Case Studies | SaaS B2B

Search the catalogue in plain English

Natural Language Image Search

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 two clear needs.

Natural language as the only input

Customers needed to search purely in plain language, with a model translating their words into queries that run against the client's current image search base, so the most convenient path to a result required no query syntax at all.

Validating Amazon Bedrock as the platform

Alongside the user-facing goal, the project set out to confirm that Amazon Bedrock was a suitable foundation, with success defined as a working pipeline using a Bedrock large language model.

Solution

A request from the client's application arrives through Amazon API Gateway, which passes it to AWS Lambda. Lambda invokes a large language model on Amazon Bedrock to interpret the natural language input and translate it into a search query.

Changes

The proof of concept met its agreed scope: a working natural language search pipeline was delivered on Amazon Bedrock, with acceptance based on signing off the delivery scope, the competence of the client's internal technical lead, and confirmation that Amazon Bedrock was a suitable service for the requirement. The gains in ease of use and customer service were the projected benefits of removing the need for query syntax.

  • Plain-language search — A Bedrock large language model translates natural language into queries against the client's existing image search base.
  • Lower barrier to entry — New and unfamiliar customers can search by describing what they want, with no platform-specific syntax to learn.
  • Serverless pipeline — Amazon API Gateway and AWS Lambda invoke Bedrock and combine the services into a single, repeatable flow.
  • Platform validated — The engagement confirmed Amazon Bedrock as a suitable foundation for the client to build on.
  • Handover — Knowledge was shared with the client's technical lead to support delivery and continued development.

With a validated Bedrock pipeline in place, the client has a clear path to integrate natural language search into the live platform and extend it as the catalogue and customer base grow.

AWS Stack

Amazon Bedrock

For the large language model that interprets natural language search.

AWS Lambda

For serverless model invocation and pipeline logic.

Amazon API Gateway

For accepting requests from the client's application.

AWS IAM

For secure, role-based access across the pipeline.

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.