Skip to content
SaaS Platforms · Anonymised — SaaS platform, financial services · 2026

Adding AI summarisation to a regulated SaaS product, without breaking the audit

Shipped the first AI feature into a regulated product — with evals, guardrails, and cost monitoring designed in from week one.

The situation

What was happening before we got involved.

A compliance-heavy SaaS product wanted to add AI summarisation to a workflow where the wrong answer would be a serious problem. They'd seen demos, run their own prototypes, and stalled on the question every regulated team eventually hits — how do you make it safe enough to ship?

What we did

The decisions we made, and why.

  1. 01

    Evals before the feature

    Built the evaluation harness in week one, against examples the product team chose, including the edge cases that the demo had quietly avoided. Every prompt change ran the evals before merging.

  2. 02

    Guardrails as code, not policy

    Hard limits on what the model could do, enforced before the response reached the user. A fallback path for when the model failed an internal check. A clearly labelled "human review" route for cases the system wasn't sure about.

  3. 03

    Cost as a first-class metric

    Tracked cost per summary from day one, with alerts on outlier calls and a daily dashboard. The product team could trade quality and cost as a deliberate decision, not a surprise.

The outcome

What changed, in production.

AI summarisation has been live in the product for nine months at the time of writing, through three internal audits and one external review without compliance incident. The feature handles roughly 4,000 summaries a day at a steady cost per call that's been tunable since launch.

Working on something similar? Let's talk.

Liverpool, UK. Available across the UK and remote.

What happens next...

Someone on the team usually replies within a working day.

  1. 01

    We read every message

    Usually within a working day. The first reply comes from a person on the team, not an autoresponder.

  2. 02

    If there's a fit, we set up a 30-minute call

    We listen, ask questions, and try to work out whether we're the right people for what you're building.

  3. 03

    If we can help, we send a written proposal within a week of the call

    An honest indicative range, a shape for the engagement, and the people we'd put on it.