Start a conversation

What helps us answer well

• The process as it happens today, with rough volumes and who is involved.
• The systems that hold the data, and who owns them.
• Any hard constraint: data classification, hosting, a regulator, a deadline.
• Whether an NDA is needed before documents are shared — say so and we send ours first.

Before the first call

Do you work with our existing systems, or do we have to move?

We integrate with what you run. Replacing a system of record is almost never part of an AI project, and the cost of doing it usually dwarfs the benefit.

What if the data cannot leave our environment?

Then the model runs inside your environment. We deploy open-weight models in your cloud tenant or on your hardware, and state the accuracy trade-off in writing before the work starts.

How do you prove the system is good enough?

With a test set built from your own cases. Retrieval and answer quality are scored separately, and the same suite runs on every change so a regression is visible immediately.

Can we sign an NDA before sharing documents?

Yes, and it is normal at this stage. Say so in the enquiry form: we will sign yours or send ours before any detail is exchanged.

Do you take fixed-price work?

Stages are fixed price and agreed in writing before they start. The discovery sprint exists to make that number reliable instead of optimistic.