Case Studies | Healthcare & Life Sciences

From manual scoring to AI-graded wellbeing insight

AI Wellbeing Audit Platform

About

A Healthcare & Life Sciences business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The engagement concentrated on three focus areas, each central to replacing manual grading with a trustworthy automated process.

Automating a manual, subjective grading process

Every audit was read and scored by hand across five competencies. This was slow and difficult to apply consistently at scale, so the platform needed to grade each response, roll scores up to a section average, and produce an overall result that matched the judgement of a human assessor.

Understanding free-form answers, not tick boxes

The client wanted respondents to answer in their own words rather than choosing from multiple-choice options. That shifted the problem from simple tallying to genuine language comprehension, which is where a large language model on Amazon Bedrock earns its place.

Trust, safety and data confidentiality

Because the platform handles sensitive workplace and wellbeing information, it needed a guardrail against misuse of the AI and a design that keeps documents secure and supports compliance and regulatory requirements throughout.

Solution

Audit responses are submitted as a structured JSON payload through an API and placed onto an Amazon SQS queue that feeds an AWS Lambda function. That first stage calls Amazon Bedrock to run a misuse check on the input. If the content fails the check, a message is returned to the caller and processing stops.

5

Wellbeing competencies graded automatically by the LLM

2-stage

Bedrock pipeline with a built-in AI misuse guardrail

Free-form

Open responses replacing multiple-choice answers

By the numbers:

  • 5 - Wellbeing competencies graded automatically by the LLM
  • 2-stage - Bedrock pipeline with a built-in AI misuse guardrail
  • Free-form - Open responses replacing multiple-choice answers
Changes

The proof of concept met its scope: it demonstrated that Amazon Bedrock, using Anthropic's Claude model family, is a suitable platform to automate the client's wellbeing audit and grade free-form responses across all five competencies with question-level, section-level and overall scoring backed by evidence.

  • Automated grading — The platform grades each response and returns per-question scores, per-section averages with evidence, and an overall audit summary, replacing manual analysis across the five competencies.
  • Free-form comprehension — Respondents can answer in their own words, with the LLM interpreting and scoring open text rather than relying on multiple-choice inputs.
  • Built-in guardrail — A first-stage misuse check screens every submission before it reaches the grading model, blocking and explaining rejected inputs.
  • Evidence-backed reporting — Scores at question, section and audit level are accompanied by summaries and supporting evidence, giving employers defensible, actionable insight.
  • Handover — The solution was deployed via CloudFormation into the client's own AWS environment and tested for function, with acceptance tied to sign-off that Bedrock had met the original scope.

With Amazon Bedrock validated as a suitable foundation, the client is positioned to continue developing its application on AWS and extend automated, evidence-backed wellbeing reporting to more organisations.

AWS Stack

Amazon Bedrock

For large language model grading of free-form audit responses using Anthropic's Claude model family.

AWS Lambda

For serverless compute that runs the misuse check and grading stages.

Amazon SQS

For decoupled queuing between the intake, guardrail and grading stages.

Amazon API Gateway

For receiving audit submissions and returning results to users.

Amazon Virtual Private Cloud

For network isolation for the audit workload.

AWS CloudFormation

For repeatable deployment into the client's own AWS account.

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.