Question 1

What does this cost?

Accepted Answer

There is no price list. Effort follows scope, and scopes differ too much for a number on a website to be honest. The figure for your institution comes out of scoping and is set out in the proposal. The first call and the assessment pack cost nothing.

Question 2

Who is behind this, and what happens if that person is unavailable?

Accepted Answer

One person, named, with a background that can be checked, plus named subcontractors where specialist knowledge is required. Knowledge base, prompts, evaluation data and operating documentation sit in your repository, not mine — you do not need me to reach them. Cover arrangement and handover period are settled in the contract. The Practice section also states what this practice does not have today.

Question 3

Why not simply use a large vendor?

Accepted Answer

Sometimes that is the right answer: for a brand name in the procurement file, for hundreds of seats across several countries, for an existing framework agreement, for genuine 24/7 availability, or where your procurement requires certifications I do not hold. The section on making sense of the category lists the cases individually, along with the questions to test both routes. If I am not a fit, I will say so on the call.

Question 4

Where does our data sit?

Accepted Answer

In the chat pilot the agent processes public documents only; customer data never reaches it. Transcripts and logs sit in a region you choose. Deployment in a dedicated VPC or in your own data centre is supported by the platform in use, but I have not implemented it — that belongs in scoping and in the contract, not on this page. With hosted inference, prompt content leaves the zone under a processing agreement in a contractually fixed region.

Question 5

What if the agent makes something up?

Accepted Answer

The agent answers only from the approved knowledge base and cites a source for every statement. Where it finds no citation, it says so and hands over. Guardrails additionally apply before and after generation to blocked topics — investment advice, tax guidance, commitments on terms. Error cannot be ruled out; what it is made is detectable and traceable.

Question 6

What happens at 03:00 when the agent answers wrongly?

Accepted Answer

Three things apply independently of one another. First the post-check: without a citation the agent does not answer, it hands over. Second monitoring: [thresholds] on handover rate, answer length and guardrail hits raise an alert to [alerting path]. Third you: every surface carries a reporting route, and your operations team can switch the agent off without reaching me. Confirmed incidents are reported to you within 24 business hours with time, affected sessions and cause.

Question 7

Who can switch the agent off, and how quickly?

Accepted Answer

You can. The kill switch sits in your hands, not mine: the roles you designate in your institution switch the agent off via an API call, without reaching me. The channel then falls back to your existing behaviour — contact form, queue, or opening-hours message. Switching off does not have to be justified.

Question 8

What service hours and response times apply?

Accepted Answer

One person does not have 24/7 availability, and I do not claim any. What is agreed is service hours of 03:30 to 13:30 UTC with [response time] for highest-severity incidents and [response time] below that. Outside those hours what protects you is the kill switch, not my availability — which is why it sits with you. If your institution requires genuine 24/7 cover, that is a reason to choose a larger vendor.

Question 9

Are we told before anything ships?

Accepted Answer

Yes, beforehand. Every change to prompt, guardrails or knowledge state runs against the test set and goes live only after your sign-off. You receive notice before release, with the change, the test result and the rollback path. Model changes made by the provider are announced as soon as I know of them — the fact that I do not control them is part of the disclosure.

Question 10

Who is liable for a wrong answer?

Accepted Answer

Towards your customers, you are — outsourcing does not change that, and any vendor implying otherwise should worry you. What the contract settles is duties of care, service levels and liability between us, backed by professional indemnity cover. Scoping the first stage to public content without authentication keeps the exposure deliberately small while trust is still unproven.

Question 11

How do we get out again?

Accepted Answer

The exit strategy is part of the contract, not a later negotiation. Knowledge base, prompts, transcripts and evaluation data are exportable in open formats at any time. There is no proprietary lock on your content: what you brought in, you take back out in the same form. Export on exit is not charged for.

Question 12

Can this connect to our CRM and telephony?

Accepted Answer

Both are integration paths for Stage 2 and later, not channels that run today. Telephony over SIP depends on the speech platform in use; which handover paths it supports is examined during scoping, before anything is committed. CRM and core banking through defined tool calls with logged input and output, no open database access. In Stage 1, none of it is connected.

Question 13

Why do chat and voice share one configuration?

Accepted Answer

Because two configurations inevitably drift. Separate systems mean two release processes, two audit trails and two sets of answers that diverge further with every product change. Here the channel is a property of the session, not a product of its own: same prompt, same knowledge base, same guardrails, one log.

Question 14

Can we stay on chat alone?

Accepted Answer

Yes. That is a complete state, not half a project. Chat absorbs most of the out-of-hours volume on its own. Voice is available when you want it — it is not a condition.

Question 15

How do customers know they are talking to an AI?

Accepted Answer

In chat through a permanently visible marker, not a notice shown once on opening. In voice through a statement in the first response. In both cases the route to a human stays available and is offered actively on request. You sign off the wording.

Banking

Automate Workflows in Banking