Can Y.’s Post

💡 Make GitHub Copilot Work With Your Team Using Prompt Files When working with GitHub Copilot in VS Code, you can create reusable prompt files that live right alongside your source code. 📦 These files can be stored in source control and executed anytime, making them perfect for tasks your team performs repeatedly. For example, my team uses a prompt file to: ✅ Add new properties across multiple layers of our API ✅ Generate consistent release notes for those properties Since creating it, we’ve used the same prompt file to add 20 new properties, saving time and keeping our output consistent across services. ⚙️ You can even define which AI mode and model Copilot uses when running the prompt, giving you predictable, repeatable results every time. If your team uses Copilot regularly, try building a few prompt files for your common workflows. It’s a small step that makes AI collaboration more structured, consistent, and team-friendly. 💬 Have you tried using prompt files with Copilot yet? I’d love to hear how your team’s using them. #GitHubCopilot #VSCode #AIinDevelopment #DeveloperProductivity #SoftwareEngineering #CodingTools

I just read the blog post on “The road to better completions: Building a faster, smarter GitHub Copilot with a new custom model” and here are some of my take-aways. #SystemDesign #AgenticAi #GithubCopilot #AIEngineering

All Eyes on GitHub Universe 25. Big one for Copilot. If GitHub wants to close the gap between CoPilot and its competitors, this is the week. GitHub's dev conference starts Tuesday morning (Oct 28). Here's what I'll be watching based on what I've seen and where I think CoPilot needs to go: My predictions: - Big boy context window. Context expansion to compete with Cursor. Hundreds of thousands of tokens. - Speed, speed, speed. Latency cuts. Cursor feels noticeably faster in day-to-day work. CoPilot needs a real speed plan, not "we’re working on it." - Multi-agent orchestration. I've seen Claude Code's subagent system run autonomous coding sessions for 8 hours, 24 hours, even more than 24 hours. CoPilot takes a stab at an orchestration story here I think. - The big strength Github has is that they can own SO MUCH of the deployment pipeline. I’m looking for a single agent path from code to rollout to monitor, with approvals where you need them. Wildcard that I don't know where they'll go - pricing. Love to talk to people about what they expect and what happens there. This is a chance to play catchup and play to their strengths. For those running full-stack operations: pay attention to how these agents handle cross-repo coordination and deployment pipelines. That's where GitHub could actually pull ahead. What do you want to see shipped? Give me some predictions! #GitHubUniverse #AIAgents #DeveloperTools #SoftwareEngineering #DevTools #DX #FullStackDrip

I was skeptical about GitHub Copilot Pro at first. But after a few weeks of using it, I’ve changed my mind. Not because it’s flashy or futuristic, but because it genuinely helps. Agent mode feels like having a thoughtful teammate who’s always available. It explains code, finds bugs, and even helps you understand parts of the repo you forgot you wrote. It doesn’t replace developers. It supports them. It gives you space to think, to solve, to breathe. If you’re leading a team, this is worth investing in. Not just for productivity — but for the people behind the keyboard. And of course — code review is still the key. Copilot can help you write faster, but thoughtful review is what keeps the bar high. AI can assist, but humans still shape the craft.

🚀 Creative Use of GitHub Copilot for Code Review A few months ago, I faced an interesting challenge during a code review. One of my colleagues had pushed 35-40 files - a lot of files, limited time, and everything bundled together in a single Bitbucket branch. Even though we had access to GitHub Copilot, we couldn’t use its built-in code review features directly since the repo was hosted on Bitbucket, not GitHub. So, I decided to get creative. Here’s what I did 👇 1. I pulled the latest code locally and took all the commits that were pushed to Bitbucket, keeping them in a staged state. 2. Then, I removed the files from staging, moving them under the Changes section in my local setup. 3. Once all the modified files appeared there, I used GitHub Copilot locally to review each file one by one, by prompting it with clear instructions for what to check and analyze. 4. I then went through each of Copilot’s suggestions, verified the logic, and made adjustments where needed. This approach turned out to be surprisingly effective - Copilot helped me quickly identify potential logic issues (like an extra for loop in a setup function), while I could focus on validating the reasoning and context. 💡 Key takeaway: Even when your workflow doesn’t perfectly align with your tools, creativity and the right prompts can help you get the most out of AI. #AI #CodeReview #GitHubCopilot #Bitbucket #SoftwareEngineering #DeveloperExperience #Innovation #Productivity #MERNSTACK #REACT

As someone who’s always exploring AI tools to make life a bit easier, I recently decided to dive deeper into GitHub Copilot. Since I use VS Code every day, I came across this great playlist from the VS Code YouTube channel. It goes beyond just the basics — covering things like prompting strategies, Agent Mode, and even what not to do when using Copilot. Here are a few videos I found really helpful 👇 🎯 Get Started with GitHub Copilot in VS Code (2025) Good starting point — covers the basics, different use cases, available features, and extra learning resources. ▶️ https://lnkd.in/dkBEsF5W 💡 Essential AI Prompts for Developers Explains 4 prompting strategies (Role Prompt, Stepwise Chain of Thought, Pros & Cons, and Q&A Strategy) that help get better results from Copilot. ▶️ https://lnkd.in/dsw9rrNV 🤖 VS Code Agent Mode Just Changed Everything This one shows how you can use Agent Mode, MCP servers, and PRD documents to build a complete app — including the database part. ▶️ https://lnkd.in/db_kPGDU 🚫 Copilot Best Practices (What Not To Do) A nice take on best practices — explained through common mistakes people make with Copilot. ▶️ https://lnkd.in/dJ73mt9j 🎥 Full playlist (GitHub Copilot + VS Code): https://lnkd.in/dfaBTEyB) 💡 Copilot has already become an integral part of modern software development. If used right, it’s not just a productivity tool — it’s like having a pair programmer who helps you write, learn, and grow.  👇 I’d love to hear what tools or tricks you use to make your dev workflow smarter. #githubcopilot #vscode #ai #coding #copilot #developer #odoo

💻 GitHub Copilot & Context Engineering - Internal Session with Alex Yochev. Last week we had the pleasure of hosting Alex Yochev, Senior Solution Engineer at Microsoft, for a special session on "GitHub Copilot Presentation: Context is King - Engineering Prompts That Actually Code". 🎯 In the age of AI-assisted development, writing good prompts is no longer just an advantage, but an essential skill. Alex shared practical techniques for crafting smarter prompts, managing context, and using tools like GitHub Copilot and VS Code to turn vague ideas into production-ready code. Discover more highlights from the event! 👇 #BoschDigital #AIEngineering #TechTalks

👨💻 Just published a full walkthrough of the new GitHub Copilot Code Review Agent (2025 update). From custom .instructions.md files to CLI workflows and hybrid review logic, it’s built to make code reviews faster and smarter—right from your editor or terminal. If you're working in VS Code or GitHub regularly, this update is worth checking out. ▶️ Watch here: https://lnkd.in/gfJ2sBng #GitHubCopilot #CodeReview #DeveloperExperience #VSCode #DevTools #TheCuriousDev #AIForDevelopers

GitHub Copilot CLI is here! Now you can ask Copilot questions, generate scripts, and refactor code directly from your terminal. No more context switching needed! 🚀 This feels like a huge boost for staying in flow and productivity. Good to see it asks for confirmation before executing. #GitHub #DeveloperTools

Software development is evolving faster than ever and AI-driven tools like GitHub Copilot are at the heart of this transformation. In our latest blog by Punitpreet Singh, explore how Copilot is empowering developers to code smarter, faster, and more securely in C# enterprise environments - turning AI into a true coding collaborator. From accelerating delivery timelines to improving data-driven decision-making, GitHub Copilot is helping teams achieve up to 55% faster development, reduce errors, and enhance code quality — all while enabling secure, scalable, and intelligent IT consulting outcomes. 💡 Read how Cubastion’s AI-powered IT consulting leverages GitHub Copilot to drive innovation, automate routine tasks, and deliver enterprise-grade software solutions with unmatched speed and precision. 🔗 Read the full story here: [https://lnkd.in/gzNn5qHp] #GitHubCopilot #AIDrivenDevelopment #ThinkCubastion #SoftwareEngineering #DigitalTransformation #CSharpDevelopment #AIinITConsulting #Automation #DataDrivenDecisions #EnterpriseSoftware #TechInnovation #SoftwareProductivity #AIAssistant #CubastionConsulting