Like many massive enterprises, we should navigate the sweetness and chaos of legacy code. In our case, many years of SQL procedures and enterprise logic that underpin a platform able to dealing with over 3 million concurrent customers and a whole lot of micro code deployments per week. It’s a fancy machine. Contact one half, and also you threat breaking 10 others. That’s why modernizing the codebase is each a technical problem and a human one. It requires empathy, belief, and the flexibility to make knowledgeable guesses.
Contained in the Innovation Engine
At bet365, the platform innovation operate was established to impress chance. We’re a small, specialised group charged with exploring rising and future applied sciences. Our goal is to establish the place they’ll have the best influence, and assist the broader group perceive find out how to use them meaningfully.
We’re enablers and ambassadors for change. Our work spans every thing from product improvement and cybersecurity to the way forward for the workforce. Our guiding mannequin is McKinsey’s Three Horizons of Development reimagined for innovation. Horizon 1 focuses on what we will implement right this moment. Horizon 2 explores what’s coming subsequent. Horizon 3 dares us to think about the longer term nobody is speaking about but.
This framework helps us steadiness ambition with pragmatism. It creates house to experiment with out shedding sight of operational worth, and it ensures our builders, architects, and stakeholders are all a part of the identical dialog.
When GenAI Met Builders
When GPT-4 dropped in 2023, every thing modified. Like most within the tech world, we have been fascinated. Generative AI provided a tantalizing imaginative and prescient of the longer term full of sooner insights, immediate summaries, and automatic refactoring. However the pleasure shortly gave method to doubt. We handed very succesful builders a robust LLM and stated, “Go for it.” The outcomes have been blended at greatest.
They inserted code into the immediate home windows, stripped out context to avoid wasting house, and hoped the AI would perceive. It didn’t. Builders have been confused, annoyed, and, understandably, skeptical. They noticed the AI as a shortcut, not a associate, and when the output didn’t match expectations, frustration adopted. Many requested the identical query: “Why am I asking a machine to jot down code I might simply write myself?”
What we realized was profound. The issue wasn’t the AI. It was the connection between the AI and the individual utilizing it. We had assumed that ability in software program engineering would robotically translate to ability in immediate engineering. It didn’t. Did we miss one thing? The purpose we couldn’t overlook was throughout the train, our builders have been finishing the duties constantly round 80% of estimated time. There was positively one thing right here. We simply weren’t positive what it was. So, we went again to fundamentals.
Vibe Coding and the Limits of Belief
There’s a brand new time period in developer tradition: “vibe coding.” It’s the place you throw a bit of code at an LLM, get a response, tweak it, throw it again. Iterate quick. Ship sooner. It’s fashionable. It’s seductive. However it isn’t threat free.
And not using a clear understanding of intention or context, vibe coding can shortly turn into a recreation of trial and error. And when your system is as advanced as ours – many databases processing 500,000 transactions a second – “trial and error” isn’t adequate. We wanted greater than vibes. We wanted imaginative and prescient.
Context Over Content material
The turning level got here after we realized the actual job wasn’t instructing AI find out how to write higher code. It was instructing people find out how to talk with AI. We realized a brand new mantra: intention + context + element. That’s what the AI wants. Not simply content material. Not simply “repair this operate.” However: “Right here’s what this code does, right here’s why it issues, and right here’s what I want it to turn into.” This perception is essential.
Our builders, particularly these tackling essentially the most advanced, interdependent issues, tailored shortly. They have been used to considering deeply, offering rationale, and navigating ambiguity. They acquired it. They fed the AI what it wanted. They flourished. The distinction was mindset. We got here to name this phenomenon “the unreliable narrator.” Not simply the AI, however the developer. As a result of usually, the issue wasn’t that the machine acquired it unsuitable. It was at instances that we weren’t clear on what we have been asking.
RAG, GraphRAG, and the Energy of Grounded Context
To construct dependable, human-aligned AI assist we wanted a method to floor what the AI was seeing in truth. That’s the place we noticed the facility of Retrieval-Augmented Technology (RAG). RAG permits an AI mannequin to retrieve related context from an exterior supply – like documentation, system metadata, or a data base – earlier than producing a response. It’s sooner to implement and extra versatile than fine-tuning, making it ideally suited for dynamic, domain-intensive environments like ours. Builders can replace the data base with out retraining the mannequin, retaining outputs present and grounded.
However RAG has its limits. When a query spans a number of methods or requires reasoning throughout disconnected items of knowledge, conventional RAG, which relies on textual content similarity, begins to falter. That’s why we turned to GraphRAG, a extra superior strategy that makes use of a data graph to reinforce LLM outputs.
A data graph doesn’t simply maintain info, it encodes relationships. It captures how parts work together, the place dependencies lie, and what might break in case you change one thing. GraphRAG makes use of this construction to enhance prompts at question time, giving the AI the relational context it must reply with precision. That is very true in environments the place accuracy is essential, and hallucinations are unacceptable.
As a real-world train, we checked out our SQL server property. We wished to construct a system that we might use to realize worthwhile perception on how the system works.
To construct it, we began by parsing all our database objects together with tables, views, procedures, features, and so on. into summary syntax bushes (ASTs). Utilizing Microsoft’s ScriptDOM, we extracted key info and used them to assemble the preliminary data graph. We overlaid this with pure language descriptions to additional clarify what every factor did, and added runtime statistics like execution frequency, CPU time, and skim volumes.
The end result was a wealthy, relational illustration of our SQL property, full with contextual insights about how objects are consumed and the way they work together. Then we surfaced this intelligence to builders by three core instruments:
- A chatbot that lets customers question the system in plain language
- A visualiser that renders a 3D map of dependencies and relationships
- A Cypher executor for superior graph querying and evaluation
What’s necessary to notice is that a lot of the system’s worth lies within the graph, not the mannequin. The AI doesn’t must know every thing. It simply must know the place to look, and find out how to ask the suitable questions. That’s the facility of grounding.
For us, GraphRAG wasn’t only a nice-to-have, it grew to become important. It helped us transfer from generic code help to one thing much more worthwhile: a system that understands what our code means, the way it behaves, and what it impacts.
We’re not simply writing code anymore. We’re curating it. We’re shaping the intentions behind it. Our builders now have tooling to realize additional perception to turn into code reviewers, system designers, and transformation brokers at an professional stage throughout enormous division spanning architectures. All from a easy interface permitting pure language inquiries That’s the actual shift. The long run isn’t about AI doing our jobs. It’s about reimagining what the job is.
The success of our code modernization program has little to do with algorithms and every thing to do with perspective. We needed to unlearn outdated habits, rethink our relationship with code, and embrace a tradition of curiosity. We needed to cease asking AI for solutions and begin giving it the suitable questions. The expertise was the simple half. The individuals half, now that was the actual breakthrough.
