Service 02 of 04

AI development,evidence first

We build agents that answer from content you own and say so. The interesting engineering is not the answer — it is knowing when there isn’t one. That is the part most demos skip and every real deployment needs.

Who this is for

Organisations where getting it wrong has a cost.

Customer service teams with predictable, high-volume questions your pages already answer — and where being wrong is not acceptable.

Organisations that want their content to be answerable and cited, not interpreted or improvised.

Teams where the answer to 'why did it say that?' needs to trace to a specific page, not a model's generalisation.

Not for organisations wanting an agent to improvise, speculate, or answer questions their pages do not address.

The evidence contract

Five properties every agent we ship has to hold.

01

Grounded

Retrieval runs over sources you control — your pages, your policies, your documents. No open-web fallback, so an answer can never come from somewhere you have not approved.

02

Cited

Every reply carries the page it came from, as a link the reader can check. Citation is part of the answer's layout, not a tooltip.

03

Refusing

With no supporting source the agent declines and routes to a human. We design that state first, because it is the one that protects you.

04

Evaluating

A question set drawn from your real support history, run on every change, with refusal rate and citation accuracy tracked as first-class numbers.

05

Logged

Every question, retrieval and refusal is inspectable by your team. You can read what people asked and what the system did about it.

The refusal, in practice

“I can’t answer that
from our pages.”

A guest asks: can I check in early? The agent retrieves the page that covers check-in times. If the page says from 3pm, subject to availability, contact reception — it says exactly that. If the page says nothing about early check-in, it says plainly: I cannot find that in our pages, here is how to reach reception. It does not invent a policy. That second case is designed before any answer is written. The refusal is not a fallback — it is the feature.

What we will not build

Agents that answer from the open web while wearing your brand.

Anything that impersonates a named member of your staff.

Automated decisions on people — hiring, credit, admissions, grades.

Training on your customers' data without their explicit consent.

Engagement

What a build looks like.

Four stages, in order. The refusal case before the happy path, every time.

01

Read your pages and support history

Before any code, we read what your visitors actually ask. We identify the questions your pages cover, the ones they almost cover, and the ones they cannot answer at all.

02

Design the refusal case

The first thing we write is what the agent says when it does not know. That state is designed before we write a single answer. It is the one that protects your brand.

03

Build the question set

A representative set drawn from your real traffic, not made-up examples. Every answer and refusal is reviewable before go-live.

04

You review before it ships

You see every answer and every refusal in the question set. One you are not satisfied with means we do not ship. No exceptions.

What we build

Grounded chat & support agents

Public-facing or internal. Agent AI Chat is our own, in production.

Retrieval over your content

Ingest, chunking and freshness for sites, handbooks and PDFs.

Model integration into existing tools

Inside the CRM or admin your team already opens each morning.

Evaluation & guardrail work

Often on someone else's build, as a day-rate engagement.

Enquiry

Tell us what you’re building.

Six fields. No discovery call before we’ve read anything — send this and you’ll get a written reply first.

What is this about

Your name

Email

Company

Budget range

Timing

What you need

What happens next

01

A written reply within one working day — a scope, a question, or an honest no.

02

If it fits, a 30-minute call, after we've both read something.

03

A fixed scope with dates and a handover plan before any invoice.

Or just write to us

hello@futuregen.studio

London · Address to be confirmed

When live, the form composes a message to that address. Nothing stored elsewhere.

Destination address not set — configure it before this ships.

Agent AI Chat

Start .

Email

Your site URL

Subscription backend not yet connected — configure it before this ships.