Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. A Firm Says Our AI Got a Clause Wrong. How Do We Show What Happened and Stop It Recurring?
Problems We Solve

A Firm Says Our AI Got a Clause Wrong. How Do We Show What Happened and Stop It Recurring?

When a law firm says your AI misread a clause, you need evidence and a fix. We build source citations, confidence flags and an evaluation set.

Updated 3 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

Accuracy disputes are hard because your product gives an answer without showing where it came from, and you have no systematic way to test whether a fix works. We build extraction that cites the exact source text, flags low-confidence answers for review, captures fee earner corrections, and turns them into an evaluation set that every change to prompts or models is tested against.

An email from a knowledge lawyer

Your product reviews leases and extracts key terms: break dates, rent review mechanisms, alienation restrictions. A knowledge lawyer emails: on a lease review last week, your product said there was no break clause. There was one, in a schedule, drafted unusually. The associate relied on the summary before checking the lease, and the supervising partner caught it. They want to know why it happened and what you are doing about it.

Your team looks. The product does not store which parts of the lease it read for each answer. You can rerun it, but the model version has changed since, and the output is different. You fix the prompt, but have no way to know whether the fix breaks something else.

Why AI extraction errors are hard to handle

Legal documents are drafted in endless variations, and extraction features will sometimes get things wrong. The problem is not only the error rate. It is the lack of evidence and the lack of a way to measure improvement.

  • Answers are shown without the source text they were based on.
  • The product shows every answer with the same confidence, so users cannot tell which to check.
  • Inputs, outputs and model versions are not recorded, so an error cannot be reproduced.
  • Fee earner corrections are made in the final document, and your product never learns about them.
  • Prompt and model changes are tested on a few examples, not a representative set.

What unmanaged errors cost

Every error a firm finds reduces trust in every answer your product gives, and knowledge lawyers talk to each other across firms. Without evidence, you cannot explain what happened, which makes the firm's risk team nervous. Without an evaluation set, each fix is a guess that may create new errors elsewhere. Firms may restrict the product to low-value tasks, or tell fee earners to verify everything, which removes the time saving that justified buying it.

How we build extraction firms can check

What we build makes every answer traceable, highlights the uncertain ones, and turns corrections into a test suite.

  1. Source citations for every extracted term: the clause or paragraph it came from, with a link that opens the document at that point.
  2. Explicit not found answers that say what was searched, so no break clause found in the main body or schedules is distinguishable from a guess.
  3. Confidence signals based on the model's answer, agreement between checks and whether the source text is unusual, with low-confidence answers flagged for review.
  4. A record of each extraction: document version, prompt, model and version, sources and output, so any answer can be examined later.
  5. Correction capture: fee earners mark an answer as wrong and give the right one with its location, in a few clicks.
  6. An evaluation set built from corrected examples, with permission, plus synthetic and public documents, run against every prompt or model change before release.
Firm's questionWhat the product shows
Where did this answer come from?Cited clause, opened in the document
Did it look in the schedules?What was searched for a not found answer
Which answers should we check?Low-confidence flags
What exactly happened last week?Stored record with model version and sources
Is your fix any good?Evaluation results before and after the change

Confidentiality matters here. Corrections from one firm's documents are only used in evaluation with that firm's agreement, and never shown to another firm.

The next unusual break clause

A lease arrives with a break clause buried in a schedule. The product finds it, cites the schedule paragraph, and flags it as low confidence because the drafting is unusual. The associate clicks the citation, reads the clause, and confirms it. When the product does miss something on another lease, the associate marks the correction, the case is added to the evaluation set, and the next prompt change is tested against it before release. The knowledge lawyer sees citations on every answer and fewer surprises.

Can your product explain its answers?

  • Extracted terms are shown without the source text.
  • Every answer looks equally certain.
  • You cannot reproduce an answer from last month.
  • Fee earner corrections never reach your team.
  • Prompt or model changes are released without a proper test set.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

Will citations slow the product down?

Very little. The model is asked to return its sources as part of the answer, and we check they exist in the document.

Can confidence scores be trusted?

They are a guide, not a guarantee. We calibrate them against your evaluation set so they flag the answers most likely to need review.

Where does the evaluation data come from?

Corrections from firms that agree, synthetic documents, and public documents such as published leases or contracts where available.

What do you need from us?

Access to your extraction code, examples of disputed answers, and any documents you are permitted to use for testing.

Keep reading

More on Problems We Solve

Start here

Tell us what is slowing your legal tech product inside law firms

Describe what your product does for law firms, which systems it has to work with and where deals or rollouts get stuck: security reviews, integrations, adoption or support. We will tell you what we would build and what we would not, and if the answer is a document or a process rather than software, we will say so.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →