For educators

Grade what a student did with the answer

Every teacher asks students to show their work. The tools those students use do not.

A fluent paragraph tells you nothing about who wrote it, or whether anyone opened a source.

Open three sources. Show where the machine got it wrong.

Tools that claim to spot AI writing consistently misclassify non-native English writing as AI-generated, and the chatbots write better every month. Policing the output is a race nobody finishes. Plenty of teachers have already made the move on their own, letting the machine do the collecting so that the analysis becomes the thing worth grading.

The task: The assignment now Research three enforcement actions and write a summary of each.; The assignment instead Here is the machine's table for those three. Find where it is weakest and show your working.
What the student does: The assignment now Prompts a chatbot, reads a fluent paragraph, rewrites it in their own words.; The assignment instead Opens sources. Compares what the cell claims against what the document says. Overrides what does not hold.
What they hand in: The assignment now Prose you cannot attribute.; The assignment instead A record of which claims they checked, which they changed, and the reasoning they gave for each.
What you are grading: The assignment now Whether the writing is good, and whether you believe they wrote it.; The assignment instead Judgment. Whether they went to the source, and whether their disagreement was well founded.
If they use AI: The assignment now The problem.; The assignment instead The point. The machine is supposed to do the collecting.

The judgment record names who decided

A verdict is LoQuery's one-word call on how well a source supports a claim, and when a student changes one, the cell keeps both. The machine's original, the student's replacement and the reason they typed sit on that cell as three fields. LoQuery writes them while the student works, so you can grade the thinking instead of reconstructing it afterwards.

Session record Judgment

Judgment record Student run · 3 items × 4 fields

Cells in the run: 12
Sources opened: 5
Verdicts changed: 1

Kinross incident Official explanation

confirmed with caveats → uncertain

Opened the source. The USAF finding is there, but the RCAF denied one of its aircraft was involved, so calling it explained is stronger than the record supports.
user
Shag Harbour incident Primary source

confirmed kept

Checked the archive listing and it holds up. Kept the verdict but noted the file is a research guide rather than the file itself.
collaborative
Lake Michigan 1994 incident Date

mismatch kept

No reasoning given. Source not opened.
evaluator

The system records this today. The teacher-facing view that would show it to you is designed and not built. See what is not built yet, below.

The row that matters most is the last one. A cell nobody opened is the thing a grade book cannot otherwise tell you.

Cell values, sources and caveats here are real and open to checking. The scores, attempt counts and source totals show the shape of a run and get replaced once a captured session record lands.

The run these three rows came from, step by step →

Teach the five words, so arguments get specific

Every cell carries one of four verdicts, and a fifth word covers the candidates LoQuery threw out before any research began. The vocabulary is the teachable part, because it gives a class something more precise to argue about than whether the answer is right. Nothing inside LoQuery explains these words to a fifteen-year-old, so the glossary sits on a marketing page until it sits in the product.

confirmed: We found it, and the source backs it up.

What it actually means

The evidence cleared the threshold and the source is one the system rates as authoritative for this kind of question. It still means go and look. A confirmed cell is a claim with a receipt attached, not a promise that the receipt is correct.

Ask a student Open the source. Does it say what the cell says?
confirmed with caveats: We found it, but there is something you should know first.

What it actually means

The claim is supported and something about it needs qualifying: the document covers more than the thing you asked about, the source is weaker than we would like, or a date sits near the edge of the window you set. The caveat is written out with a code, so it is a category rather than a mood.

Ask a student Read the caveat first, then decide whether the answer still works for your question.
uncertain: We could not establish it, so we are not going to guess.

What it actually means

The system searched, read pages, and did not find evidence it was willing to stand behind. It scores itself zero and says so. This is the hardest behaviour to build and the easiest to skip, because a system that always produces something looks better and helps less.

Ask a student Ask why. Is it not on the open web, or was the question not answerable as asked?
mismatch: We found something, but it is about the wrong thing.

What it actually means

What came back does not resolve to the entity you named. A different company with a similar name, a cluster of events where you asked about one, a person rather than an incident. The result is kept and flagged rather than quietly dropped, because knowing the search went sideways is more useful than an empty cell.

Ask a student Look at what it did find. Usually it tells you the question needs to be more specific.
rejected: It never made it into the research at all.

What it actually means

A discovery-stage decision. The candidate failed entity validation before any research began. A page heading, a location, an institution. Rejections are shown with their reasons rather than silently removed.

Ask a student Scan the reasons. If something real was rejected, the question needs rephrasing.

And on every verdict, a record of who decided it

evaluator the machine reached this on its own
user a person overruled the machine and this is their call
collaborative the machine's verdict stood, with a person's reasoning attached

That field is the assessable artifact. It is the difference between a student who accepted everything and a student who argued with three cells and wrote down why.

A class pays for runs (not seats)

Schools and educational institutions in need pay what a run costs LoQuery and nothing on top, and a run costs cents. There is no per-seat licence, so a class of thirty pays only for the runs those thirty students make. The commercial rate that firms pay is what funds the school side.

The published pricing rule, and which parts are still open →

Setup is an extension and a sign in

To deploy: A browser extension and a sign in, with no server-side deployment and no student information system to integrate.
To approve: On managed Chromebooks an administrator allowlists the extension, and that is the only approval anywhere in the chain.
Where runs live: Stored, so a student can reopen their own work and show it to you. What we store, and what we do not do with it →
Where searching happens: In the student's browser, so no search a student runs reaches a LoQuery server.

No teacher view, no safe mode, no invoice

Three gaps you would hit in week one, because the record and the vocabulary run today while the classroom built around them does not.

No screen hands you the record yet, so a student opens their own LoQuery run and shows you the cells they argued with.
Nothing filters the open web before it reaches a student, though you supply the item list and can restrict a run to domains you name. A setting that does that by default is designed and not built.
No invoice reaches a school today, because LoQuery bills per user, pay as you go, and schools do not buy that way.

A class concept is missing too, and so is accessibility work aimed at learning differences, which needs a practitioner rather than a developer guessing.

This works in a real classroom with real fifteen-year-olds.