PROFESSIONAL SERVICES · SYSTEM

AI drafting from your own precedents

IN SHORT

Draft from your own precedents and the actual file, not from the open internet — so the fee earner edits a grounded first version and can see exactly which precedent and which document each part came from.

The problem

Routine drafting is a large share of chargeable time and almost none of it is original. The fee earner finds the last similar letter, copies it, and carefully removes the previous client's details — a process that is both slow and the source of the most embarrassing errors a firm makes. Meanwhile the firm's genuinely good precedents sit in a document management system nobody can search in plain English.

How it works

Your precedents, standard documents and past advice are indexed into a knowledge base restricted to your firm. When a draft is requested, the system retrieves the right precedent and the relevant facts from the live matter file, and produces a first version with the client's actual details, dates and figures in place. Every substantive statement is traceable to its source — this clause came from that precedent, this figure from that document — so review is verification rather than proofreading.

Where the money is

In recovery rather than raw hours. Routine drafting is frequently written down because clients will not pay full rate for a letter they know is standard. Producing it in a fraction of the time turns written-down work into recovered work, and it releases senior time towards the matters that justify senior rates.

What stays with your people

Everything that constitutes advice. Nothing generated is sent without a qualified person reading, amending and taking ownership of it. The system is a very fast, very literal assistant that has read every file — it is not a fee earner and it does not carry your indemnity.

What you get

  • Grounded in your own precedents, not general internet text
  • Facts, dates and figures pulled from the live matter file
  • Every substantive statement traceable to its source document
  • Plain-English search across your own past advice and precedents
  • Drafts logged against the matter with a record of who reviewed them

Questions we get asked

Does it invent case law or figures?
It is built specifically to avoid that. Retrieval is restricted to your own documents, outputs carry citations back to the source, and anything it cannot ground it flags as missing rather than filling in. That is also why a qualified review is non-negotiable and built into the workflow rather than assumed.
Is our client data used to train models?
No. Systems are built inside your own tenancy, and model routing is documented so you can answer a client or a regulator precisely about where data goes and what is retained.
Which documents are worth starting with?
The highest-volume, most standardised ones — the letters you have written a hundred times and write down every time. Bespoke advice is the last thing to touch, not the first.

TRUST & CREDENTIALS

How we work, and what stands behind it

This page is maintained by Forth Systems. Everything listed below describes our own team, hosting choices and the technologies we build on — it is a statement of practice, not an independent certification or an endorsement by the vendors named.

UK team & data residency

Who builds it, and where your data sits while they do.

  • UK-based engineers

    Edinburgh-headquartered. Every system is designed, built and supported by our own UK-based engineering team — no offshore delivery pool.

  • UK / EU hosting by default

    Applications and databases are provisioned in UK or EU regions unless you require otherwise, with encryption in transit and at rest.

  • Human-in-the-loop by design

    Every AI system we ship keeps a manual override. Nothing irreversible happens without an operator able to review, edit or stop it.

  • Audit trails as standard

    Automated actions are written as first-class records — who or what did it, when, against which input — so operations stay evidence-ready.

Systems we build on

The platforms our systems run on. These are the technologies we deploy and support — not sponsorships or reseller badges.

  • OpenAI, Anthropic & Google models

    Model-agnostic delivery. We route each workload to the model that fits it on cost, latency and accuracy, and can switch without a rebuild.

  • Supabase & Postgres

    Row-level-security Postgres as the operational spine under every platform we run.

  • Stripe payments

    Payment capture, checkout and reconciliation wired directly into job and permit workflows.

  • Xero, Sage & HubSpot integrations

    Production integrations into the finance and CRM systems UK operators already run, so automation lands where the business keeps its records.

Streetworks & industry credentials

Operational domains we build in daily, with the sector systems we integrate against.

  • DfT Street Manager integration

    The permit chain we built for Kerbco creates and tracks streetworks permit applications against DfT Street Manager and local highway authority processes.

  • NRSWA-aligned workflows

    Permit, reinstatement and traffic-management workflows built to the New Roads and Street Works Act process contractors are inspected against.

  • Traffic management planning

    Roadplan produces signing and guarding layouts for council submission and for the crew installing them on site.

  • Operator-built, not consultancy-built

    Our platforms are built around real operating workflows — including the permit chain we built for our client Kerbco, a Scottish drop kerb contractor.

Insurance certificates, registration numbers and security documentation are available on request — ask the team.