Case Studies | SaaS B2B

Turning inbound emails into structured scope

PoC - LLM Email Processing

About

A SaaS B2B business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The challenge had three focus areas that the proof of concept needed to address.

Manual email triage

Each incoming enquiry had to be read and interpreted by hand to scope the work. At volume, this was slow, inconsistent and a bottleneck on the sales pipeline.

Detail locked in attachments

Much of the useful information arrived as attached documents rather than in the email body. The system needed to read those files reliably and pull out the relevant content.

Output the team could actually use

Extracted information was only valuable if it landed in an usable form, so the pipeline had to produce structured output, as a file or via an API, that the client could integrate into their own systems.

Solution

Emails are extracted from Outlook and passed into an AWS-hosted pipeline. Attached documents are read with Amazon Textract, and the combined content is processed by a large language model in Amazon Bedrock, invoked through AWS Lambda, to extract the key information the client needs to scope each job.

3

Output options: text file, Excel or an API endpoint

2

AI services combined: Amazon Bedrock and Amazon Textract

100%

Serverless pipeline built on AWS Lambda

By the numbers:

  • 3 - Output options: text file, Excel or an API endpoint
  • 2 - AI services combined: Amazon Bedrock and Amazon Textract
  • 100% - Serverless pipeline built on AWS Lambda
Changes

The proof of concept met its acceptance criteria, demonstrating that Amazon Bedrock and Amazon Textract can automate email and document processing end to end, and validating AWS Bedrock as a suitable platform for the client to build on.

  • Automated scoping — Inbound emails are read and interpreted automatically, removing the manual triage step from the sales process.
  • Attachments handled — Amazon Textract extracts detail from attached documents so nothing useful is missed.
  • Integration ready — Structured output is delivered as a file or via an API endpoint, ready to flow into the client's CRM or applications.
  • Platform validated — The build confirmed Amazon Bedrock as a suitable foundation for the client's in-house LLM email processing tool.
  • Handover — Cloud Combinator delivered the solution with an immersion session and knowledge transfer so the internal team could continue the model's development.

With the approach proven, the natural next step (projected) is to integrate the pipeline into the client's existing application and extend the model to cover more of their enquiry types, building on the foundation delivered in the proof of concept.

AWS Stack

Amazon Bedrock

For large language model processing of email content.

Amazon Textract

For extracting text and data from attached documents.

AWS Lambda

For serverless model invocation and pipeline logic.

Amazon API Gateway

For delivering structured output to client applications.

Amazon S3

For secure storage of source data and results.

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.