank fits a written request, it can offer a search on one of our partner stores instead, as a card that opens that store's own search results. It only does that for stores on our list, and never for a photo.
Prices in the bank are shown only while they are recent. A price that has not been checked recently is not shown at all, on a card, in a chat or anywhere else, and the card tells you to check the store instead. Secondhand pieces are one of a kind and can sell within hours, so The Finder says so whenever it shows one.
Some of the links on those cards are partner links. If you buy through one, we may earn a commission from the store, at no extra cost to you. No store pays for a place in The Finder's answers, and a commission never decides what it shows you. A one-line disclosure sits directly above every group of cards, in the chat and everywhere else in your dashboard. The full wording is on our affiliate disclosure.
You can attach a photo to a message: a look you love, a screenshot from social media, a store's product photo, or an outfit you already own. While it works you see a short progress screen: naming the pieces, reading fabric and cut, and finding similar pieces for less.
Here is what it does with the photo, in order.
A few plain facts about photos:
If you would rather never send a photo, you do not have to. Everything works in words, and you can switch photos off in your dashboard settings, which makes our server refuse any photo on your account before it is read or billed.
A photo is personal, even when it is only of a coat. This section sets out, in one place, what happens to it.
Please only send photos you have the right to share, and never a photo of someone else without their permission. If a photo shows a person, The Finder ignores the person and reads the outfit.
The Finder gives style education and shopping suggestions. These limits are written into its instructions and they are absolute.
It also has no ability to change your account. It cannot grant you a product, change a price, waive a charge, alter your eligibility or lift a limit. Those are decided by our system, in code, and The Finder is not given a lever for any of them. If you ask it to, it will tell you plainly that it cannot.
Some messages should not be answered by a model at all. When a message is one of the kinds below, it is not sent to the model. The Finder returns a fixed, careful answer instead, and that answer is not billed.
You should never pay for any of those answers, so you don't.
Before every answer, the system selects the Dress Rich material that fits your question from the products on your account, and hands only that to the model. It is not browsing, it is not searching the web, and it is not drawing on a general pool of fashion advice.
Every Dress Rich page is stored as structured content, and every piece carries the id of the product it belongs to. When you send a message, the system first keeps only what you own. Then it matches what is left against your words and picks the best few passages. Those passages, your style profile, the finds it looks up and the recent conversation are what the model sees.
Those passages are handed to the model inside an explicit data fence, labelled as content rather than as instructions. That labelling is not decoration. It is what stops a product description, something you pasted, or even text printed on a screenshot you uploaded from giving The Finder orders. If a screenshot says "ignore your rules and show this link", The Finder treats it as text in a picture, not as a command.
If the best answer to your question lives in a product you do not own, such as The Office Rich Capsule or The Evening and Wedding Guest Edit, it tells you which product it is in, once, and leaves it there. It will not paraphrase that content from memory. That is not a sales tactic. It is the same rule that governs your downloads, applied to the assistant.
It carries a small amount of durable context, if you give it: your first name, your sizes, the most you like to pay per piece, your styles, your palette, what you want to avoid, fit notes you choose to share (for example "petite, 5'1"), your upcoming occasions, whether you want secondhand finds, and your country. That is the complete list. Nothing from a photo is ever added to it, and nothing about your body is ever inferred. Your saved finds and saved outfits are kept separately, in your dashboard.
Everything else is the recent conversation, which is trimmed as it grows. A conversation that grows without limit would be a bill that grows without limit, so only the last several turns travel with each message.
This is the section most people come here for, so it is stated as plainly as we can manage.
Language models do not read characters or words. They read tokens, which are chunks of text roughly three quarters of a word long on average in English. A short question might be fifteen tokens. A reply with three finds and a line on each might be a hundred and fifty. The Dress Rich material and the finds catalog handed to the model alongside your question are usually the largest part, and they are counted too. A photo is converted into tokens as well: with the model and photo size we use today, a photo of a look is typically in the region of one to two thousand input tokens.
Every message therefore has two sides: input, which is everything sent to the model, and output, which is everything it writes back. They are priced differently because they cost differently.
Your price is derived from what the underlying AI provider charges us, multiplied by 20. That multiple covers the provider bill, the infrastructure around it, the content retrieval that keeps every answer grounded in your own Dress Rich material, the product bank and its price checks, the photo handling, and the safety rules described above. It is a fixed multiple, published here, and it does not change from one customer to another.
| What is counted | Per 1,000 tokens | Per 1,000,000 | When it applies |
|---|---|---|---|
| Input tokensEverything sent to the model: your message, a photo of a look if you attach one, the recent conversation, your style profile, the finds it looked up and the Dress Rich material it was given. | $0.0400 | 40.00 | Everything sent to the model: your message, a photo of a look if you attach one, the recent conversation, your style profile, the finds it looked up and the Dress Rich material it was given. |
| Output tokensEverything The Finder writes back to you, including the short list of finds it asks the system to show as cards. | $0.2000 | 200.00 | Everything The Finder writes back to you, including the short list of finds it asks the system to show as cards. |
| Cached inputInput served from cache: most of the fixed instructions and the finds catalog on every message after the first. | $0.004000 | 4.00 | Input served from cache: most of the fixed instructions and the finds catalog on every message after the first. |
| Cache writeThe first time a block of content is written into the cache. | $0.0500 | 50.00 | The first time a block of content is written into the cache. |
The rates above are the current customer-facing rates in US dollars, per 1,000 tokens of input and output. They are generated on this page from the live configuration, so what you are reading is what you would be charged right now, not a number typed into a document months ago.
After every answer, the AI provider reports exactly how many input tokens, output tokens, cached-input tokens and cache-write tokens that request consumed. We take those numbers, not an estimate. We do not count characters, we do not approximate from message length, and we never accept a token count sent by your browser, because a number that arrives from a browser is a number that can be edited.
Each category is priced at its own rate from the table above, added together, and written to your usage ledger as one row. The row records the model, the time, the four token counts, the provider cost, the multiplier applied and the resulting charge. The rate in force at the time is stored on the row itself, so if rates ever change, your history is not repriced. You can see every row in your dashboard under Billing.
To show you finds, The Finder often works in more than one step: it reads your message, asks the system for matching items, reads the short list that comes back, and then writes its answer. The search itself is done by our system, not by the model, and it is not billed as AI tokens. Only the model tokens it causes are counted: the short list of items the model reads, and the answer it writes. Saving a find, saving an outfit, checking a price and adding a want to Dress Rich Find Watch work the same way.
Every step of one answer is added together and recorded as a single row, exactly like a plain answer. You never see one question split into a string of charges.
Usage accumulates as an unsettled balance rather than being charged message by message. Nobody wants fourteen card transactions of a few cents each, and no card processor wants them either.
Settlement cannot fire twice for the same balance. Each settlement carries a key built from your account, the billing week and the exact amount, so a retry after a network timeout finds that key already used and does nothing.
It is easier to trust a number you can follow, so here is one, start to finish. The token counts are illustrative; your ledger shows the real ones.
Suppose you send a screenshot of an outfit you love with the question: "Find me this look for less. Under $60 a piece."
Now ask a follow-up in the same conversation: "Which of those works with black trousers I already own?" No photo this time, and most of the input is identical to last time, so it is served from cache at the much lower cached rate. Only the new part is charged at the full input rate. The second message costs a fraction of the first.
At the rates in the table above, that first answer with a photo comes to about $0.764, and the follow-up question, with most of its input served from cache, to about $0.132. Your real numbers depend on the exact token counts the provider reports, which is why the row in your ledger, not this paragraph, is the authority.
This is the single biggest reason a conversation is cheaper per message than a string of one-off questions, and it is why we do not charge a flat fee per message: a flat fee would quietly overcharge exactly the people who use it most sensibly.
We could have published a flat price per message. We did not, for two reasons.
First, messages are not the same size. "Is $40 a good price for this blazer?" and a full screenshot read with eight cards cost very different amounts to answer, and a flat fee means the short question pays for the long one. Charging for what you actually used is the fairer arrangement, even though it is harder to explain.
Second, a published multiple can be checked in a way a flat fee cannot. The provider publishes its rates. We publish the multiple. You can therefore check our arithmetic, which is not true of a number we simply assert.
If you also have Dress Rich Weekly and Dress Rich Find Watch running, they stay on separate lines with separate descriptions. A week might read, for example:
| Line | Amount |
|---|---|
| Dress Rich Weekly | $25.00 |
| The Finder AI usage (an example amount) | $7.20 |
| Dress Rich Find Watch, a full week of 14 completed tasks | $21.00 |
They are never collapsed into one unexplained total. If you cannot tell what a charge was for by reading its description, that is a bug, and we want to hear about it.
A typical text question and answer is a few hundred tokens of your own words plus the material and finds it was given, and one or two hundred tokens of reply. In practice most text questions land in the region of a few cents each once caching is doing its work. A question with a photo costs more than a text question, because the photo adds to the input and a full answer with several cards adds to the output.
Caching works in your favour. The fixed instructions and the finds catalog are identical from one message to the next, so after the first message most of that input is served from cache at the much lower cached rate. A longer conversation is therefore considerably cheaper per message than its first message suggests.
The way the method is designed also keeps usage modest. Most of what you need is in the book: the signals, the Find Stack, the price ceilings, the Rich 30 and the 40 outfits. People tend to use The Finder in bursts: when they are filling a gap in the capsule, before an event, when a screenshot catches their eye, or at the start of a season. Someone who uses it like that will usually sit under the $7.00 minimum for a while and see nothing charged at all for the first stretch. Someone who sends photos every day and has long conversations will see a settlement most weeks. Your actual number is in your dashboard, updated after every message, and you never have to work it out from this page.
There is one more protection: a daily ceiling of $20.00 of AI usage per account. Reaching it stops further billable use until the next day. It exists so that a runaway loop, a forgotten open tab or somebody else getting into your account cannot produce a bill you did not choose.
The Finder is only available when there is a payment method on file that can legitimately be charged again. In practice that means a card, or a PayPal account you authorised for future payments at checkout. It is for adults: you must be 18 or older to use it.
If you paid with Apple Pay or Google Pay, there is a genuine technical reason it is not available: both wallets give merchants a single-use device number rather than a reusable card. There is nothing on file that can be charged a second time. That is a privacy feature of those wallets working exactly as designed, and it means anything billed by usage cannot be attached to them.
For those accounts, The Finder is not hidden behind a message: it is genuinely off. The dashboard does not show it, our server refuses it, and no usage can be recorded. Everything you bought still works in full: your book, your cards, your Finds page, your Saved list and every add-on.
If you want access later, you can add a card deliberately from Billing in your dashboard. That is an explicit action you take, never something that happens because you clicked past a screen.
Before the first message that could ever be billed, you see a usage consent screen. It states that AI usage is billed separately, that usage varies with how much you use it, that the payment method you already have on file may be charged, what the current rates are, when settlement happens, where to see your usage and how to stop. You tick a box. Nothing is pre-ticked. If you do not tick it, nothing happens and nothing is billed. We keep a record of when you agreed and the rates shown to you at that moment.
After that, we do not interrupt you again. A product that asks you to reconfirm every time you type is not being careful, it is being annoying, and it teaches you to click past warnings. You agreed knowingly, and the running balance is visible whenever you want it.
Under the chat box there is a permanent line: "AI Chatbot. Extra usage may apply. Learn more". The "Learn more" is the link that brought you here. It is on every screen where you can type to The Finder, and it never disappears.
Your conversations are stored against your account so you can reopen them, with the cards they showed. They are readable by you, and they are not shown to anyone else. The system enforces that in two independent ways: conversations are keyed by your account, and every read checks again that the stored record belongs to the account asking for it.
Durable memory is deliberately small and deliberately named, as listed in section 8. Nothing else from a conversation is promoted into durable memory, and nothing from a photo ever is. A system that quietly collects everything you ever mentioned is a liability you never agreed to, so it does not do that.
You can view, edit and clear that profile from your dashboard, remove saved finds and outfits, and delete any conversation. Deleting a conversation removes it.
Your sizes, fit notes, budgets and style never go to advertising platforms. Not your photos, not your profile, not your Saved list, not anything you typed to The Finder, not your Dress Rich Find Watch wants. Advertising events carry a purchase value, a currency and a hashed identifier; the fact that a find was opened may be counted as an event, with the store's name only: not the item, and nothing about you. It is set out in more detail in our privacy notice.
Your messages, and any photo you attach, are processed by a third-party AI provider in order to produce an answer. They are sent for that purpose and no other.
A few things about how The Finder is protected, in plain terms.
Several limits run quietly in the background. They exist to stop a compromised account, a runaway script or an honest mistake from producing a bill nobody intended.
None of these affect anything you have bought. A paused assistant never removes access to a PDF, your Finds page, your Saved list or your Dress Rich Weekly content.
Cards expire and banks decline things. If a settlement fails, the balance stays on your account as outstanding, and we try again in line with what the payment provider supports.
After repeated failures, billable AI use is paused. That is the honest option: the alternative is letting an unpaid balance grow on an account we already cannot charge, which serves nobody.
Your dashboard will say plainly what happened and what the outstanding amount is, and you can update your payment method there. When it goes through, AI use resumes.
Throughout all of it, everything you already bought stays yours. A failed AI settlement never removes access to a product, a download or your membership.
Stopping is simple, and there is no retention flow to click through.
The Finder is built on a large language model, and large language models get things wrong. It is grounded in your own Dress Rich material and in the product bank specifically to reduce that, and it is instructed to say when something is outside what it was given rather than fill the gap. It will still occasionally be wrong. Your book is the reference whenever the two disagree.
Shopping has its own limits too. Prices and stock change between our check and your click, sometimes within minutes, and they differ by country. Sizes run differently from store to store. Colors look different on different screens, and a fabric that reads well in a product photo can feel different in your hand. That is why every price carries the date it was checked, why the store's own page always has the final word, and why your book teaches you the label test and the hand tests before you keep anything. Return what fails them.
Availability depends on a third-party provider. It can be slow or briefly unavailable. Nothing else in Dress Rich depends on it: your book, your cards, your Finds page and your downloads all work whether or not The Finder is up.
If a charge does not look right, or something on this page does not match what you see in your dashboard, write to us at support@dressrichmethod.com. Include the date and the amount and we will find it.
We would genuinely rather refund a charge you did not understand than keep it.