Interview: Bet365’s Tech Innovation

GenAI: What’s the use?

Bet365, like many other businesses, is exploring GenAI. Reed believes that, on an empirical level, the use of GenAI is a good idea. The foundation model reads the internet, and then turns the data it gathers into sentences.

The betting company has been experimenting with a Large language model before it became a key use case. “It is very obvious what can and cannot be done in the code space,” he says. Reed says that while writing code is a great thing, “what we were more interested in was, if it can read code, what can you understand?” The problem Bet365 wanted tackling was the ability to understand their code base without having to have someone read the code.

Like any large tech company that has been around for many years, he says, “you start to think about your technical data and legacy code base. And that there is a portion of your workforce that just maintains this legacy codebase.”

“Once you can get a level of comprehension from the AI, you can start to look at a value construct against your code and ask the bigger questions”

Alan Reed, Bet365

The maintenance challenge is that people’s understanding of how an application is programmed diminishes unless they frequently look at the code. “Every now and again, you realise you don’t understand the code to the degree you need to for the task ahead,” he says, referring to the difficulty in maintaining application code long term.

There is another benefit: if the AI can understand the code, both as content and contextually, it becomes a powerful tool for IT transformation projects. “Once you can get a level of comprehension from the AI, you can start to look at a value construct against your code and ask the bigger questions,” says Reed.

Not only can GenAI be used to improve the maintainability and portability of code bases, but it can also help to identify common blocks of code to aid migration efforts.

Referring to Bet365’s migration programme, Reed says: “Over a period of time, we put a lot of our business logic into databases. One of the things that we’re looking at as we do a platform migration is to modernise this code in a similar way to how we did the cloud migration.”

Summarizing databases

Reed wanted to test how well GenAI would work with the code base, given that it could read and understand it. Reed says that while a GenAI tool can understand the codebase and provide chat-oriented programming, it lacks a localised knowledge understanding, which led to the team to create a new tool. Retrieveal augmented generation, or RAG (pronounced “retrieval-augmented-generation”)

He says that RAG is the idea of adding your own nuance to the large language models, along with your own documentation, standards, and thought processes.

The paper published by Microsoft showed Bet365 how to use GraphRAG, a database that combines a graph with retrieval augmentation, to summarize its databases and business logic. Reed claims that the technique creates a knowledge graph for its databases. “We added everything we thought would be useful for a developer,” says Reed, allowing developers to query code and receive a meaningful answer.

Reed claims that the system provides extra information, such as which databases are the most used and which database tables use the most processing. “We wanted to know logical reads and physical reads. We wanted to make it very, very rich.

This information is crucial when determining which parts of the IT Infrastructure should be modernised in order to maximise value. A database that has existed for many years is almost certain to be interconnected with other databases. It is therefore difficult to work out what’s going on. This is why Bet365 needs an AI tool that is able read and understand the data in a database.

We almost immediately realised that it was an excellent way to show people the size and scope of the issue in front of them. Reed says it was a great way to get a message out.

A careful approach to tech innovation

It may be that innovation is best served cold. Reed’s example shows that while certain tech innovations, such as AI glasses, can be a way to innovate, they require careful consideration.

While it may not be the most exciting thing, an AI that can not only understand code and databases but also allows developers to ask technical queries of the code shows that AI is capable of much more than enhancing workflows and existing processes.