Case Studies | SaaS B2B

Turning shift emails into insight

LLM Extraction of Shift Details

About

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

Challenge

The proof of concept set out to solve three problems.

Unstructured, inconsistent emails

Shift emails arrived in a wide variety of formats, with single or multiple shifts each. The first focus was to prove that an Amazon Bedrock model could reliably extract the shift details and tell individual shifts apart.

No way to analyse the data

Without structure there could be no analysis. The second focus was an automated pipeline that took emails received through Amazon SES, had the model extract the details, and inserted them into a relational database ready for querying.

Safe, trustworthy processing

Handling inbound email with AI needs guardrails. The final focus was a check to confirm each email genuinely came from a healthcare provider and was not an attempt to misuse the AI service, all within a secured environment.

Solution

Cloud Combinator delivered the work through its AI and ML Project Accelerator, from understanding the client's data to a working, secured pipeline in their account.

SQL-ready

Shift data structured in Amazon RDS for analysis

1,000/mo

Emails the design was costed for (projected)

PoC

Proof of concept via the AI and ML Project Accelerator

By the numbers:

  • SQL-ready - Shift data structured in Amazon RDS for analysis
  • 1,000/mo - Emails the design was costed for (projected)
  • PoC - Proof of concept via the AI and ML Project Accelerator
Changes

Cloud Combinator delivered a working proof of concept that met the success criteria: Amazon Bedrock reliably extracting shift details from varied emails and distinguishing multiple shifts, an automated SES-to-RDS pipeline, and example SQL queries proving the data could be analysed. The solution was deployed in the client's AWS environment with a demonstration and documentation.

  • Structure from chaos — Amazon Bedrock turns inconsistent, free-form shift emails into clean, structured records, distinguishing multiple shifts within a single email.
  • Analytics unlocked — With shift data in Amazon RDS, the client can run SQL to see which healthcare providers are their biggest source of work.
  • Safe by design — A Bedrock misuse check screens inbound email, suspicious content is logged to CloudWatch, and the pipeline runs inside a VPC with secrets managed securely.
  • Built to extend — The data store was designed so the client can layer further analytics, such as Amazon Q, on top in future.
  • Handover — Included a demonstration, example SQL queries, and the materials and documentation to run and extend the service.

With shift data now structured and queryable, the client has the foundation to make source-led decisions about where to focus, and a clear route to richer analytics and natural-language querying as the product grows.

AWS Stack

Amazon SES

For receiving shift emails from healthcare providers.

AWS Lambda

For orchestrating the screening, extraction and storage steps.

Amazon SQS

For throttled processing that keeps within Bedrock service limits.

Amazon RDS

For storing structured shift data ready for SQL analytics.

AWS Secrets Manager

And Amazon VPC for secure credentials and network isolation, with Amazon CloudWatch for logging.

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.