The art of simplicity

The best way to improve the results you get back from GitHub Copilot, is by providing it some extra context. I explained before how you could use the copilot-instructions.md for this or by creating re-usable custom prompts. GitHub Copilot - Custom Instructions GitHub Copilot– Reusable prompts files When doing this it is not only important to create this context up front but also update them while your project grows and evolves. I typically put it as an extra task at the end of each sprint. Today when I opened VSCode, the following message popped up: Wow! That’s great. Now it already starts suggesting bringing my copilot-instructions.md  up to date for me! In this example, it adds one rule to the file: Sidenote: If you have a hard time coming up with good prompts, I recommend to certainly check out the Cursor rules examples. Although originally created for Cursor (another AI enabled IDE I really like), they can be a good starting point for your Copilot Instructions...

A few weeks ago, I did a webinar with a colleague where we talked about GitHub Copilot and the different ways you could use it. At that time, we demonstrated both the Chat mode and the Edits mode. With Microsoft 50-year anniversary the new Agent mode was made general available bringing the number of options to 3.   Remark: I didn’t succeed in letting Microsoft Designer generate a pathway splitting in 3 directions…. So now the question becomes: When to choose what mode? Great question! When to choose what mode? Choosing between GitHub Copilot Chat, Edits, and Agent mode depends on what you're trying to achieve: Copilot Chat : Ideal for conversational interactions where you ask questions, seek explanations, or brainstorm ideas related to coding. It's like having an AI-powered teammate that responds to your queries in real time. Copilot Edits : Best when you're actively modifying code. This mode allows you to start an edit session where...

The AI development landscape is evolving at an astonishing pace, with new tools emerging every day across every aspect of the development process. Whether you're fine-tuning models, optimizing deployment, or managing infrastructure, the ecosystem keeps expanding with innovative solutions. Everyday I hear a colleague talk about a new and exciting tool. But how can you ever keep up with this ever growing list? The team behind AINativeDev created a guide to the AI development ecosystem . A guide to the AI development ecosystem With 244 tools currently featured, this curated landscape offers insights into how AI development is being shaped across various domains, including: Prompting Tools – Enhancing AI interactions with structured prompts. Code Editors & Review Tools – Helping developers write, test, and optimize AI-integrated code. Autonomous Agents – Tools designed to automate coding tasks and enhance workflows. Model Be...