Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. We Improved a Model and a Firm Complained the Results Changed. How Should We Ship Changes?
Problems We Solve

We Improved a Model and a Firm Complained the Results Changed. How Should We Ship Changes?

Law firms validate a legal tech product's outputs, then an update changes them without warning. We build version pinning, change notes and per-firm switch-over.

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

Firms complain when outputs change because they tested your product, built internal guidance around its behaviour, and then an update altered answers without notice. We build versioned features and model settings per firm, side-by-side comparison of old and new outputs, change notes written for knowledge lawyers, and a switch-over each firm controls within a window you set.

A better model, and an unhappy knowledge team

Your team moves a contract review feature to a newer model and adjusts the prompts. On your tests, results are better. A week later, a firm's knowledge lawyer writes: the risk ratings on indemnity clauses have changed, several clauses previously rated amber are now green, and their internal guidance for fee earners was written around the old ratings. Nobody told them. They want to know what changed and whether the old ratings were wrong.

Another firm has not noticed yet, but their innovation team ran a validation exercise on the old version last quarter and presented it to their risk committee.

Why firms treat output changes seriously

Law firms often validate a product before relying on it, and write guidance for fee earners about how to use it. That validation and guidance assume the product behaves consistently. In ordinary software, an improvement is simply good news. In a product whose outputs feed legal work, an unannounced change can undermine a firm's own controls.

  • Model and prompt changes go to every firm at the same time.
  • Release notes describe features, not changes in output behaviour.
  • Firms cannot see old and new outputs side by side.
  • There is no way for a firm to stay on the previous behaviour while it checks the new one.
  • Your own tests show improvement overall, but not where outputs differ in ways a firm cares about.

What surprise changes cost

A firm that finds outputs changed without warning loses confidence in its own validation, and may suspend use of a feature until it re-checks. The knowledge team has to rewrite guidance at short notice. Your support team spends time explaining changes after the event. And the next time you want to improve a model, firms will push back, which slows the improvements your product depends on.

How we build changes firms can plan for

What we build lets you keep improving while each firm moves on its own terms.

  1. Versioned feature behaviour: each AI feature has a version made up of model, prompts and settings, and each firm is on a specific version.
  2. An evaluation comparison before release, run on your test set, showing where outputs differ between versions and by how much, grouped by clause type or question.
  3. Change notes written for knowledge lawyers: what changed, why, where outputs differ and examples, rather than a line in a release log.
  4. A preview mode where a firm can run the new version on its own sample documents and see old and new outputs side by side.
  5. Firm-controlled switch-over within a window you set, with a default date so firms do not stay on old versions for ever.
  6. A record per firm of which version produced each output, so past work can be explained after a switch.
StageWhat the firm sees
New version readyChange notes and comparison examples
PreviewOld and new outputs side by side on their documents
DecisionSwitch now, or at the default date
After switchEvery output labelled with the version that produced it
Questions laterRecord of version per output for past work

Older versions are supported for a defined window, not indefinitely. That window is a commercial decision for you, and making it explicit helps firms plan.

The next model change

Your team prepares a new version of the contract review feature. The evaluation comparison shows most outputs unchanged and a group of indemnity ratings that differ, with examples. Change notes go to each firm's knowledge lead. One firm previews the new version on a set of its own contracts, agrees the new ratings are better, updates its guidance and switches early. Another waits for the default date. Nobody is surprised, and every output shows which version produced it.

Do your updates surprise firms?

  • AI model or prompt changes go to every firm at once.
  • Firms find out outputs changed from their own users.
  • You cannot show a firm where old and new outputs differ.
  • Firms cannot stay on the previous version while they check.
  • Past outputs are not labelled with the version that produced them.

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

Does supporting several versions slow development?

Some, which is why versions are supported for a set window. The model layer keeps the cost down by making versions a configuration, not separate code.

What if a provider retires the model a firm is using?

The firm is moved to a newer version with notice and a comparison, following the same process as any other change.

Do small prompt fixes need the full process?

Not always. We help you set a threshold, so changes that do not alter outputs meaningfully go out with a short note.

What do you need from us?

Your AI feature code, your current test examples, and any complaints firms have made about changes.

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 →