Slow client onboarding
ID and AML checks, conflict searches and engagement letters handled by email and PDF mean days pass before a matter opens — and some clients go elsewhere.
Legal & legal tech
AI & Software Development for UK Law Firms & Legal Teams
We build client onboarding, matter workflows, document automation and AI-assisted review for small and mid-size firms, in-house legal teams and legal-tech startups — with confidentiality, conflicts and privilege treated as design requirements from the first sprint.
- Client intake platform built for a boutique law firm
- Lawyers sign off anything AI drafts
- Matter-level access and full audit trails
Industry challenges
Where legal teams lose time and margin.
Most of the friction sits around the legal work rather than in it: onboarding, chasing, re-keying and hunting for the precedent someone drafted last year.
Good first projects
- Online intake with ID, AML and conflict checks built in
- Document automation from approved precedents
- A client portal for updates, documents and e-signatures
- Search across your own know-how, with citations
Drafting from old documents
Lawyers start from the last similar document rather than a maintained precedent, so errors and outdated clauses travel from matter to matter.
Know-how nobody can find
Precedents, research notes and past advice sit in the DMS and in inboxes, so the answer a colleague wrote last year gets researched all over again.
Time recorded from memory
Time is pieced together at the end of the week from calendars and sent items, and unrecorded work is written off without anyone noticing.
Clients chasing for updates
Clients phone and email for progress, documents and next steps, taking fee-earner time that a secure portal would give back.
AI use without a policy
Staff try public AI tools on client documents while the firm is still deciding its approach — a real risk to confidentiality and privilege.
Solutions
What we build for legal teams.
From an intake flow that opens matters properly to AI that finds the right clause — integrated with the practice management system and DMS you already run.
Client intake and onboarding
Online intake, ID and AML checks through your chosen provider, conflict searches and engagement letters, with the matter opened only when every step is complete.
Learn more
Document automation
Questionnaire-driven drafting from your approved precedents — letters, contracts, leases and court forms — so every first draft starts from the current version.
Learn more
Matter workflows
Tasks, key dates, approvals and file reviews built around how each practice area really works, rather than a generic template.
Learn more
Client portals
Secure portals where clients upload documents, sign engagement letters, pay invoices and see how their matter is progressing.
Learn more
Know-how search
Search precedents, research notes and past advice in plain English, with answers that cite the source and respect matter-level permissions.
Learn more
Practice system integrations
Connect intake, portals and AI tools to your practice management, document management, time recording and accounts systems through their APIs.
Learn more
AI use cases
AI that supports legal judgement.
Reading, finding and first drafts — with a qualified lawyer reviewing anything that goes to a client, a counterparty or a court.
Contract review support
Compare an incoming contract with your playbook, highlight deviations and missing clauses, and suggest mark-up for a lawyer to accept or reject.
Clause extraction
Pull change-of-control, assignment, termination and renewal clauses from a data room into a review table, each linked to the page it came from.
Precedent and know-how search
Ask a question in plain English and get an answer drawn from your own precedents and notes, with citations so the lawyer can check every point.
Drafting support
First drafts of letters, attendance notes and routine clauses from the matter file, written for a lawyer to edit and approve.
Enquiry triage
Sort website and email enquiries by practice area, value and urgency, and route each one to the right team. Whether to take a matter on is always the firm’s decision.
Contract request intake
Let the business request NDAs and routine agreements through a form that drafts from approved templates and flags anything outside policy for a lawyer.
Technology & integration
Built around the systems your firm already runs.
Most firms already have a practice management system and a DMS. We integrate through their published APIs, and tell you early if a supplier offers no API.
Practice and document systems
Practice management APIsDocument management APIsEmail and calendar integrationTime recording and billing
Documents and signatures
Precedent and clause librariesWord and PDF generationE-signature integrationVersion comparison
Onboarding checks
ID and AML check providersSanctions and PEP screeningCompanies House APISource of funds questionnaires
Applications
Next.js and ReactNode.js and TypeScriptPythonPostgreSQL
Hosting and identity
AWS, including UK regionsSingle sign-onEncrypted storage and backupsInfrastructure as code
AI
LLMs with retrieval (RAG)Clause extractionOpen models in your own cloudEvaluation sets and citations
Security & data
Confidentiality, built into the architecture.
Confidentiality and privilege shape how we design, host and log — not just the policy document. These are the practices we apply by default.
Matter-level permissions
Access by matter and team, with information barriers where a conflict calls for one — applied to search and AI as well as to documents.
No training on client documents
AI runs under business terms that exclude training on your data, which we confirm for your chosen provider, or on open models inside your own cloud.
Data residency by design
UK hosting where your policies or clients require it, and a clear record of every service that processes client data — AI providers included — and where.
Full audit trails
Who opened, changed, shared or exported each document and matter, logged so you can answer a client, an insurer or the regulator.
Lawyers stay accountable
AI output arrives as a suggestion with its sources. A lawyer reviews and approves anything that reaches a client, a counterparty or a court.
Evidence for your COLP
Data flows, access controls and suppliers documented so your COLP, DPO and IT lead can assess risk and answer clients’ security questionnaires.
We are a software development company, not a law firm or compliance consultancy, and we do not give legal or regulatory advice. We build to the requirements your COLP, DPO and risk team set under the SRA Standards and Regulations and UK GDPR, and provide the technical evidence they ask for — professional judgement and sign-off stay with your firm.
Relevant work
Products we have designed and built.
From our case studies: a client intake and due-diligence platform for a boutique law firm, covering risk checks, document management and compliance workflows.
All case studiesHow we work
How a legal tech project runs with us.
Seven stages, the same on every project. The length of each one changes with the work; skipping one never saves time for long.
- 01
Discovery
We sit with fee earners, support staff and your COLP to map the process as it really runs, and agree early which data AI may see, where it may be processed and who signs off.
Process map and confidentiality rules agreed
- 02
Strategy
We check what your practice management system and DMS already do, so we build only the gaps rather than duplicating software you already pay for.
Build-or-configure decisions and a first scope
- 03
UX & architecture
User journeys, wireframes and a clickable prototype, alongside the architecture, data model and integration plan that will carry it.
Prototype and architecture decisions
- 04
Development
Two-week sprints with a demo at the end of each, code review on every change, and a staging environment your team can use.
Working software every sprint
- 05
Testing
Alongside functional and security testing, AI features are measured against documents your lawyers have already reviewed, so accuracy is known before anyone relies on it.
Evaluation results your lawyers can check
- 06
Launch
Production deployment with monitoring, backups and a rollback plan, followed by a handover of code, credentials and documentation.
A live, documented product
- 07
Optimisation & support
After launch we fix, measure and improve — a support retainer, a roadmap of next features, or a clean handover to your own team.
Support plan or handover
FAQs
Questions we get asked.
Straight answers on scope, cost, timelines and how we work. If yours is not here, ask us directly.
Is it safe to use AI on client documents?
It can be, with the right set-up: business terms that exclude training on your data, hosting in a region your policies allow, permissions that mirror your matter access, and full logging. Where documents must not leave your environment, we run open models in your own cloud. Your firm decides what is acceptable; we build to that decision.
Can AI review contracts for us?
It can do the first pass — comparing a contract with your playbook, finding missing or unusual clauses and extracting key terms — and show its findings against the text. A lawyer then reviews and decides. We do not build tools that give legal advice to clients without a lawyer in the loop.
How do you stop AI inventing cases or clauses?
Answers are generated from your own documents and cite their sources, so a lawyer can check every point. We test against an evaluation set of your material, show when the system is unsure, and never present unsourced output as fact. UK courts have already criticised lawyers for citing cases that AI made up, so checking is built into the workflow.
Can you integrate with our practice management and document systems?
Usually, through their APIs. Most modern practice management and document management platforms offer one; some older on-premise systems only allow exports or supplier-built connectors. We confirm what is possible during discovery, before designing anything around it.
Can you build client onboarding with ID and AML checks?
Yes. For work in scope of the Money Laundering Regulations, we integrate your chosen ID and screening provider, Companies House data for corporate clients, source of funds questions and conflict searches, so a matter opens only when the checks your policies require are done. Your MLRO sets the rules, and the evidence is stored against the matter.
How do SRA rules affect the software we build?
The SRA Standards and Regulations shape the requirements rather than the technology: confidentiality, conflicts, supervision and treating clients fairly. In practice that means matter-level permissions, conflict checks, audit trails and review steps. Your COLP interprets the rules; we build and document to their requirements.
Do you work with legal-tech startups?
Yes. We help founders scope and build a first version — often intake, document automation or AI review — with the confidentiality controls law-firm buyers ask about in their security questionnaires. You own the code and IP from day one.
How much does legal software development cost?
It depends on scope and integrations. A discovery sprint starts from £2,000 and usually covers one process end to end, such as intake or a document automation pilot. The build is then quoted as a fixed price with milestone billing. AI usage fees and per-check ID costs are running costs we estimate up front.
Start a project
Looking at intake, automation or AI for your firm?
Tell us about the process you want to change and the systems involved. An NDA can be signed before discovery, and we will come back with the questions that matter and a realistic first step.
What happens next
- 1A senior engineer reads your brief within one working day, and replies with questions or a first view.
- 2A 30-minute call to understand the goal, constraints and what good looks like — no sales script.
- 3A written proposal with scope, milestones, team and a GBP estimate you can take to your board.
Techsleight Labs is a trading name of Krapton IT Consultancy.
Explore