Case Studies | GovTech

Putting a navigation model for visually impaired users on AWS

Model Deployment on SageMaker

About

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

Challenge

The engagement had three focus areas, each aimed at proving AWS as the platform for the client's model.

Making the existing model queryable

The client's model needed to be deployed so the app could call it reliably. That meant hosting it on managed infrastructure and exposing an endpoint that could be queried through an API, rather than leaving the model as something that only ran in isolation.

Storing the data securely

The training data and the model itself needed a secure, well-permissioned home in the cloud, so the model could be served and future work could build on the same foundation.

Setting up for future retraining

This was not only about serving today's model. The client wanted the architecture in place to retrain and improve models as more data is collected, so the deployment had to leave a clear path for ongoing model development.

Solution

Cloud Combinator ran the work as a staged cloud accelerator, moving from understanding the product to a working deployment and a best-practice review, with the client's technical lead upskilled along the way.

1 endpoint

Positioning model hosted on SageMaker, queryable via API and Lambda

6 stages

Cloud accelerator, discovery through Well-Architected review

$1.2k

Indicative monthly AWS run rate for model hosting (projected)

By the numbers:

  • 1 endpoint - Positioning model hosted on SageMaker, queryable via API and Lambda
  • 6 stages - Cloud accelerator, discovery through Well-Architected review
  • $1.2k - Indicative monthly AWS run rate for model hosting (projected)
Changes

Acceptance was met when the model was deployed in SageMaker with its endpoint queryable through an API, and AWS was demonstrated as a suitable environment for the client to continue developing the product. The engagement left the client with a hosted model, secure data storage, and an architecture ready for future retraining.

  • Model deployed and queryable — The existing model runs on Amazon SageMaker with an endpoint the app can call through an API handled by AWS Lambda.
  • Data stored securely — Amazon S3 holds the client's data with appropriate permissions, ready to serve the model and support further work.
  • Retraining-ready architecture — The setup leaves a clear path to train and deploy new models as more data is collected.
  • Image classification demonstrated — An Amazon Rekognition model shows AWS-based image classification relevant to the client's visual positioning service.
  • Handover — A Well-Architected review and a full walkthrough leave the client's technical lead able to continue model development in SageMaker.

With the model live on SageMaker and AWS proven as a suitable platform, the client is positioned to scale the service to more users and venues, and to retrain and improve its models on the same foundation as it gathers more data.

AWS Stack

Amazon SageMaker

For hosting and serving the client's navigation model as a queryable endpoint.

Amazon S3

For secure, well-permissioned storage of the data and model.

Amazon API Gateway

And AWS Lambda for handling queries to the model endpoint.

Amazon Rekognition

For demonstrating AWS-based image classification for the visual positioning work.

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.