Case Studies | SaaS B2B

A grounded GenAI content creation chatbot on AWS

GenAI Content Chatbot

About

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

Challenge

The proof of concept concentrated on four focus areas.

Grounded, brand-safe generation

The chatbot had to generate content anchored in the client's own data, not open-ended model output, and apply guardrails so responses stayed safe and brand-compliant. Where retrieval alone was insufficient, a LLM completion step would fill the gap.

Multiple knowledge bases, managed dynamically

Different products needed logically separate knowledge bases, with the ability to create, upload to, and select them on demand, and a reliable way to track their metadata and identifiers.

Conversational context

The assistant needed to remember prior turns within a session so that follow-up questions made sense and content built naturally on what came before.

Team enablement

As a proof of concept destined for the client's own environment, the build had to come with the documentation and knowledge transfer needed for the client to operate, monitor, and extend it.

Solution

Cloud Combinator delivered the build in stages, automating the infrastructure first so every component was reproducible from the outset.

5

Core AWS services automated through CloudFormation

3,000

Questions per day the design is sized for (projected)

50MB

Maximum document size per knowledge-base upload

By the numbers:

  • 5 - Core AWS services automated through CloudFormation
  • 3,000 - Questions per day the design is sized for (projected)
  • 50MB - Maximum document size per knowledge-base upload
Changes

Acceptance was measured against the project success criteria: a working chatbot that accepts input, retrieves from a Bedrock knowledge base, applies prompt logic and guardrails, uses memory for context, and returns output, plus dynamic knowledge-base management and session tracking, all handed over so the team can maintain it. The proof of concept demonstrated that the AWS environment is suitable for the continued development of the content creation chatbot.

  • Grounded generation — Bedrock knowledge-base retrieval with guardrails keeps content anchored in approved data and brand-safe.
  • Dynamic knowledge bases — A Boto3 API creates, uploads to, and selects knowledge bases, with metadata tracked in DynamoDB and documents added via pre-signed S3 URLs.
  • Conversational memory — Bedrock agent memory and DynamoDB sessions maintain context across turns.
  • Serverless and reproducible — API Gateway and Lambda run the workflow, and one CloudFormation template redeploys the whole stack.
  • Handover — A runbook, reference architecture, and knowledge-transfer session enable the team to operate and extend the solution.

With the proof of concept validated on AWS, the client has a grounded, guardrailed foundation to build toward a production system, adding capabilities such as user authentication and frontend integration on top of a reproducible, serverless base.

AWS Stack

Amazon Bedrock

For knowledge bases, agents, and guardrailed generation.

Amazon API Gateway

For the chatbot interaction endpoint.

AWS Lambda

For serverless backend processing.

Amazon DynamoDB

For session tracking and knowledge-base metadata.

Amazon S3

For document storage via pre-signed uploads.

AWS CloudFormation

For reproducible infrastructure as code.

Amazon CloudWatch

For monitoring of the serverless components.

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.