AI Chatbots · United Kingdom

AI chatbots and the transcript problem

Nobody plans to collect health data through a support chat. It arrives anyway, in the third message, because a customer explains why they need a refund. That is the UK data-protection problem with chatbots, and it is a design problem, not a policy one.

The failure mode is free text

A chatbot is the only system you will build where the user chooses what data to give you. Forms constrain input. Chat does not.

You can design a support bot intending to handle order status and delivery windows, and it will handle order status and delivery windows. It will also receive, without being asked, the customer explaining that they need to change a delivery because they are in hospital, or that they missed a payment because of a bereavement, or that a name on an account has changed. Under UK GDPR that is special-category data under Article 9, held to a materially higher standard than the order number sitting next to it in the same transcript.

Your terms of service cannot prevent this. A banner asking people not to share sensitive information does not stop them and does not help you afterwards. The only things that work are architectural.

What we design in, before the bot answers a single question

Retention that is short and enforced. A defined lifetime for raw transcripts, applied by a job that actually runs, decided before launch rather than after the first subject access request. Undefined retention is the norm because storage is cheap; it is also how a two-year archive of unredacted customer conversations comes to exist.

Redaction at the boundary. Strip or hash obvious identifiers before a transcript is stored or forwarded to a model provider. This does not catch everything — nothing catches everything in free text — but it substantially reduces what accumulates.

Separate the transcript from the metric. Most of the business value in chat logs is aggregate: which questions recur, where the bot fails, how often a conversation escalates. That value survives de-identification completely. Derive the metrics, keep those, and let the raw text expire.

Know what leaves. Every message sent to a model provider is a transfer. The UK page covers where our processing happens and who the sub-processors are; for a chatbot specifically, the provider’s retention and training-use terms are a scoping decision with a named answer, not a default inherited from whichever SDK was fastest to wire up.

Subject access requests, which are the real test

A UK customer can ask for a copy of their personal data, and you have a month. For most systems that is a database query. For a chatbot it is a question about whether you can find every conversation that person had, across sessions, including the ones where they were not logged in.

If the answer is “we would have to search free text for their name”, the system was not designed for the jurisdiction it operates in. Designing for it means a resolvable link between a person and their transcripts, and — just as importantly — a retention policy short enough that the search space stays small.

The same design makes erasure requests tractable. These two obligations are why the retention decision belongs at the start.

PECR, briefly, because it is not GDPR

The Privacy and Electronic Communications Regulations sit alongside UK GDPR and govern storage and access on a user’s device. A chat widget that sets a session cookie to maintain the conversation is likely covered by the strictly-necessary exemption. One that persists an identifier to recognise returning visitors, or feeds an analytics product, is not, and needs consent obtained the same way your other non-essential cookies do.

This matters mostly because chat widgets are often added by a different team from the one that owns the consent banner, and the two are rarely reconciled. Worth checking what yours writes.

What this changes about the engagement

The scoping conversation starts with retention and redaction rather than with conversation design, and the written plan from discovery states what is stored, for how long, where, and how a subject access request is answered. That document is what your DPO needs and it is the same one that makes the build estimable.

Contracting, currency and hours are as set out on the UK page — quoted and invoiced in USD, contracted under Colorado law, with the working overlap in your afternoon.

Questions from United Kingdom buyers

Before you
ask us.

A consultation costs nothing. Bring what’s slow, manual or breaking and we’ll tell you honestly whether it’s worth building — including when the answer is no.

Is a chat transcript personal data?

Almost always. Even without a name, a transcript tied to a session, an account or an IP address relates to an identifiable person. Treat it as personal data from the start; the alternative is discovering it during a subject access request.

What about special-category data?

This is the one people miss. You cannot stop a customer volunteering their health, their religion or their trade union membership in free text, and the moment they do, that transcript is Article 9 data with a much higher bar for lawful processing. The mitigation is retention and redaction by design, not a line in your terms telling people not to do it.

Do cookie rules apply to the chat widget?

PECR governs storage and access on the user's device, and most chat widgets set at least a session identifier. If it is strictly necessary to provide the service the user requested, it can be exempt from consent; anything doing analytics or persistence beyond that is not. It is worth checking what your widget actually writes rather than assuming.

How long should transcripts be kept?

Shorter than you think, and defined before launch. Storage is cheap, which is exactly why undefined retention is the default and why it becomes a liability. We usually land on days-to-weeks for raw transcripts with a longer window for derived, de-identified metrics.

Let’s talk

Bring us your
biggest challenge.

Describe the workflow, the systems it touches, and what a wrong decision costs. We work with United Kingdom clients remotely; the engineering is the same either side of the Atlantic.

Eagle County, Colorado · working worldwide Higher ideas. Real impact.

Talk about ai chatbots

Tell us what’s slow, manual, or breaking. We’ll say honestly whether it’s worth building—including when the answer is no.