Florin Lungu’s Post

Discover how to integrate GitHub Copilot directly into your terminal workflows. From cloning repositories to managing pull requests, this guide reveals strategies to enhance productivity. What stood out to me was the potential for streamlining processes, saving time for developers. How do you think AI tools like Copilot can change the way we work in the terminal?

Curious about enhancing your terminal experience? This article provides a comprehensive guide on using GitHub Copilot CLI, complete with a starter kit of effective prompts. I found it interesting that leveraging AI directly within the command line can streamline workflows significantly. How do you see AI tools impacting your coding practices?

🤓 Using GitHub Copilot to implement a feature in DotVVM When playing intensively with AI-powered tools, I don't think we are close to AI fully replacing software engineers in general. However, for several classes of tasks, it already works. Yesterday, a new user to DotVVM, the open-source framework we build at RIGANTI, reported an issue. It wasn't anything new; it was reported many times in the past, but since it is a by-design behavior of DotVVM, it cannot be changed. Essentially, when you need to redirect to another page, DotVVM throws an exception to signal that, and the exception is subsequently caught by DotVVM and transformed into a redirect response. If you wrap the redirect call in a try/catch block and don't let this exception pass, the page will break. I wanted to write a Roslyn analyzer that would identify this pattern in the code and emit a warning years ago, because it is frustrating for new users. It would take an hour or two, but there were always more important tasks on the project. However, since we already have Roslyn analyzers in the project, with tests and a release process in place, it shouldn't be a significant problem for the AI to add just one more analyzer. So I tried it - I basically copied the question from the forum as a GitHub issue and asked Copilot to implement it. Since it was an isolated task that didn't require deep knowledge of the project itself, and there are thousands of analyzers on GitHub that were part of the training dataset for LLMs, it was a success. Copilot figured out exactly where to make code changes, created meaningful test cases, and even considered nested try/catch blocks that I hadn't mentioned. We did a code review with my colleague and proposed several changes we noticed, for example, extended the requirement to handle "when" clauses or "catch" blocks without exceptions. It is not a major feature, but there are surely hundreds of similar small improvements in DotVVM, and using AI for them can be extremely useful. #developer #dotnet #ai #copilot #github

🚀 From Requirements to Draft PR — Using GitHub Models in GitHub Actions I’ve been experimenting with how far we can push autonomy in the software delivery chain. The result? A GitHub Actions workflow that turns plain-English requirements documents dropped into an inbox/ folder into: ✅ Structured GitHub Issues 🤖 Auto-assigned Copilot agents 💡 Draft Pull Requests ready for review All powered by GitHub Models (GPT-4o) and a bit of smart YAML. It’s an elegant loop — from requirements to working code stub with zero manual triage. If you’re exploring how to integrate Generative AI directly into your engineering workflow, this piece breaks down the logic, system prompts, and guardrails I’ve found most effective. 📖 Read the full breakdown here: 👉 https://lnkd.in/dCYueRuy

🚀 Google just dropped Code Wiki, and I spent the afternoon testing it. My honest take: it's exactly what I needed, but not quite what I want yet. Here's the situation: As data engineers, we constantly work with open source tools - dbt, Airflow, Spark, etc. Understanding how they work under the hood usually means: - Diving into GitHub repos blindly 🔍 - Watching YouTube tutorials that don't address your specific use case 📹 - Hoping the docs are up to date (they're not) 📄 Code Wiki changes this: ✅ Auto-generated docs that update with every commit ✅ AI chat (Gemini) that answers specific questions about the codebase ✅ Direct links from concepts to actual code files I tested it on some tools I use daily and it works surprisingly well for understanding internals. The gaps ⚠️: - Diagrams need more depth - UI could be more polished - Only works with public repos (for now) 🤖 Why this matters: I've been exploring options for auto-documentation using AI agents, and Code Wiki is a great example of the potential this technology has for our day-to-day work as developers. 💡 The real opportunity: If this becomes available for private repositories - imagine auto-documented internal dbt models, Airflow DAGs, and data pipelines. No more stale Confluence pages. No more "ask <Insert developer name>, he wrote this 2 years ago." For now, it's a solid way to understand the open source tools we depend on every day. Worth checking out 👉 https://codewiki.google/ Anyone else tried it? Curious to hear other perspectives 💬 #DataEngineering #CodeWiki #Google #AI #OpenSource

🚀 Built a Production-Ready REST API in 30 Minutes with GitHub Copilot Just completed a challenge: created a Restaurant Management API using ASP.NET Core 9, Clean Architecture, and JWT authentication — all in 30 minutes with GitHub Copilot. AI + smart prompting = massive productivity boost. ⚡ Results ✅ 18+ REST API endpoints ✅ Clean Architecture (Domain, Application, Infrastructure, API) ✅ JWT Auth with role-based access ✅ 6 entity models with relationships ✅ EF Core with SQLite ✅ Swagger, AutoMapper, BCrypt, error handling ✅ ~2,500 lines of production-ready code 🧠 The Secret The key was a clear, detailed prompt — including structure, entities, authentication, and dependencies. Copilot generated most of the code while I focused on testing and refinement. 🕒 30-Minute Breakdown 0–5 min: Project setup 5–15 min: Layer generation 15–20 min: Configuration 20–25 min: Migrations & build 25–30 min: Testing & docs 💡 Learnings Specific prompts = better results Copilot understands architecture & SOLID principles AI code quality is impressive — with logging, validation, and error handling Iteration and clarity matter AI accelerates productivity, not replaces developers. 🧩 Tech Stack ASP.NET Core 9, EF Core 9, SQLite, JWT, AutoMapper, Swagger, BCrypt 🎯 Takeaway This isn't about replacing developers, it's about multiplying developer productivity. The 30-minute challenge would have taken 8-12 hours manually. That's 95% time savings on boilerplate and architecture setup, leaving us to focus on business logic, optimizations, and creative problem-solving. 🔧 Next Steps Future add-ons: email notifications, reservations, reviews, payments, SignalR tracking, caching, and pagination. Have you tried GitHub Copilot for project scaffolding? Share your experience — how much time did it save you? #GitHubCopilot #ASPNetCore #DotNetDevelopers #CSharp #CleanArchitecture #Microsoft #BackendDevelopment #WebAPI #SoftwareEngineering #DeveloperProductivity #AI #GitHub #OpenAI #VisualStudio #CodingCommunity #TechInnovation #FullStackDeveloper #WebDevelopment #DevLife #Programming #DotNetCore GitHub Microsoft OpenAI

"You're absolutely right!" 🤩 That's GitHub Copilot's favorite line when I call out its overly complex errors. As a solo developer building an app, I've learned the hard way: AI tools are powerful, but they can lead you astray without clear direction. Early on, I tried using AI to whip up a rapid prototype. It was a dream for quick demos, but for enterprise-grade needs? Total disaster! The code was a mess of convoluted scripts that crumbled under real-world demands. The culprit? Vague prompts. If I say "deploy to my development environment" without mentioning GitHub Actions, Copilot churns out endless shell scripts for deployment and testing. It's like asking for a sandwich and getting a five-course meal you don't have time to eat. Here's the truth for anyone building a "GPT wrapper:" You can't just be a business visionary. You need to understand the technical challenges, like scalability, security, or CI/CD pipelines, to guide AI tools effectively. Engineers, this means crafting precise prompts. Specify your stack, tools, and constraints upfront to avoid wading through irrelevant code. For example, telling Copilot to "build an end-to-end auth flow with React frontend, Node.js backend, and JWT for secure user login" saves hours of cleanup, instead of "create a login system" that dumps a mix of unrelated frameworks. Managers, you don't need to code fluently, but you must know enough to steer the ship. Learn the basics of your tech stack to ask the right questions and set realistic goals for your MVP. Managers should be able to do 20% of the engineering work. This lesson hit home when I rebuilt my app's core features. Clear prompts and a solid plan turned AI from a liability into a productivity booster, helping me ship reliable code faster. Be adventurous with AI, but stay grounded. Know your tech, refine your prompts, and build something enterprise-ready. Code on! How do you make AI tools work for your projects? Drop a comment or let’s connect!

⚡️GitHub Copilot CLI — The Future of Coding *Lives in Your Terminal* ⚙️ Forget copy-pasting commands from Stack Overflow. Forget switching tabs to Google your next script. 👉 **GitHub Copilot CLI** just made your terminal *smarter than ever.* Imagine this: 💬 You type — `copilot "create a bash script to check for uncommitted changes and push if clean"` 🤖 Copilot writes, explains, and runs it — right there in your command line. No IDE. No browser. No context switching. Just **AI + CLI = developer superpowers.** --- 🔍 **What makes this a game-changer:** * 🔄 Automate tasks, refactor scripts, and handle GitOps — all with natural language. * 🧠 Explain unknown commands before running them. * 🚀 Build, debug, and even write documentation without leaving your shell. * ⚙️ Extend with **MCP servers** to integrate custom tools, APIs, and workflows. --- 💡 *Pro tip:* You can install it instantly: ```bash npm install -g @github/copilot ``` Start talking to your terminal — not typing at it. Welcome to the **agentic AI era of development.** 🧑💻💬 📖 Read the full guide: 👉 *GitHub Blog – “GitHub Copilot CLI 101: How to use GitHub Copilot from the command line”* 🔗 [https://github.blog](https://github.blog) --- #GitHubCopilot #AI #DevTools #CLI #DeveloperExperience #Automation #AgenticAI #ML #TechInnovation #DevCommunity #GitHub

This article breaks down the impactful role of Copilot in enhancing the GitHub platform. I found it interesting that Copilot not only streamlines coding processes but also empowers developers to be more creative and efficient. What stood out to me was how AI can evolve traditional workflows in significant ways. How do you see AI tools like Copilot changing the landscape of software development in the future?