TL;DR
It should say so, at zero, with the customer's own words attached. Microsoft documents its agent returning a washing machine for washing powder it cannot find.
It should say so — plainly, at zero, with the customer's own words next to it.
That sounds too obvious to write down, and it is the most commonly broken rule in this whole category. The pressure runs the other way: a system that returns nothing looks broken, and a system that returns something looks like it worked.
For anyone specifying what a quoting system does with a line it cannot resolve. 7 minute read.
Why is the near-miss worse than the miss?
Three outcomes get lumped together and they are not the same:
| Outcome | What it costs |
|---|---|
| Matched, correct | Nothing |
| Matched nothing, and says so | Seconds of a reviewer's attention |
| Matched something adjacent, confidently | The order, or a return — and it surfaces late |
The third is not a worse version of the second. It is a different failure class, and what makes it expensive is exactly what makes it look successful: it produces a complete, priced, plausible row that nobody has any reason to question.
A line that matched nothing is cheap. A person looks, resolves it in seconds, the quote goes out. A line that matched the wrong thing at high confidence is expensive, and the cost lands weeks later when the wrong item is on a lorry.
What does a confident near-miss actually look like?
You do not have to take this from us. Business Central's Sales Order Agent [GA] documents one:
"Searches for related consumables often return the main product instead of the requested accessory or consumable. For example, suppose the customer requests a quote for `WonderWash Waschpulver` in the DE version. The inventory includes `WonderWash Waschmaschine` but not `WonderWash Waschpulver`. However, the agent returns `WonderWash Waschmaschine`."
Read the middle sentence carefully. The requested item is not in the catalogue at all. The correct answer was we do not stock this. What came back was a washing machine instead of washing powder — same brand, entirely different item, entirely different price.
Microsoft publishes a second one in the same section: "When a search term appears as part of a longer word, the system fails to match it" — where one of two valid candidates is silently omitted and nothing signals that the list is incomplete.
Both are bounded to named local versions in Microsoft's own wording, and both are published by the vendor rather than found by us. Publishing them is the right call and more than most vendors do.
What does Microsoft's agent do with an unresolved line?
It stops and asks, which is the right instinct — and the mechanics are worth knowing because they shape what you build alongside it.
When availability checking is switched on and an item is not available, Microsoft documents that "reviewers are notified by a Request Assistance step in the timeline for the task in the Task tab." The reviewer opens an Item Availability page, verifies, and decides whether to stop the task or let the agent proceed.
One constraint on that review step matters more than it looks. The process page states it: "You can't change the items and quantities at this point." The reviewer can verify and confirm, or stop — but not correct in place.
And there is a harder boundary. The agent cannot invent the item: "The agent doesn't create new items, contacts, or customers. It only works with the entities that are already registered in Business Central." Microsoft's published test suite lists "unknown item handling" as a scenario it evaluates against, so this is deliberate behaviour rather than an oversight.
So the vendor's answer to an unresolved line is: escalate to a human, and do not guess. That is the same conclusion the rest of this article reaches — the difference is in what the human is given to decide with, which is the next section.
Why say zero rather than a low score?
Our position, and it is a design choice rather than a documented feature.
An unresolved line stays on the sheet, with the customer's own words attached, at zero. Not the nearest plausible product with a hopeful tick. Not forty per cent. Zero, stated, next to what the customer actually wrote.
Three properties, each deliberate:
- The line does not disappear. A dropped line is the worst available outcome, because the quote arrives looking complete and short, and neither party notices until delivery.
- Zero is not the same as low. A number in the middle invites acceptance on a busy afternoon. Zero is a refusal to guess, and it reads as one.
- The customer's words sit underneath. A reviewer resolving the line needs the raw text, not our interpretation — that is what makes the fix take seconds instead of a search through a mail client.
How does a reviewer settle an unresolved line?
A row that says needs you has to give the reviewer something to press, on the row, always visible. A control that appears only on hover is a control somebody misses, and a control in a toolbar requires knowing the toolbar exists.
Ask the customer. The question goes out from the same workspace into the same thread, attached to this line — "pipe insulation 22 mm, which thickness, and is it the foil-faced?" The answer comes back against the row it belongs to. Without this, an incomplete line is a dead end.
Find it by hand. Search the catalogue and pick the item. The reviewer's choice beats every heuristic, and it should be remembered for this customer so the same words resolve without a person next time — which is chapter 1's Item Reference table, filled in one row at a time.
Mark it not stocked. Which brings us to the outcome people are most reluctant to build.
Is "we don't stock this" an acceptable answer?
Yes, and treating it as an error state loses business.
The instinct is to hide what the system could not work out — to drop the line rather than admit it. A quote that comes back covering thirty-nine of forty lines, and says plainly that line eleven is not something you carry, is a useful and professional document. The customer sources that one item elsewhere and gives you the rest.
A quote that silently returns thirty-nine lines invites the customer to notice the gap themselves, and to wonder what else was missed.
Say it on the quote. It costs one row and it buys the thing the whole exercise depends on: a customer who believes what the document says.
Want to know how many of your lines would come back unresolved, and why? Book a 15-minute call — bring a real request and your catalogue, and we will look at both. No deck.
Sources
- Process sales quotes and orders with Sales Order Agent
- Sales Order Agent overview — Business Central
- FAQ for Sales Order Agent — Business Central
- Item availability in Sales Order Agent (preview)
This article is part of our work on the RFQ quoting engine.
Share this article
How an agent reads an RFQ, matches each line to your catalogue and prices it, and what has to happen to the lines it cannot resolve.
