Case Studies | PropTech

From tender to Bill of Quantities in under a day

AI-Powered Quantified-Scope Automation

About

A PropTech business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The challenge had three focus areas, each central to making automated quantification trustworthy enough to rely on.

Effort and cost of manual quantification

At four to five days per tender and around three tenders a month, manual quantification amounts to roughly 70 mandays and about £70,000 of labour each year. The objective was to bring quantification time below half a day per tender.

Extracting structure from messy documents

A tender pack is not clean data. It spans scanned PDFs, drawings and archives running to around 150 pages, and quantities have to be read reliably from tables and specifications before anything can be automated.

Accuracy, security and fit with existing workflows

The output has to land in the team's Bill of Quantities format without disturbing the downstream pricing workflow, stay within a controlled accuracy tolerance, and keep all data inside the UK.

Solution

A tender pack lands in Amazon S3 and triggers a serverless pipeline. Amazon Textract extracts the tables and text from the documents, then Claude on Amazon Bedrock maps the extracted content to the structured Bill of Quantities format, with Bedrock Guardrails keeping the model inside an agreed variance tolerance. AWS Lambda then writes the results into an editable Excel workbook ready for the estimator to review.

<0.5 day

Target quantification time per tender, down from 4 to 5 days (projected)

13

Mandays saved per month once live (projected)

~£70k

Annual manual quantification cost the solution targets

By the numbers:

  • <0.5 day - Target quantification time per tender, down from 4 to 5 days (projected)
  • 13 - Mandays saved per month once live (projected)
  • ~£70k - Annual manual quantification cost the solution targets
Changes

Cloud Combinator delivered a scoped, costed AI solution that converts a tender pack into an editable Bill of Quantities automatically, with a recommended serverless build that reaches production in roughly eight to twelve weeks and a strong return from the first month of use.

  • Automated quantification — Textract and Bedrock turn a 150-page tender pack into a structured, editable Bill of Quantities, removing days of manual transcription per bid.
  • UK data residency by design — The pipeline runs serverless in the London region, keeping tender data inside the UK and minimising the security surface.
  • Controlled accuracy — Bedrock Guardrails hold the model to an agreed variance tolerance, so estimators review a bounded, trustworthy draft rather than raw output.
  • Handover — The client received a recommended build path plus a costed extension option, ready to move from proposal into an eight-to-twelve-week production build.

With quantification reframed as an automated step rather than a manual bottleneck, the client is positioned to bid faster and free its estimators for the higher-value work of pricing and winning tenders.

AWS Stack

Amazon Textract

For extracting tables and text from scanned tender documents.

Bedrock Guardrails

For holding model output inside an agreed accuracy tolerance.

AWS Lambda

For writing the editable Excel workbook and running pipeline logic.

AWS Step Functions

And Amazon EventBridge for orchestrating the serverless workflow.

Amazon S3

For secure, UK-resident storage of tender packs and generated outputs.

YOU MIGHT LIKE

Related success stories

View all case studies

Case Studies | Insights

Utilising Language Recognition, Speed, and Enhanced Security to Make Social Media a Force for Good

  • Here, we take a detailed look at how the Cloud Combinator team collaborated with another cutting-edge AI service provider that provides intelligent systems to “make social media more social” for brands and users alike.
  • Arwen AI is a UK-based startup specialising in AI solutions to manage and enhance brands’ social media interactions. Founded in 2020 by Matt McGrory, Dr. David Cole, and Joel Bailey, Arwen. AI focuses on using AI to automatically detect and remove spam, toxic comments, and other unwanted content from social media platforms.
  • The team at Arwen have three core products. ‘Moderate’ is focused on identifying and removing toxic content from social media channels. ‘Engage’ helps brands identify and engage with meaningful conversations on social media, and ‘Customize’ allows brands to apply bespoke algorithms to their channels - creating an even more effective moderation and engagement.
Read more
CONTACT US

Ready to turn AI into impact?

We'll help you spot the highest-value opportunities, reduce risk around your first AI initiative, and define a clear path to results from day one.

Why talk to us:

Outcome-driven recommendations

AWS-recognised delivery expertise

Risk-aware AI adoption

Clear next step, not a sales pitch

Start with a focused 20-minute conversation about your goals — no pressure, no commitment.

We use cookies

This website uses cookies to enhance user experience and to analyze performance and traffic on our website.

See our Privacy Policy for details.