GitHub Copilot deep dive: Model selection, prompting techniques & agent mode

Level up your AI-assisted development with this GitHub Copilot deep dive where we try out all different AI models to see what works best for certain tasks. We go beyond simple code suggestions to explore agent mode for complex tasks, compare the strengths of various integrated models (Claude, Gemini, etc.), and demonstrate practical tips for prompting, debugging, tracking changes, and refining UIs with visual input. In this episode, we test out: Claude 3.5 and 3.7 Sonnet GPT-4o, 4.1, 4.5, o3 and o4-mini Gemini 2.0 Flash and 2.5 Pro #GitHub #Copilot #GitHubModels ▬▬▬▬▬▬ TIMESTAMPS ⌚ ▬▬▬▬▬▬ 00:00 Intro to Models 01:33 Preparing the Prompt and Custom Instructions 06:45 Model Selection and Use in Agent Mode 11:24 Debugging Build Errors 35:10 Using Visual Inputs and File Drop Techniques 40:47 Comparing Results 41:10 Refining the Frontend 52:46 Making it secure & accessible 58:55 Testing with Copilot 1:06:27 Documentation 1:14:24 Wrap-up and key takeaways Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 100 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com