Why Generative AI Gets Prices Wrong,

and what that reveals about the data

A guaranteed response, a fake price

This scenario has played out thousands of times since conversational AI became part of everyday life: a buyer, a category manager, or someone simply curious asks a general-purpose language model a question about price. The answer comes in a matter of seconds, phrased with the same confidence as if it were an exact answer. The figure seems credible. It isn’t always.

What is striking is not just the error—every system makes mistakes sometimes. It is the absence of a signal that would allow us to detect it. A model that hesitates, that indicates a margin of uncertainty, that says “I don’t know,” would be easier to correct than a model that asserts a made-up price with the same ease as an exact price.

This behavior is not a teething problem that will disappear with the next version of the model. It is a direct and lasting consequence of what these systems actually do.

Predicting is not the same as verifying

A general-purpose language model—whether it’s ChatGPT or an equivalent competitor—operates on a principle that is simple to state but less simple to intuitively accept: for every word it generates, it calculates the statistically most likely sequence of words, based on everything it has seen during training. By default, it does not consult any real-time database. It “knows” nothing in the sense that a spreadsheet or an ERP system knows what a cell contains.

For creative writing or rephrasing, this mechanism produces excellent results: the most plausible answer is, most of the time, the right one. But when it comes to a price—a specific, date-sensitive number that has only one correct value at any given moment—the mechanism changes in nature. The model does not seek the actual price: it seeks the number that, statistically, most closely resembles a plausible price for this type of product, based on patterns it has encountered in its training corpus, which is frozen at a cutoff date that never corresponds to the present moment.

• No native access to the actual catalog —the model does not query the point-of-sale system, ERP, or e-commerce site of the relevant retailer.
• A corpus frozen in time —even information that was correct at the time of training may be outdated by the time the question is asked.
• No inherent concept of uncertainty —the model, as formulated, does not distinguish between a firmly established fact and a statistical extrapolation.

Why Price Is a Particularly Revealing Example

Many errors made by generative AI go unnoticed: an approximate date, a slightly outdated statistic, a nuance lost in a summary. The price, however, is immediately verifiable. All you have to do is visit the retailer’s website or compare it to the receipt to see the discrepancy. That’s what makes the problem visible—it’s no more common than elsewhere, just easier to measure.

This visibility is becoming increasingly important as consumers grow accustomed to asking a chatbot for advice before making a purchase rather than comparing prices on their own.

The more consumers rely on a general-purpose chatbot to handle part of their price research, the more the gap between the stated price and the actual price becomes a tangible business problem—both for the retailer whose product is misrepresented and for consumer trust in the tool itself.

What an isolated model lacks to be reliable in terms of price

The difference isn't due to the model's size or version. It's due to what surrounds it—or doesn't surround it.

To put it this way: it is never the model alone that makes a price estimate reliable—it is what it is connected to, and the rigor with which that connection is established.

The Real Issue: Data, Not Model Power

When faced with an incorrect answer, the natural instinct is to look for a “smarter” model. This is rarely the right approach. A more powerful model, without a connection to a source of truth, will produce an incorrect answer that is phrased even more convincingly—which exacerbates the problem rather than solving it.

A seminal academic study on the factuality of language models illustrates this well, using an exercise that is far removed from pricing but reveals the same mechanism: the generation of long-form biographies.

The figure does not pertain to prices, but the mechanism is applicable: an isolated language model, no matter how advanced it may be, produces a mix of correct facts and plausible extrapolations, without distinguishing between the two. In the case of a biography, the issue is often trivial. But when it comes to a price shown to a customer or used to make a business decision, it is no longer trivial.

What This Reveals About the State of Data in Companies

The issue goes far beyond language models. It touches on a longer-standing and more structural problem: most organizations do not have data that is clean, structured, and accessible enough for AI—whether generative or not—to rely on it reliably.

A model that gets a price wrong is therefore not just a modeling issue. It is often the most visible symptom of an underlying problem: the lack, upstream, of a reliable product reference system, a clean price history, and formalized business rules.

At Booper: Connecting AI to the Truth, Not to Its Memory

The AI Center: A Solution Rooted in the Retailer's Actual Data

Booper’s AI Center —the “BOOPER AI Assistant”—provides natural-language responses on pricing, competitive matching, promotions, and monitoring. The difference from a general-purpose chatbot isn’t due to a larger model; it’s because its responses are based on the retailer’s actual data, not on the general knowledge of a model trained on the web at a specific point in time.

The GENIUS Link module provides a concrete example of what it means to “properly connect” an AI component to the real world: using NLP (natural language processing), it matches a retailer’s products with tracked competitor SKUs, even when the product names differ— displaying a confidence score for each match, rather than a binary answer that would mask the uncertainty. This is the exact opposite of the behavior of a standalone language model: here, uncertainty is shown, not masked.

Four Things to Consider Before Trusting a Price Provided by AI

1. Check the source, not just the number. Explicitly ask where the data comes from. A system connected to a single source of truth can provide an answer; a standalone model can generally only describe its own operation.
2. Never publish a price without human verification. A price generated by generative AI, no matter how convincing it may be, remains a hypothesis that must be verified against the actual source before any commercial or client use.
3. Be wary of a lack of hesitation. A system that displays a confidence score or acknowledges its limitations is more reliable—not less—than a system that always responds with the same level of confidence.
4. Check the timeliness of the data. Retail prices are constantly changing. An answer that was correct yesterday may be wrong today if the system isn't connected to an up-to-date source.

Checklist before trusting an AI-generated price quote:

• Is the system connected to a live data source, or is it responding solely from its training memory?
• Does the answer indicate a level of confidence, or is it just a number presented as a certainty?
• Is the underlying data up to date, or does it come from an old training session?
• Are there any business rules (margin thresholds, product line consistency) that are applied before the price is displayed?
• Does a human verify an AI-generated price before it reaches a customer or is used in a business decision?

Is your data ready to power a reliable AI pricing system? Spend 30 minutes with our team to assess where your data stands today and what needs to be fixed before you integrate AI into it. → Let’s schedule a meeting.

FAQ

Do you still have questions? Here are the answers to the most frequently asked questions on this topic.

‌

To learn more about this topic: AI and retail pricing, what truly falls under the umbrella of artificial intelligence (pillar), AI that decides vs. AI that executes, and data quality as the glass ceiling of AI pricing. To assess the reliability of your pricing data, check out our pricing assessment.