Coding with AI: What Works (and What Doesn’t) when building in CFML
AI is actually quite an old field of research, going back to work done by Turing in the 1950s. The rediscovery of the ideas of neural networks and large language models a couple of years ago has changed the trajectory of AI usage in our day-to-day lives and in our work environments quite significantly though.
AI-powered coding tools are changing the way we write software, but how well do they actually work for ColdFusion, Boxlang, and Lucee?
In this session, we’ll take a hands-on look at GitHub Copilot, ChatGPT, Claude, Cursor and potentially some others (given the speed this ecosystem evolves with) —what they get right, where they do a bad job, and how you can make the most of their abilities in your workflow. We’ll also have a look at comparing the quality of the output and its usefulness to other, more widespread used, tech stacks.
We’ll also have a look at the rise of AI agents: tools designed to go beyond smart autocomplete and actually carry out coding tasks for you. Can they refactor your code? Write full features? Fix bugs? Write tests for you?
There is a lot of hype and it needs to be somewhat separated from reality. In this talk I’ll discuss how (and when) to use these AI-driven assistants effectively.
Whether you’re totally sceptical or already using AI every day, you’ll walk away with a clearer picture of what’s possible, what’s coming next, and how to potentially code smarter with AI.
Kai Koenig
