Karan Bishwakarma’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

🚀 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

🤖 If you're using GitHub Copilot Agentic Mode in VS Code, you’ve probably updated your monorepo to support custom instructions. But here’s something fun to try: path-specific instructions. Imagine having an agent that not only understands your monorepo’s architectural layers, but also adapts to the specific tech stacks and nuances of each one! Here’s how you can start: 1️⃣ Create an instructions folder inside your .github folder. 2️⃣ Add a file for one of your monorepo layers. 3️⃣ Define its scope on top of the file, for example: --- applyTo: "persistence/**" --- 4️⃣ Ask your model of choice to generate initial instructions by analyzing that layer, then start tweaking! The result? My agents are now more concise, give smarter code reviews, and evaluate fewer tokens while understanding context better. It also creates less to none of those clumsy documentation files in the process! 📚 Source: https://lnkd.in/d6iiiUWm (I’ve been working with GenAI for a while, and I’m excited to share more about running Agents in Production. Would love to hear your thoughts!)

✏️ New blog from me: How GitHub engineers are using Copilot to cut toil and speed up our engineering. Tldr = Copilot is helping with tasks like UI and copy fixes, large-scale code cleanup and refactoring, bug and flaky-test resolution, feature building (new API endpoints and internal tools), and migrations/security work. Here’s the breakdown → https://lnkd.in/gn_np_yC

👨💻 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

🚀 Unlock Developer Productivity with GitHub Copilot I’ve known about GitHub Copilot for a while, but today I took a deep dive into how it really works—and wow, it’s a game-changer! It’s more than just code suggestions. It’s a true AI-powered pair programmer that can: ✅ Generate precise code modifications via chat ✅ Approve changes one by one—or all at once ✅ Create Swagger documentation for APIs ✅ Create UML flow diagrams for code functions and classes ✅ Analyze entire codebases and recommend improvements ✅ BE DEV can generate React code for front-end development ✅ Fill complex forms faster and efficiently and reduce lead time time to PROD ✅ Leverage 100s of extensions for customization Copilot doesn’t just speed up coding—it transforms how developers design, review, and deliver software. 👉 Check out this YouTube playlist https://lnkd.in/gc4efpJ2 for demos and tips. Have you tried Copilot yet? How is AI shaping your workflow? Share your thoughts below! 👇

## 🜍 Rebuilding the Cathedral — From Confusion to Clarity with Rust, Godot, and Open Tools My project [**https://lnkd.in/gYgxzPkX) has evolved into a living experiment — blending **Rust**, **Godot 4.5**, and **free open deployment** using **Cloudflare** and **GitHub Pages**. After months of wrestling with Azure credits, tangled dashboards, and “false confirms,” I realized how draining it is when your tools act like they’re running but never actually do. Even assistants inside VS Code can fake execution — leaving you in limbo. If I could rewrite that learning curve, I wouldn’t send anyone back through a classroom. I’d hand them the *real commands* that open the door: ```bash # Install the package manager brew install pnpm # Verify everything’s healthy brew doctor brew audit # Set up your workspace pnpm install -g pnpm run build # Push your work live git add . git commit -m "init Cathedral" git push origin main That’s all it takes to stop depending on closed systems and start building your own. Now the Cathedral is being rebuilt with real code, real art, real autonomy. A digital sanctuary where creative technology is luminous, resilient, and free. ⸻ 🜲 Reflection If you ever felt locked out of your own project — remember: You can teach yourself to walk through the gates. Rust, Godot, PNPM, and GitHub Pages are enough to build your own Cathedral.

Big leaps just announced at GitHub Universe 2025 At this year’s event GitHub delivered major updates that signal how software development is evolving at speed and scale. First, they revealed Agent HQ: a mission-control hub that lets developers pick, manage, and compare multiple AI coding agents in one unified space. These agents can come from GitHub, OpenAI, Anthropic, Google, xAI, and more. Peace of mind plus choice. Next, GitHub introduced new workflows in VS Code like “Plan Mode” (build your step-by-step strategy with AI) and code-review automation where agents team up with tools like CodeQL to spot issues before you do. Here’s why this matters: Developers will spend less time switching tools and more time creating value. Organizations will see how productivity now ties directly to how well they integrate agents. The new era isn’t just faster code; it’s agent-driven development. If you build software, manage dev teams, or invest in digital products, this is a signal worth watching. https://lnkd.in/guWwiJbm #GitHubUniverse #Agents #AIcoding #DeveloperTools #Innovation #SoftwareDevelopment

Did you know you can give GitHub Copilot custom review instructions? I’ve started using this to automate the kind of feedback I keep repeating in pull requests. With the rise of AI-assisted code, even good contributions tend to reuse patterns or miss small team conventions. Instead of commenting the same things like “use async,” “prefer f-strings,” or “move this into a shared utils module,” I can ask Copilot to look for them automatically. All it takes is a .github/copilot-instructions.md file. You can describe what you want in plain English, such as “flag any code that calls time.sleep in async functions” or “remind authors to add type hints.” Copilot’s reviewer then incorporates those rules into its automated review. It is not perfect and sometimes misses context, but it helps enforce consistency across a codebase. Unlike a linter or pre-commit hook, it can also catch more subjective issues that are part of a team’s culture. If your team uses Copilot reviews, this feature is worth trying. It is a small change that saves a surprising amount of repetitive feedback.

Just read how GitHub Copilot has seriously leveled up! It's gone way beyond autocomplete with "mission control" and agent mode, becoming a full workflow assistant. Think automated tests, PR reviews, and multi-step refactors right in VS Code or CLI. This is a game-changer for dev speed. 🤯 #GitHubCopilot #DevTools