AI-ready data is business data an AI can reason about without you in the room. Every number has one written definition, a labeled source and period, and a link to the products, orders, customers and spend it belongs to. Facts only you know, like unit cost, are written down and approved. Answers are checked against the source of record before anyone acts on them.
AI-ready data is business data that an AI can reason about correctly without a person in the room to explain it. For a consumer brand, your products, orders, customers, ad spend and costs are joined into one model. Every number has one written definition. Every answer can be traced back to the system that recorded the money.
Most brands have plenty of data, and very little of it is ready. The gap is not storage or access. It is meaning.
Access is not understanding
Connecting Claude or ChatGPT to your store takes a few minutes now. Ask it “what was revenue last month?” and it will answer with confidence. The trouble is that the question has several correct answers. The AI has no way to know which one you mean.
Three honest answers to one question. Gross sales before discounts and refunds, net sales after them, and the money that actually settled after marketplace fees. An AI with no written definition picks one and does not tell you. Illustrative numbers.
None of those numbers is wrong. Each is right for a different decision. Gross sales tells you about demand. Net sales feeds the P&L (your profit and loss statement). The settled amount is what reached the bank. Say an AI silently picks one, then compares it to a month where it picked another. It will tell you a story that never happened.
That is the whole problem in miniature. The AI is capable. The data does not carry its own meaning.
The five properties of data AI can understand
Here is a practical test. Data is AI-ready when it is defined, connected, labeled, owned and checked. Miss one and the answers drift.
| Property | What it means | What breaks without it |
|---|---|---|
| Defined | Every metric has one written definition that every answer shares | “Revenue” means three things across three answers |
| Connected | Products, listings, orders, customers and ads are linked to each other | The AI cannot tell which ad sold which product, or that five listings are one product |
| Labeled | Every number carries its source, period and known caveats | A half-finished month is compared to a closed one and reads as a collapse |
| Owned | Facts the systems cannot know are written down, dated and approved | Margin is calculated with last year’s unit cost, or with no cost at all |
| Checked | Answers are compared to the source of record before anyone acts | Two tools disagree and the AI averages them into a number nobody recorded |
Defined
A definition is a sentence plus a formula: “Net revenue is gross sales minus discounts, refunds and cancellations, excluding shipping and tax, by the date the order was placed.” Write it once. The point is not that your definition is the only correct one. The point is that every answer uses the same one, so this week and last week are actually comparable.
Start with the ten metrics your team argues about most: revenue, new customers, repeat rate, ad spend, return on ad spend, contribution margin, units, average order value, refunds and inventory on hand.
Connected
Your data describes things. There is a product family and the variants inside it. There are the Amazon and Shopify listings for each variant, the orders that bought them, and the customers who placed those orders. And there are the campaigns that brought those customers in. In most brands those things live in separate systems with separate IDs.
Take one bottle of shampoo. On Amazon it has an ASIN (Amazon’s code for a product), such as B0-something. On Shopify it is variant 4412. On the retail shelf it carries a UPC (the barcode number). Nothing in your data says those three codes are the same bottle.
A written-down model of those things and how they relate is called an ontology. It sounds academic. In practice it is a map. This listing belongs to this product family. This campaign sends shoppers to Amazon rather than to the store. This customer first bought this product. Without the map, ask an AI “how is our repair line doing?” and it adds up whatever rows happen to have “repair” in the title. Our guide to product hierarchy walks through building that map.
Labeled
A number without a label is a trap. Every figure an AI reasons about should arrive with:
- Its basis. Is this order data, settlement data, or store gross sales?
- Its period, and whether that period is closed. The current month is still in flight, meaning not finished. Orders will cancel, refunds will land, and ad platforms will restate (revise their earlier numbers).
- Its known blind spots. Meta’s pixel (the tracking code Meta puts on your store) cannot see a purchase that happens on Amazon. Amazon buyer emails can arrive days late, so recent customer counts run low. A cohort (a group of customers who first bought in the same period) that is six weeks old cannot tell you its repeat rate yet.
The label is what lets the AI say “this looks like a drop, but the month is not closed” instead of sounding an alarm. Better still, the label travels with the number itself. No prompt (the message you send the AI) has to remember to mention it. We cover the most common mislabeled numbers in why AI gets your ecommerce numbers wrong.
Owned
Some of the most important facts in your business live in nobody’s system. What a unit actually costs to land. When a product launched. Which ads point to Amazon. What margin the founder considers healthy. Whether “the 3-pack” means the 3-count bottle or three separate tubes.
These facts need an owner, a date and an approval. “Landed cost for the 90-count bottle is $4.10 per unit, effective 1 June, approved by finance” is a fact. A cost figure someone typed into a chat three months ago is not. Keep one more distinction: facts are stored, but metrics are not. Lifetime value (what a customer spends with you over time) or return on ad spend should be recalculated fresh every time. Never save them as a fact that quietly goes stale.
Checked
Even well-defined data produces bad answers sometimes. The last property is a habit built into the system. Compare the answer to the source of record (the system that actually recorded the money) before a person acts on it. On Amazon, that is the settlement report, which shows what Amazon actually paid you. On Shopify it is payouts. For ads it is the platforms’ invoices, and for costs it is the general ledger in your books. When two figures for the same metric and period disagree, say so out loud. Never average them.
Where the ontology ends and the harness begins
The five properties split cleanly into two jobs.
The ontology holds the meaning. It holds the definitions, the map of things and links, and the approved facts. It also holds governed actions, which are changes with rules attached. For example, a proposed new unit cost takes effect only after a person approves it. The ontology is the brand’s memory, written in a form a machine can use.
The harness governs the AI. A harness is the layer wrapped around a model. It decides what data the model can reach: your brand and nothing else. It decides what the model is handed with each question: the definitions, labels and facts that apply. And it decides how answers are checked before you see them. The model does the reasoning. The harness keeps that reasoning attached to your real numbers.
You need both. An ontology without a harness is a well-organized library that the AI may or may not consult. A harness without an ontology is a strict referee with no rulebook.
How to make your data AI-ready
You can do most of this in a few focused weeks, with or without software.
- Pick a source of record for each money number. Settlement for Amazon revenue and fees, payouts for Shopify, invoices for ad spend, the ledger for costs. Orders and clicks remain useful as early signals. They are not the truth.
- Write your product family map. Use one row per family. List its name and every SKU (your own product code), ASIN, variant and UPC that belongs to it. Add units per pack, launch date and status.
- Write definitions for your ten most argued-about metrics. One sentence and one formula each, in plain words.
- Write down the facts nobody’s system holds. Landed cost per unit with an effective date, launch dates, targets, which campaigns drive Amazon. Give each an owner.
- Mark every period as closed or in flight. Decide your close rule (for example, a month is closed ten days after it ends) and apply it everywhere.
- Test with questions you already know the answer to. Pick five whose answers are surprising, such as a product that sells well but loses money. If the AI gets the unsurprising version, the data is not ready. A test that only asks easy questions cannot fail.
A quick readiness check
Answer yes or no:
- Does everyone on the team get the same number for last month’s net revenue?
- Can you list every listing that belongs to your best-selling product family?
- Do you know the landed unit cost for every active product, and when it last changed?
- Can you tell which ad campaigns send shoppers to Amazon versus your store?
- Is the current month clearly marked as incomplete wherever it appears?
- When two tools disagree, is there a rule for which one is the record?
Three or more “no” answers means an AI will give confident answers you should not act on yet.
Where Synthesis fits
Synthesis is ontology software and an AI harness for consumer brands. It joins Amazon, Shopify, ad platforms, email, subscriptions and accounting into one isolated model per brand. The definitions and the product family map are written once and shared by every answer. Every number arrives labeled with its basis, period and caveats. It serves that model to Claude and other AI tools. It flags figures that disagree instead of quietly picking one.
Questions people ask
What is AI-ready data?
Data an AI can reason about correctly on its own. Each number has one agreed definition and carries its source and period. It connects to the business things it describes. It can be checked against the system that actually recorded the money.
Can I just connect ChatGPT or Claude to Shopify and Amazon?
You can, and it will answer. Access is not understanding. A raw connection hands the AI tables with no shared definitions. So it picks one meaning of “revenue” and mixes finished months with months still in progress. It also cannot see costs or facts that live outside those systems.
Is AI-ready data the same as a data warehouse?
No. A warehouse puts the data in one place. AI-ready data also needs the definitions, the relationships between things, labels on every number and a way to check answers. A warehouse is the floor, not the building.
What is the difference between an ontology and a semantic layer?
A semantic layer is a set of metric definitions, such as how net revenue is calculated. An ontology also models the things in the business and how they connect. It also covers what can be done about them, such as approving a unit cost. Brands need the definitions either way.
What is an AI harness?
It is the layer around an AI model. It decides what data the model can reach and what context it gets with each question. It also checks the answers before a person sees them. The model does the reasoning. The harness keeps it on your real numbers.
How long does it take to make a brand's data AI-ready?
The data connections can be set up in a day. The part that takes thought is writing down definitions, the product family map and the facts only the team knows. For most brands that is a few working sessions. Then come small fixes as questions show gaps.