INDUSTRY
Construction
WesTrac started the 6 week engagement with an ambition to drive cutting edge LLM usage.
The Challenge
WesTrac is a Caterpillar equipment provider with over 3,000 employees servicing the mining and construction industries. As part of their Customer Experience strategic vision, they saw the opportunity for transformation in their business using the power of Generative AI through Large Language Models (LLMs). They were looking for a tangible pathway for their Data & Analytics (D&A) team to get started. Therefore, WesTrac engaged Mantel Group to start the journey.
”“In the early stages we engaged Mantel Group to discuss customer experience pain points and available technologies to assist us with harnessing AI to support solutions for those. We then brought in the AI experts within their [Data] brand to help develop our first commercial and production-ready large language model, in addition to feasibility testing of several other high value use cases.”
Emma Spartalis (Group Manager Data & Analytics)
As a starting point, WesTrac set three challenges:
- Establish a Generative AI solution in production to rapidly prove value
- Validate and prioritise the use cases identified elsewhere in the business to uplift the customer experience
- Enable the D&A team with the skills, technology blueprints and processes to deploy future LLM applications
The primary candidate for production was a use case to improve WesTrac’s customer experience by automating the rewriting of invoice notes from the highly technical, shorthand language used by technicians to a more customer friendly invoice description. Rewriting customer invoices was currently being done manually by service administrators, and taking 100s of hours of manual effort per month.
Our Approach
To achieve these outcomes in a short six weeks, Mantel Group tackled objectives in parallel, working closely with the D&A team to ensure upskilling throughout. Our team used the main use case as the vehicle to set up much of the infrastructure needed for future LLM deployments. The team set up an end-to-end pipeline within the WesTrac Azure Databricks environment using the Azure OpenAI service, concurrently acting as a blueprint for further LLM automation.
To set objectives, Mantel Group worked closely with both the D&A team and business SMEs responsible for the invoice notes to ensure detailed requirements were documented, test cases and success criteria were established early, and business processes were clearly defined.
In parallel, the team investigated the business need and viability of alternative use cases. The one showing immediate promise was to improve safety outcomes by providing a natural language interface to query and search Safe Work Procedures (SWPs). Since Mantel Group had already developed an LLM solution accelerator internally, the team were able to prove and demo the use case within two weeks of getting the initial data, in a showcase to executive leaders.
”“The team worked in an AGILE way, communicating well and transferring technical knowledge to our data engineers in the process. [Mantel Group] also contributed a great deal to our governance frameworks for deploying LLMs in a safe, ethical and highly transparent and explainable way, which were principles we agreed from the outset were critical for the success of the engagement.”
Emma Spartalis (Group Manager Data & Analytics)
Outcomes
WesTrac started the 6 week engagement with an ambition to drive cutting edge LLM usage. By the end of the process, they had all of the foundations to achieve:
- Proven value by delivering LLM-generated invoice notes to service administrators via a Power BI report, creating significant efficiency gains whilst keeping a human-in-the-loop process for quality assurance
- The WesTrac D&A team were set up to undertake future LLM implementations, including the safety use case which had by then garnered broad stakeholder support
- The client had a comprehensive deployment framework to refer to for LLM usage at WesTrac including reference architectures, best practice engineering, use case validation, and ethics and risk assessment templates
”“We’re incredibly proud of the position we’re in now to start deploying more AI use cases and generating significant value for our customers and employees. We are so grateful to the [Mantel Group] team for supporting the transformative work happening inside WesTrac.”
Emma Spartalis (Group Manager Data & Analytics)
