Case Studies | SaaS B2B

Smarter tag suggestions, in any language

AI-Assisted Tagging

About

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

Challenge

The proof of concept focused on three areas.

Random suggestions were not helping

Users were shown a random selection of tags rather than relevant ones. The first focus was to suggest tags an user is likely to want, learned from how the client's own users have tagged before.

Learning from the client's own data

Generic models would not capture the client's tagging conventions. The second focus was to train an Amazon Comprehend model on the tagged data the client provided, so suggestions reflected their real usage.

Easy to integrate

The result had to be usable in the product. The final focus was a clean API so a sentence could be sent in and returned with accurate tagging.

Solution

Cloud Combinator delivered the work through its AI and ML Project Accelerator, from understanding the product to a working, tested model in the client's account.

Custom

Amazon Comprehend trained on the client's own tagged data

Multi-

Tagging across the languages the client supports

PoC

Proof of concept via the AI and ML Project Accelerator

By the numbers:

  • Custom - Amazon Comprehend trained on the client's own tagged data
  • Multi- - Tagging across the languages the client supports
  • PoC - Proof of concept via the AI and ML Project Accelerator
Changes

Cloud Combinator delivered a working proof of concept against the success criteria: a custom Amazon Comprehend model, trained on the client's data, that returns a sentence with accurate, relevant tagging through a simple API. It was deployed in the client's AWS environment with a demonstration and documentation.

  • Relevant, not random — A custom Amazon Comprehend model suggests the tags an user is likely to need, learned from the client's own tagging.
  • Trained on real usage — Training on the client's labelled data means the model reflects their conventions rather than generic language rules.
  • Simple to consume — A clean API and Lambda layer let the client send in a sentence and get back accurate tags, ready to integrate into the product.
  • Owned and portable — Built as infrastructure and deployed in the client's own AWS account, ready to extend beyond the proof of concept.
  • Handover — Included testing on the client's data, a demonstration and documentation for the team to continue development.

With intelligent tagging proven on AWS, the client has a foundation it can integrate into the platform and refine as more tagged data accumulates, improving the user experience across every language it supports.

AWS Stack

Amazon Comprehend

For a custom model that suggests structural and sentiment tags from the client's own data.

AWS Lambda

For calling the model and handling any post-processing.

Amazon API Gateway

For sending text in and returning tagged results.

Amazon S3

For storing the labelled training data.

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.