Use case

AI document review that cites the passage behind every answer

AI document review reads a stack of documents and tells a qualified person what they need to know about each one, in roughly the time it takes to open the first file. It pulls the specific fields a checklist calls for and separately flags anything that looks unusual for a person to weigh, and it shows exactly where in the document each answer came from rather than asking anyone to take its word for it. The job looks the same under a lot of different names: an insurance adjuster working a claims backlog, a procurement team reading supplier contracts, a letting agent checking a stack of tenancy files, a grants officer reading applications against eligibility rules, a compliance team working through submissions — all doing the same underlying task.

· Reviewed by Artur Horimoto, Founder & CEO

Two different jobs hiding inside "document review"

"Review this pile of documents" sounds like one task. It is actually two, and they behave nothing alike.

The first is extraction: pull specific fields out of every document — a policy number, a contract's effective date, an applicant's declared income, a supplier's insurance expiry. This is a well-defined task with a checkable answer. Either the extracted date matches what's printed on the page or it doesn't, and a person can confirm that in seconds by glancing at the source. It's tedious at volume, but it isn't ambiguous.

The second is assessment: does this clause sit outside what the firm normally accepts, does this claim's account of events look consistent with the supporting evidence, does this application raise something an eligibility rule doesn't explicitly cover. There's no single correct answer sitting on the page waiting to be copied out — assessment depends on judgment, on what "normal" looks like for this business, on context a checklist can't fully capture in advance.

That difference matters because it's where the value and the risk both concentrate. Extraction saves time; get a field wrong and it's usually caught the moment someone checks it against the source. Assessment is where a genuinely bad outcome hides — a missed exclusion clause, a claim that should have been flagged and wasn't, an application that slipped past a rule nobody thought to write down explicitly. A useful system has to treat these as two different jobs with two different standards, not one blended "review" step that quietly borrows extraction's confidence for assessment's harder calls.

The manual way vs. the automated first pass

Manual review usually means one person opening one document at a time: reading it in full or scanning for known terms, typing the fields they find into a spreadsheet or case system by hand, and separately forming a judgment about anything that looks off — all under whatever time pressure the pile of remaining files creates. What counts as "worth flagging" quietly shifts depending on who's reading, how many files are left, and how the last few similar documents turned out.

An automated first pass does the same two jobs, structured so a person reviews results instead of raw pages. The system opens each document, pulls the checklist fields with a citation attached to each one, and produces a separate assessment layer that surfaces anything worth a second look — again with the exact passage attached, not just a verdict. A reviewer's day starts with a stack already sorted into "fields captured, nothing flagged" and "here's specifically what needs your eyes," rather than a blank read of every file in the order it arrived.

Manual review Automated first pass
Extraction Typed by hand from the page, one document at a time Pulled automatically, every field tied to its source passage
Assessment Formed by whoever is reading, under time pressure Flagged for a person, with the passage that triggered the flag
Consistency Varies by reviewer, by day, by how many files are left The same checklist and criteria applied to every document
Verification Requires re-reading to double-check a field A cited passage confirms or corrects a field in seconds
Final call Made by the person reading Still made by the person reading

That last row is the point worth sitting with. Automating the reading doesn't automate the decision — it changes what the person spends their limited attention on, from re-typing fields off a page to weighing the handful of things that actually needed a human judgment call.

Documents that don't cooperate: scans, bad formatting, and versions that drift

Real document stacks are rarely clean, consistent PDFs. A claims file might include a faxed form scanned a second time by whoever received it. A supplier's contract template looks nothing like the one your own legal team drafts, and no two suppliers format theirs the same way. A grant application submitted this year uses a different layout than the one submitted last cycle for the same programme.

The first hurdle is simply reading what's on the page. A scanned or photographed document needs optical character recognition — software that turns an image of text into text a system can actually search and extract from — before any of the extraction or assessment work can start, and a poor-quality scan degrades that step the way it would degrade a person's ability to read it. The second hurdle is structure: tables that don't line up the same way twice, handwritten annotations in a margin, a form field that moved between one version of a template and the next. The third is version drift — a contract gets amended, a claim file gets supplemented with new evidence weeks later, an application gets resubmitted with corrections — and the system has to know it's reading the current version rather than silently blending a superseded clause into a current answer, which is a worse failure than simply being slow.

None of this gets solved by pretending it doesn't happen. It gets handled by building for it from the start, and by being honest about where confidence genuinely drops — which is exactly where the next section picks up.

How a build actually works

Every answer comes with its passage, not just its answer

A field or a flag with no source attached asks a reviewer to trust it blind, which is the opposite of what fast, reliable review requires. A build worth using shows the exact passage — the sentence, the clause, the line on the form — that produced each extracted field and each assessment flag, so a person can confirm it against the original in the time it takes to glance at two things side by side, rather than re-reading the whole document to check one line. This is the difference between a tool a reviewer trusts and one they quietly stop using: an answer with nothing behind it invites doubt, and a bare assertion is never good enough on its own, no matter how confident it sounds.

This is also where extraction from PDFs and other source formats has to hold up under pressure — a field pulled from automated data extraction is only as useful as the citation that lets someone verify it landed in the right place.

The low-confidence pile goes to a person, not a guess

Every extracted field and every assessment flag carries a confidence level, not just a value. A clean, typed document with an unambiguous field produces high confidence. A badly scanned page, a term with no clean match to anything in the checklist, or a clause structured in a way the system hasn't seen before produces low confidence — and low confidence doesn't get smoothed over with a best guess presented as fact. It gets routed to a person, marked as needing review, exactly the same way a claims handler would set aside a file they weren't sure about rather than approve it on a hunch. That routing decision is what human-in-the-loop design actually means in practice: build the system to hand off the cases it isn't sure about, instead of quietly guessing and hoping nobody checks.

Whatever industry runs this — a claims team, a procurement desk, a compliance function, or a firm managing legal matters — the output is a first pass for a qualified person to check, never a decision the system makes on its own. That holds regardless of what the documents are or what's riding on getting them right.

What it connects to

A document review system is only useful if it reaches the documents you actually receive and lands its output where your team actually works. Typically that means:

  • Wherever documents arrive — an inbox, a claims portal, a supplier onboarding form, an application intake system — read as they come in rather than batched for a manual sweep later.
  • Your case or matter management system, so extracted fields and flags land as structured records rather than a separate spreadsheet someone has to reconcile by hand.
  • Whatever holds the checklist and the rules, so extraction fields and assessment criteria reflect what your team actually requires, not a generic template.
  • Your document storage, so the source file stays one click away from every cited passage, and a superseded version doesn't quietly outrank the current one.

None of this requires replacing what your team already runs. Where a system exposes an API, a build connects to it directly; where an older platform doesn't, there's usually a workable route in through an export or a webhook it already supports. When the stack is entirely contracts rather than a mix of document types, a narrower contract analysis build is often the better starting point, and either shape sits under the same knowledge systems work more broadly.

Frequently asked questions

What's the difference between extraction and assessment in document review?

Extraction pulls a defined field from a document — a date, an amount, a policy number — and the correct answer is checkable against the page. Assessment is judgment — does this look unusual, does it match the file's history — and there's rarely one obvious right answer. We build and measure these as two separate jobs rather than one blended review step.

Will it ever miss something a human reviewer would have caught?

It can, which is exactly why low-confidence fields and flags get routed to a person rather than resolved automatically. The design goal isn't a system that never misses anything — no reviewer, human or automated, manages that. It's a system that's honest about what it isn't sure of, so a person's attention lands on the cases that actually need it.

Can it handle scanned or badly formatted documents?

Yes, with optical character recognition handling scanned input first. Quality still matters — a clean scan reads more reliably than a faxed copy of a faxed copy — and when a document is genuinely too degraded to read confidently, that gets flagged for a person instead of producing a guessed answer with false confidence.

Does this replace the person who currently reviews these documents?

No. It changes what they spend their time on — from typing fields off a page and reading every document cover to cover, to checking cited passages and weighing the flags that actually need judgment. The final call on any document stays with the qualified person reviewing it, in every industry this gets built for.

How long does a build like this take to go live, and what does it cost?

Most document review builds are in production within weeks, starting narrow with one document type and one checklist before expanding. Cost depends on how many document types, source systems, and assessment rules the build needs to cover — every engagement gets a clear price agreed before any work starts.

Bring the stack of documents your team is currently reading one at a time — claims, contracts, tenancy files, applications, submissions, whatever it is — to a free 30-minute strategy call, and we'll tell you honestly what a first-pass system would catch and what it would take to build.

Automate this job

Walk us through how it works today. We will map the build and give you a clear price before anything starts.

Free 30 minutes. No pitch deck. You leave with a plan either way.