All #Ai articles

Most developers think AI assistance begins and ends with autocomplete suggestions. But after building everything from complete web applications to voice interfaces using AI tools, I've discovered workflows that transform how we approach development entirely. This isn't about replacing human skills - it's about augmenting them to tackle more ambitious problems, learn faster, and ship better software. Whether you're skeptical about AI or already using basic tools, here's your roadmap from simple suggestions to AI-powered development workflows.

I set out to make my mornings easier and build something fun: a personal running coach that lands in my inbox at 6am. Using n8n Cloud to orchestrate APIs, Cursor to generate the workflows and code nodes, and Gemini to turn weather data into clear coaching advice, I wired up a simple scoring model, friendly analysis, and a nicely styled email (yes, the AI handled the email CSS). This is a practical walkthrough of the approach—less handwritten code, more connecting services—what worked, what didn’t, and why this pattern feels like where everyday developer automation is headed.

AI tools like Cursor and GitHub Copilot can do way more than just generate code. I've been exploring how to use them for documentation, commit messages, code reviews, and other workflow tasks that often get skipped. Here are some practical ways to expand how you use AI in development beyond the usual code generation.

Chrome now offers built-in, on-device AI APIs for summarization, translation, and language detection without the use of cloud required.

Discover how I built a complete breathing exercise web app without touching a single line of code, using AI to transform an idea into a fully functional product. What was good, what was bad and is this where we are heading in our industry?

As part of being a Google Developer Expert, I’m fortunate to be able to join certain Google events to connect, learn and share. The past week I was invited to Google Paris for three days of everything around AI and Cloud. Here’s a short recap with interesting things I heard and what inspired me!

Fed up with AI that makes up facts and can't keep up with your latest data? That's where RAG (Retrieval-Augmented Generation) comes in – the clever technique that's changing how we build AI applications that actually work.

The Coven of Wisdom Eindhoven meetup on Nov. 16th, in partnership with AWS and the amazing Samuel Sopeju from AWS, was a total blast! The goal was simple: dive headfirst into the deep end of machine learning using Amazon SageMaker. And we did just that!

AI-powered speech synthesis is getting incredibly realistic. This opens up many possibilities to generate realistic audio based on the text you provide. Whilst relatively fast, the latency still isn’t low enough for “real-time synthesis”. Let’s optimise that!

How can I improve the way someone interacts with ChatGPT? How can I make it feel more natural than a dreadful “chatbot”? Can I create something cool? Those were some of the questions I asked myself recently while starting a two-day hackathon at iO. I’ll take you through what I build, how, and most importantly, why.

In the second part of this series, we will take a look at some of the ways that GPT-3 can be used by content creators to improve their workflow. We will also provide some tips on how to get started with using GPT-3 for your own projects. We will use OpenAI’s Playground to try out the features of GPT-3.

In this first part we will look at how natural language AI can offer developers a lot of benefits, from helping them write code to writing this blog post. Here, we will introduce you to two of the most popular natural language AI tools, OpenAI GPT-3 and GitHub Copilot, and discuss some of the best use cases for each.