Case Studies | SaaS B2B

Bringing generative worldbuilding to AWS

Model Deployment on SageMaker

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 central to putting the model on a footing it could grow from.

Moving the model off local development

The existing model had been built and run locally, which capped how much it could be used. The core requirement was to take that model as it stood and stand it up in Amazon SageMaker so it could be served reliably rather than from a developer's machine.

Scaling with demand

Higher usage of the product meant the model had to cope with variable load. The endpoint therefore needed an auto-scaling policy so it could expand and contract with demand rather than being fixed to a single size.

Secure data and a confident handover

The client's data and model artifacts had to be stored securely, and their technical lead needed to leave the engagement able to operate and continue developing the model within SageMaker, supported by a workshop and a full explanation of the setup.

Solution

Cloud Combinator ran the engagement as a staged accelerator, combining consultancy and enablement with the deployment so the client finished with a working endpoint and the knowledge to run it.

SageMaker

Auto-scaling model endpoint deployed in AWS

Local to AWS

ML capability moved off local Python onto managed AWS

S3

Secure storage for model artifacts and data

By the numbers:

  • SageMaker - Auto-scaling model endpoint deployed in AWS
  • Local to AWS - ML capability moved off local Python onto managed AWS
  • S3 - Secure storage for model artifacts and data
Changes

The engagement met its objective: the existing the client model was stood up in SageMaker, proven in use and handed over, demonstrating SageMaker and AWS as a suitable environment for the client to continue developing its product.

  • Model in SageMaker — The client's own model was deployed to a managed SageMaker endpoint, replacing local execution and freeing the team from running it on their own machines.
  • Scales with demand — An auto-scaling policy lets the endpoint expand and contract with usage, supporting the growth the client was aiming for.
  • Secure by design — Data and model artifacts are held in a S3 bucket with appropriate permissions.
  • Consolidated on AWS — The machine learning capability now sits alongside the already AWS-hosted web platform, simplifying how the product is run.
  • Handover — A SageMaker workshop and a full explanation left the client's technical lead able to operate and keep developing the model.

With its model now running on managed, auto-scaling infrastructure, the client is well placed to grow usage of its worldbuilding platform and to build on the wider SageMaker toolset as the product develops.

AWS Stack

Amazon SageMaker

For deploying and serving the model on a managed, auto-scaling endpoint.

Amazon S3

For secure storage of the model artifacts and the client's data.

AWS Identity

And Access Management for the permissions that keep the data and model secure.

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.