Questions firms ask before working with us

The first conversation is free. Beyond that, we quote a fixed price once we both know exactly what is being built, and nothing is charged until the scope and the price have been agreed in writing.

Discovery usually takes one to two weeks. Build time depends on the system, and the timetable is fixed in the quote.

No. We handle discovery, design, build, deployment and testing. Your team's role is to explain how the work is done today and to approve what we propose.

It does not go live until that question has been answered with evidence. Every new system first runs in shadow mode: it works on your real cases alongside your team, but changes nothing and contacts no one. You compare its output with your team’s for as long as you need to, and it goes live only when you are satisfied and decide to switch it on. Once live, anything it is unsure about is passed to a person.

No. Every system sits in your own cloud account, is built on standard, well-documented technology that any competent developer can maintain, and is handed over with full documentation. You can keep us on for support, but you never have to.

Your data stays in your own environment wherever the work allows. Access is limited to what each system needs, every action is logged, and a person approves anything that requires judgement. Data is handled in line with UK GDPR and is never used to train AI models. The same rules apply to any broker or coverholder data involved.

The policy administration, document management and email systems you already use, and the spreadsheets that sit between them, including each coverholder’s own bordereaux layout. Compatibility is confirmed during discovery, before you commit to anything.

Yes, and that is the usual case. Re-architecting a live retrieval pipeline is done against a copy of your own question set, measured before and after, with the new path proved in shadow mode before any traffic moves to it. Nothing is cut over until the numbers are in front of you.

By measuring both at once. Model selection is set per task and tested against a fixed question set, caching is added wherever the system repeats work, and prompt payloads are stripped back to what each task needs. Accuracy and cost are tracked on every change, so a saving that degrades answers shows up immediately rather than in a complaint.

Your data stays in your own environment wherever the work allows. Access is limited to what each system needs, every action is logged, and nothing leaves your environment unless you decide it should. Data is handled in line with UK GDPR and is never used to train AI models.

Your existing document stores, data rooms, CRM and reporting tools, as they are. In the retrieval case study on this site, the client did not have to change any of its own systems.

Your data stays in your own environment wherever the work allows. Access is limited to what each system needs, every action is logged, and a person approves anything that requires judgement. Data is handled in line with UK GDPR, it is never used to train AI models, and a data processing agreement is provided as standard.

The practice management, bookkeeping, billing and email systems you already use, including Xero, QuickBooks, Sage, IRIS, TaxCalc, Karbon, Dext and BrightManager. Compatibility is confirmed during discovery, before you commit to anything.