Case Studies | SaaS B2B

Turning plain English into database queries

Natural Language Search on AWS Bedrock

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 hold up before a natural language search feature could be trusted in front of customers.

Plain-language access

Platform customers, including those new to and unfamiliar with the product, needed to search using natural language only, rather than learning Elasticsearch query structure. The convenience of that experience was the core objective for the client.

Accurate query translation

A large language model had to reliably turn a natural language request into a valid Elasticsearch query against the client's existing database. If the translation was unreliable, the feature would erode trust rather than build it.

Validating AWS Bedrock

The project also had to establish whether AWS Bedrock was a suitable managed platform to invoke the model, wrap it in a serverless pipeline, and continue the model's development beyond the initial build.

Solution

Rather than a single build, the work followed the Cloud Accelerator Program so that the client gained both a working pipeline and the internal understanding to own it. The six programme milestones were delivered across four stages.

6

AWS Cloud Accelerator Program milestones delivered

1

Natural language to Elasticsearch pipeline built on Bedrock

Bedrock

Validated as the managed platform to carry the model forward

By the numbers:

  • 6 - AWS Cloud Accelerator Program milestones delivered
  • 1 - Natural language to Elasticsearch pipeline built on Bedrock
  • Bedrock - Validated as the managed platform to carry the model forward
Changes

The engagement met its acceptance criteria: a working pipeline that uses AWS Bedrock to turn natural language into Elasticsearch queries, delivered in the client's AWS account, with Bedrock validated as a suitable managed platform to continue developing the model. Delivery was completed across the Cloud Accelerator Program.

  • Plain-language search proven — Customers can express what they want in natural language and have it translated into a valid query, removing the need to learn Elasticsearch syntax.
  • Serverless, scalable pipeline — API Gateway, Lambda and Bedrock were combined into a single flow that scales with demand and keeps operational overhead low.
  • Platform decision validated — AWS Bedrock was confirmed as a suitable managed environment to host the model and support its ongoing development.
  • Team enabled — Through the immersion day and Well-Architected review, the client's technical lead was equipped to continue the model's development in house.

With the proof of concept in place and the internal team upskilled, the client has a validated Bedrock foundation on which to refine query accuracy and extend natural language search across more of its platform.

AWS Stack

AWS Bedrock

For managed access to the large language model that translates natural language into Elasticsearch queries.

AWS Lambda

For serverless invocation of the model and the supporting pipeline logic, scaling automatically with demand.

Amazon API Gateway

For a managed endpoint that accepts requests from the client's application.

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.