AI lease analysis for pub advisers.
Pubs Advisory Service · A lease-analysis service built and run
A pub tenant signs fifty pages of legalese to get the keys. The system read the lease and pulled out the thirteen clauses that decide whether the deal works.
Overview
Pubs Advisory Service advise tenants and operators on the commercial leases they are about to sign, which means someone had to read every one of them properly before a single piece of advice could be given. The documents are long, frequently scanned badly, and written in language that takes training to read.
OpenKit built and ran a bespoke document-analysis system for them: a clause library specific to pub leases, a two-stage extraction and answering pipeline behind it, and a batch path for when the work arrived in volume. It ran as an internal production tool, with the maintenance and capacity reporting that implies.
- Thirteen lease clauses configured for pub tenancies.
- A prompt architecture that refuses questions the documents do not answer.
- The same engine ran on a different clause set by swapping the configuration.
13
clauses in the library, each with its own extraction notes and its own search question, written for UK pub commercial leases.
10,000
documents the scheduler takes in a single file, handling each item on its own.
5%
of that capacity in use, measured across every component of the running system.
2
stages in the prompt architecture: pull the clauses out first, then answer strictly from what was pulled.
Challenge
What the service had to get right
Pub leases carry the terms that decide whether a tenant can make a living: how the rent gets reviewed, what the property can be used for, who pays for the repairs, and whether there is a way out at the end. Those terms sit anywhere in fifty pages, often on a page that scanned crooked. Reading fast is how a clause gets missed, and reading every page properly made detailed pre-entry advice expensive enough to price certain conversations out.
- The clauses that matter to a pub tenant, specifically.
- An excerpt attached to every answer, so an advisor confirms it against the lease.
- A plain refusal when the lease does not say, because a confident wrong answer is the expensive failure here.
The library
A clause library built by the advisors
The library encodes the advisors’ own judgement about what matters in a pub lease. Each clause carries its own extraction notes, its own natural-language search question and a description of what a correct answer looks like, which is a domain expert’s knowledge written down in a form the system can execute.
Approach
Inside the extraction pipeline
Split the lease before reading it
The document is cut into overlapping extracts so a clause that straddles a page break is still whole in at least one of them. Textract handles the OCR on the scanned originals, which is where most of the damage happens in this kind of work.
Pull the clauses as question, excerpt, answer
Every clause is pulled on its own terms, and the output is structured: the question asked, the excerpt it was answered from, and the answer itself, so nothing arrives without the text it rests on.
Answer only from what was pulled
The second stage answers free-text questions over the extracted set, constrained to the supplied documents and instructed to say plainly when the lease does not answer the question.
Batches of up to ten thousand documents
Work comes in through an email-triggered path into a batch scheduler, and a post-processor turns the model’s output into clean list markup without touching the words.
The answer
How an answer comes back
Each clause comes back as the question that was asked, the answer in plain terms, and the lease’s own wording underneath it, so an advisor reads the answer and checks the excerpt in the same glance. A rent figure arrives with the review mechanism quoted beneath it.
Operations
How the service was run
OpenKit ran the system as well as building it. What that involved:
- Headroom recorded and countersigned on every component, with the finding stated plainly that no upgrades were needed.
- A review every six months and a written route for raising a problem.
- Running costs measured from the infrastructure, on capacity sized to the volume of work.
Stack
What it was built on
The build
- Custom OCR + LLM pipeline
- Citation-anchored retrieval
- Email integration for advisors
- Google Sheets export
OpenKit certifications
- ISO 27001
- ISO 9001, UKAS-accredited
- Cyber Essentials
Controls on this project
- UK GDPR
- UK data residency
Voice
In their own words
Their deep understanding of our business needs, coupled with their expertise in GPT and Cloud (AWS) software-services, enabled them to navigate complexities and deliver a bespoke AI solution tailored to our operations. The team demonstrated a high level of professionalism and adaptability, ensuring a smooth project delivery.
Other engagements
What could your business do with AI?
Find out with experts who become part of your team. We uncover opportunities, get ideas working, and help your people build on the results. We reply within one working day.
Get in touch AI Audit