Case Studies | SaaS B2B

Bringing generative AI to marketing performance

LLM Evaluation of Marketing

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, each of which had to be addressed for the solution to be viable in production.

Turning open questions into reliable AI advice

The client needed users to submit natural language queries and receive tailored guidance on improving their email marketing. That meant designing prompts and a pipeline that produced consistent, useful feedback rather than generic output, and doing so within the usage and cost limits of a shared LLM service.

Benchmarking performance against the wider market

A second requirement was to let users input their campaign performance metrics and generate a LLM-authored report comparing them with competitors in their sector and country. This required the client's own comparison

Doing it safely and handing it over

Because the platform would let end users prompt a LLM directly, guardrails were essential to prevent improper use. The solution also had to be deployable into the client's own AWS account and understood by their technical lead, so the team could operate and extend it after handover.

Solution

Cloud Combinator ran the engagement as a staged accelerator, pairing consultancy and enablement with the build so the client finished with both a working solution and the knowledge to run it.

2

Generative AI pipelines delivered on Amazon Bedrock

~20k

Campaign evaluations per month at design scale (projected)

100%

Serverless, deployed via CloudFormation to the client's account

By the numbers:

  • 2 - Generative AI pipelines delivered on Amazon Bedrock
  • ~20k - Campaign evaluations per month at design scale (projected)
  • 100% - Serverless, deployed via CloudFormation to the client's account
Changes

The engagement delivered against its original scope: two working generative AI pipelines, built on a secure serverless foundation, deployed into the client's own AWS environment and demonstrated as a suitable base for the client to continue developing the product.

  • Tailored email feedback — Users can submit an email in natural language and receive specific, actionable guidance on how to improve it, grounded in the client's own documentation.
  • Market benchmarking reports — Users can generate a LLM-authored report that compares their campaign performance with similar organisations in their sector and country.
  • Safe by design — Guardrails were configured so that end users can prompt the model directly without exposing the platform to improper use.
  • Cost-aware architecture — Queuing through Amazon SQS paces requests to the model, keeping the solution within usage limits and predictable to run.
  • Handover — A recorded walkthrough and a handover meeting left the client's technical lead able to operate and extend the pipelines inside their own AWS account.

With two proven Bedrock pipelines and a serverless foundation of their own, the client is well placed to widen the range of AI-driven insight it offers, no longer just reporting on marketing performance but actively advising users on how to improve it.

AWS Stack

Amazon Bedrock

For secure, managed access to large language models that generate the feedback and reports.

AWS Lambda

For serverless compute that runs each pipeline without managing servers.

Amazon API Gateway

For the entry point that lets users submit queries and receive results.

Amazon SQS

For pacing requests to the language model within usage limits.

Amazon S3

For storing the reference documents used to benchmark campaign performance.

AWS CloudFormation

For repeatable deployment of the solution into the client's own AWS environment.

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.