arconsis’ Post

GitHub Copilot is more than just autocomplete.   I’ve been working hands-on with Copilot over the last weeks to understand what it can really do in day-to-day development.   I’m starting a short article series that looks at GitHub Copilot from a practical engineering perspective. The intro explains the structure of the series, and the first article dives straight into Coding and Review Agents and how they support real workflows.   If you’re curious about Copilot but want substance instead of buzzwords, this series is for you. You can find the link to the intro and the first article, "Coding and Review Agents," in the comments. 👇   Feel free to share any questions or feedback with me.   #GitHubCopilot #CopilotSeries #SoftwareEngineering #AIinDev #DeveloperExperience #TechLeadership

🤖 GitHub Copilot Is Not Just Autocomplete Most people think GitHub Copilot is only good for finishing lines of code. That’s just the surface. In practice, Copilot helps with: • Writing repetitive boilerplate • Exploring unfamiliar codebases • Refactoring with context in mind • Generating unit tests • Turning comments into working code The real value isn’t speed alone. It’s reduced cognitive load. By handling the routine parts, Copilot gives developers more space to focus on system design, edge cases, and problem-solving. Like any tool, results depend on how you use it. Clear intent and good prompts matter more than people realize. Curious to hear — has Copilot changed the way you code, or is it still “nice to have” for you? #GitHubCopilot #DeveloperProductivity #AIinTech #SoftwareDevelopment #Engineering

🚀 Maximizing GitHub Copilot While Managing Risks 💻 GitHub Copilot is transforming software development by accelerating coding workflows, but responsible usage is key to unlocking its full potential. Here are best practices for managing risks with Copilot: ✅ Review Code Suggestions: Treat Copilot's outputs as a starting point, not a final solution. ✅ Avoid Blind Acceptance: Validate all code for accuracy and security. ✅ Check Licensing Compliance: Ensure suggested code aligns with your organization's policies. ✅ Use for Routine Tasks: Save time on repetitive or boilerplate code. ✅ Incorporate Peer Reviews: Human oversight ensures quality and reliability. ✅ Educate Your Team: Train developers on responsible Copilot usage. By following these practices, you can harness Copilot's power while maintaining high standards for quality and security. How is your team using AI tools like Copilot? Share your thoughts below! #GitHubCopilot #AIinDevelopment #BestPractices #SoftwareEngineering

I've been designing and implementing prompts to improve efficiency and speed of some time consuming/repetitive tasks on my team. Recently we started experimenting with Prompt Chaining techniques and it has given us great results. Andrew explains it really well here and even gives a free guide if you want to try it out.

Over the last 6-8 months, I've been using GitHub Copilot regularly and have narrowed it down to two ways I rely on it. Not for autocomplete. But as a thinking and execution partner. 1️⃣ Understanding existing code When I need to understand unfamiliar or complex code, I use Ask mode. What I usually do: - Share the code snippet and any references I already know are relevant. - Before asking for an explanation, I ask Copilot what additional references or context it needs to explain the code better. - Once all required context is attached, I ask it to explain the code step by step. This approach reduces guesswork and leads to much more accurate explanations, especially in large codebases. 2️⃣ From requirements to code This is where Copilot helps me the most. Step 1: Clarifying the problem I paste the requirements into Ask mode and start a discussion: - What approach should we take? - What assumptions are we making? - What are the edge cases? There's a lot of back-and-forth here. Sometimes I explain why something won't work. Sometimes Copilot points out gaps in my reasoning. Step 2: Confirming understanding Before any code is written, I ask Copilot to: - Re-list my requirements (to confirm it understood them correctly) - Explain the approach it plans to take - List the files / classes / functions that will be created or modified - Break everything down into numbered tasks Only after this do I move forward. Step 3: Writing the code I then switch to Agent mode and use premium models (Claude Sonnet 4 earlier, Sonnet 4.5 lately) to implement the tasks. Step 4: Review and iteration I first read and validate the generated code myself. Based on that validation, I decide how to proceed: - If the change is small, I make it manually - If it's a logic issue, I point it out and ask Copilot to fix it - If it's a bigger issue, I switch back to Ask mode to discuss the correction or approach, and then either apply the fix myself or switch back to Agent mode to update the code This loop continues until I'm satisfied. What this taught me Copilot works best when you stay in control and treat it like a collaborator, not a replacement. #GitHubCopilot #VSCode #DeveloperProductivity

🚀 Revolutionize Your Coding Workflow with GitHub's New Agents Tab! 💻✨ Elevate coding productivity with GitHub's redesigned Agents tab — your mission control for managing Copilot agent tasks directly within repositories! 📂 Seamlessly switch between tasks, view session logs with clear, grouped tool calls, and explore inline previews. 🛠️ Bash commands and recognizable icons boost transparency and clarity. Prefer the terminal? Resume sessions effortlessly via Copilot CLI for a smooth, uninterrupted coding flow! 🔄 Dive into a streamlined dev experience — all without leaving your codebase. Explore the future of coding: https://lnkd.in/ejXw8Sfn #GitHub #Copilot #DeveloperTools #Productivity #Coding

Building real memory into GitHub Copilot GitHub Copilot is becoming more than just a coding assistant. It’s evolving into a system of agents that learn from your codebase and each other. In a new blog post, Tiferet Gazit breaks down how Copilot’s cross-agent memory works, and why it’s a big deal for devs. Instead of treating every session like a fresh start, Copilot can now remember things like: ✅ Logging conventions across services ✅How your repo handles database connections ✅Which files need to stay in sync The kicker? It validates memories in real-time using code citations — no stale context, no guessing. 👉 That means better code reviews, smarter code generation, and less repetitive work for you. Curious how it works under the hood? It’s all here: 📖 Read the full post https://lnkd.in/gw5cSFsx #GitHubCopilot #AIEngineering #DevTools #LLMs #SoftwareDevelopment

When people talk about GitHub Copilot, they usually mean autocomplete in the IDE 💻 GitHub Copilot CLI is a different tool entirely, built for multi step engineering work outside the editor. That distinction starts to matter once work involves multiple steps. A common pain point with AI coding tools is sequential execution. Tasks like codebase exploration, running tests, reviewing changes, and summarizing results are often processed one after another, even when they’re logically independent. As tasks grow, this leads to longer feedback cycles and accumulated context that’s no longer relevant to later steps. With GitHub Copilot CLI, recent updates move away from a single agent handling the entire workflow. Work can be split across multiple agents that operate independently and in parallel, each constrained to a specific responsibility ⚙️ The practical impact isn’t about “smarter” output. It’s about workflow mechanics developers already care about: • ⏱️ Reduced waiting caused by strictly sequential steps • 🧠 Clearer separation between exploration, execution, and review • 📐 More predictable behavior as task complexity increases For teams using Copilot beyond basic autocomplete, this highlights a shift in how AI assisted work is structured. Where do sequential steps slow you down most in your current development workflow? #GitHubCopilot #AICoding #DeveloperExperience #SoftwareEngineering

Just read about GitHub Copilot CLI's slash commands! This is brilliant for staying in flow. Love the explicit control you get – like using /clear to reset context or /delegate to spin up a PR right from the terminal. Makes Copilot feel much more predictable and faster. Less context switching, more coding! 🚀 #GitHubCopilot #DeveloperTools

GitHub Copilot has changed how many of us write code. It accelerates , suggests patterns instantly and reduces the friction of starting from a blank file. For productivity, it’s a solid force multiplier. However we need to remember that Copilot doesn’t replace developers — it amplifies them. The strongest skill of a developer today isn’t typing code fast. It’s thinking — breaking ambiguous problems into solvable parts, choosing the right approach, and knowing when not to code at all. Copilot can suggest lines of code. Developers decide what should exist, why it should exist, and how it should evolve. Tell me your opinion.