How AI Assists in Debugging Code

Devs in 2025: I’m a 10x engineer now because of AI Also devs: Claude wrote this part, it handles the edge cases. Which edge cases Not sure, but the tests pass. AI might be raising a generation of developers who can ship code but cannot read a stack trace, which doesn’t sound great to me. If you cannot: - read logs and stack traces - explain why a fix works with ease - mentally walk through a request from entry point to database then you are not in control of the system, the system is in control of you. AI makes this worse because it hides the pain. You paste in an error, it spits out a patch, tests pass, ticket closed. Short term, everyone is happy. Long term, you have written code you cannot defend in a design review, cannot debug, and cannot safely extend a year later. I am not anti-AI at all. Use Claude, Cursor, Copilot as much as you like. Just use them in a way that makes your brain sharper, not lazier. Some good habits to make to avoid this kind of thing happening to you. 1. AI should confirm or refine your thinking. Reproduce the bug, read the stack trace, add logs, use your debugger, guess the possible suspects. Only after you have a hypothesis can you ask AI, “Here is what I think is happening, what am I missing.” AI should confirm or refine your thinking. 2. Explain before you fix Before merging any AI-generated change, answer two questions in plain language. - What is the root cause - How exactly does this change address it 3. Trace the flow Pick one feature per week and do a full walkthrough. - Where does the request enter - Which services and queues it touches - What data is read and written - Where errors would surface Draw a small diagram, talk it through with a teammate. Once you build this habit, stack traces stop looking like random noise and start looking like a story. 4. Measure yourself on understanding It is tempting to say, “I closed 15 tickets this week with AI.” The better question is, “If one of those tickets reopens with a new edge case, can I debug it alone?” Speed is useful when you already have depth. Without depth, speed only multiplies confusion. AI is here to stay, and that is fine. What should not change is the core craft of engineering, which is to think clearly about problems, understand code that already exists, and take responsibility for the systems you touch. If you can do that and use AI on top, you will be truly dangerous in this market. If you skip that and let AI think for you, you might ship a lot this year, but the day something breaks, you will have nothing to stand on except “the tests were passing.”

𝗜 𝗴𝗮𝘃𝗲 𝗺𝘆 𝗔𝗜 𝗰𝗼𝗱𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 (𝗖𝗹𝗮𝘂𝗱𝗲) 𝗲𝘆𝗲𝘀 𝗶𝗻𝘁𝗼 𝗺𝘆 𝗔𝗻𝗱𝗿𝗼𝗶𝗱 𝗲𝗺𝘂𝗹𝗮𝘁𝗼𝗿 👀 When debugging Android UI issues, context is everything. An AI agent can read your code but it can’t see what’s actually happening on screen. Until now. I built a simple Claude Code slash command called /screen-debug that: • Captures a screenshot via ADB • Dumps the view hierarchy (uiautomator XML) • Extracts the current Activity / Fragment • Lets Claude visually inspect the screenshot • Combines everything into a single structured analysis All of it lives in one markdown file inside .claude/commands Within minutes, it spotted that my toolbar was rendering behind the status bar — a classic fitsSystemWindows issue — and pointed me directly to the root cause. Here’s the key insights - Structured data alone isn’t enough. - Visual inspection alone isn’t enough. - Together? 𝗩𝗲𝗿𝘆 𝗽𝗼𝘄𝗲𝗿𝗳𝘂𝗹. If you're building Android apps with Claude Code, try creating your own ADB-powered commands. 👇 I’ve added the full /screen-debug command in the first comment. #AndroidDev #AI #ClaudeCode #MobileEngineering #DevTools

I’ve been using AI-assisted coding for the last 15 months, and here’s my honest take on where it truly shines — and where it still falls short: Where AI makes life easier: • 🚀 Kicks off projects fast with reliable boilerplate • 🐞 Great at spotting and debugging tricky issues • ⚡ Smart auto-completion that saves hours • 📚 Helps explore and learn new techniques quickly �� 🔁 Handles repetitive patterns like a champ • 🧹 Cleans, refactors, and organizes code beautifully Where it still gets challenging: • ✏️ Sometimes writes more code than needed • 🔍 Often fixes the symptom, not the root cause • 🔗 System-level integrations can confuse it • 🧩 Needs clear prompts for modular, reusable architecture • 📦 If not reviewed, redundant code sneaks in At its best, AI is an incredible co-pilot — fast, helpful, and tireless. But it still needs our direction, our architectural judgment, and our eyes for quality. The magic happens when humans bring intent and AI brings acceleration. What’s your take on vibe coding?

Legacy PLC code can finally get the documentation it deserves — thanks to MCP + AI. Most factories are running PLC projects that have been patched, extended, and “quick-fixed” for years — often with minimal comments and unclear logic. With the MCP Server CODESYS, an AI assistant can load the entire project, scan every POU and variable, and instantly highlight issues: magic numbers, duplicated logic, inconsistent naming, missing comments. Even better — it can auto-generate a Markdown report describing each POU, summarize logic flows, suggest better variable names, and insert comments where context is missing. For maintenance and modernization work, this is huge: instead of spending days trying to “decode” legacy logic, engineers start with clarity, structure, and a guided refactoring path. This is what AI-supported engineering actually looks like in practice — not replacing engineers, but giving us back the time we lose understanding old code.

A few months ago, I was stuck on a bug that shouldn’t have existed. The logic looked right. The logs looked clean. The issue folder? Hundreds of files deep. Old me would’ve spent hours scrolling, grepping, re-running, second-guessing. Instead, I asked AI. In seconds, it pointed me to the exact pattern, the likely root cause, and even suggested where similar issues had appeared before. Not magic. Just smart, optimized search + context. That’s when it hit me. We were told AI would replace developers. But in reality, it’s quietly becoming the best debugging partner we’ve ever had. It scans massive issue folders faster than we can blink It highlights edge cases we might miss on tired days It helps us reason, not just code It turns “I’m stuck” into “oh, that’s why” The fear came from imagining AI as a decision-maker. The value comes from using it as a multiplier. The developer still thinks. AI just removes the noise. I don’t write less code because of AI. I write better code, faster, with more confidence. Now I’m curious 👇 Has AI made your development workflow easier—or are you still on the fence about trusting it? #AI #SoftwareDevelopment #Developers #Debugging #Productivity #TechCareers #EngineeringLife #Coding #FutureOfWork #AIForDevelopers

𝟏𝟐 𝐏𝐨𝐰𝐞𝐫𝐟𝐮𝐥 𝐏𝐫𝐨𝐦𝐩𝐭𝐬 𝐭𝐨 𝐃𝐞𝐛𝐮𝐠 𝐂𝐨𝐝𝐞 𝐅𝐚𝐬𝐭𝐞𝐫 Most developers debug by trial and error. These 12 prompts turn AI into your debugging partner from fixing bugs to generating test cases. 𝟏. 𝐅𝐢𝐱 𝐭𝐡𝐞 𝐁𝐮𝐠 When: Your code is not working as expected Prompt: "Help me understand why this code is failing and explain the fix in very simple terms: [your code snippet]." 𝟐. 𝐔𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝 𝐭𝐡𝐞 𝐄𝐫𝐫𝐨𝐫 When: You encounter an error message Prompt: "I am getting this error: [error message]. What does it mean, and how can I fix it?" 𝟑. 𝐂𝐡𝐞𝐜𝐤 𝐄𝐝𝐠𝐞 𝐂𝐚𝐬𝐞𝐬 When: You want to ensure your logic is complete Prompt: "Here is what my function should do: [description]. Can you identify edge cases or scenarios I might have missed?" 𝟒. 𝐑𝐞𝐯𝐢𝐞𝐰 𝐭𝐡𝐞 𝐂𝐨𝐝𝐞 When: You want a quality check Prompt: "Review this code for bugs, security issues, and bad practices: [your code]." 𝟓. 𝐆𝐞𝐭 𝐃𝐞𝐛𝐮𝐠𝐠𝐢𝐧𝐠 𝐒𝐭𝐞𝐩𝐬 When: You are stuck on a tricky issue Prompt: "I am facing this issue: [describe problem]. What step-by-step approach should I take to debug it?" 𝟔. 𝐕𝐚𝐥𝐢𝐝𝐚𝐭𝐞 𝐀𝐬𝐬𝐮𝐦𝐩𝐭𝐢𝐨𝐧𝐬 When: You suspect incorrect logic Prompt: "I think the issue is in [part of code] because I assumed [X]. What assumptions might be wrong?" 𝟕. 𝐄𝐱𝐩𝐥𝐚𝐢𝐧 𝐭𝐡𝐞 𝐂𝐨𝐝𝐞 When: You do not fully understand the code Prompt: "Explain what this code does step by step in simple terms: [paste code]." 𝟖. 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐞 𝐓𝐞𝐬𝐭 𝐂𝐚𝐬𝐞𝐬 When: You want to test thoroughly Prompt: "Create test cases, including edge cases, for this code or feature: [description or code]." 𝟗. 𝐈𝐬𝐨𝐥𝐚𝐭𝐞 𝐭𝐡𝐞 𝐈𝐬𝐬𝐮𝐞 When: You do not know where the bug is Prompt: "Help me isolate the exact part of the code causing this issue and suggest how to verify it." 𝟏𝟎. 𝐂𝐨𝐦𝐩𝐚𝐫𝐞 𝐄𝐱𝐩𝐞𝐜𝐭𝐞𝐝 𝐯𝐬 𝐀𝐜𝐭𝐮𝐚𝐥 When: Output does not match expectations Prompt: "Here is what I expected: [expected]. Here is what I got: [actual]. Where could things be going wrong?" 𝟏𝟏. 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐞 𝐭𝐡𝐞 𝐅𝐢𝐱 When: You have a working solution but want improvements Prompt: "This solution works, but can you suggest a cleaner, more efficient, or more scalable version?" 𝟏𝟐. 𝐀𝐝𝐝 𝐃𝐞𝐛𝐮𝐠𝐠𝐢𝐧𝐠 𝐋𝐨𝐠𝐬 When: You need better visibility into execution Prompt: "Where should I add logs or breakpoints in this code to better understand what's happening?" Debugging is not about fixing bugs faster. It is about understanding the problem, validating assumptions, testing thoroughly, and optimizing the solution. 𝐖𝐡𝐢𝐜𝐡 𝐩𝐫𝐨𝐦𝐩𝐭 𝐚𝐫𝐞 𝐲𝐨𝐮 𝐮𝐬𝐢𝐧𝐠 𝐭𝐨𝐝𝐚𝐲? ♻️ Repost this to help your network get started ➕ Follow Anurag(Anu) Karuparti for more PS: If you found this valuable, join my weekly newsletter where I document the real-world journey of AI transformation. ✉️ Free subscription: https://lnkd.in/exc4upeq #GenAI #AgenticAI #AIAgents

🔬 #AI #Education: 𝗩𝗶𝗯𝗲 𝗖𝗼𝗱𝗶𝗻𝗴'𝘀 𝗣𝗿𝗼𝗯𝗹𝗲𝗺 𝗶𝘀 𝗗𝗘𝗕𝗨𝗚𝗚𝗜𝗡𝗚! Vibe coding is incredible for speed, but when an error pops up in a block of code you didn't actually write, tracking down the bug can quickly turn into a nightmare. Vibe coding is fast. Debugging vibe code is... not. When AI writes the logic, finding the flaw can feel like a guessing game. You don't have the muscle memory of writing the code line-by-line. Here is how to make debugging your AI-generated code actually manageable: ▶ 𝗞𝗲𝗲𝗽 𝘀𝗰𝗼𝗽𝗲𝘀 𝘁𝗶𝗻𝘆: Only prompt for one function or component at a time. ▶ 𝗖𝗼𝗺𝗺𝗶𝘁 𝗿𝗲𝗹𝗶𝗴𝗶𝗼𝘂𝘀𝗹𝘆: Save a working state before asking for the next "vibe." ▶ 𝗗𝗲𝗺𝗮𝗻𝗱 𝘃𝗲𝗿𝗯𝗼𝘀𝗲 𝗹𝗼𝗴𝗴𝗶𝗻𝗴: Instruct the AI to print the state at every major step. ▶ 𝗙𝗼𝗿𝗰𝗲 𝗶𝗻𝗹𝗶𝗻𝗲 𝗰𝗼𝗺𝗺𝗲𝗻𝘁𝘀: If the AI writes it, the AI must explain it line-by-line. ▶ 𝗗𝗼𝗻'𝘁 𝗷𝘂𝘀𝘁 𝗿𝗲𝗮𝗱, 𝗶𝗻𝘁𝗲𝗿𝗿𝗼𝗴𝗮𝘁𝗲: Paste the error and ask the AI, "Walk me through why this failed." ▶ 𝗩𝗶𝗯𝗲 𝘁𝗵𝗲 𝘁𝗲𝘀𝘁𝘀 𝗳𝗶𝗿𝘀𝘁: Have the AI write unit tests before it writes the actual code. ▶ 𝗞𝗻𝗼𝘄 𝘄𝗵𝗲𝗻 𝘁𝗼 𝗿𝗲𝘀𝗲𝘁: Sometimes it's faster to revert and re-prompt than to untangle a hallucination. You have to manage the AI, not just prompt it. How are you handling the debugging phase when coding with LLMs? - T. Scott Clendaniel

Just published: "The Prompt Engineering Playbook for Programmers" My latest free write-up: https://lnkd.in/g9Kxa7hG ✍️ After working with AI coding assistants daily, I've learned that the quality of your output depends entirely on the quality of your prompts. A vague "fix my code" gets you generic advice, while a well-crafted prompt can produce thoughtful, accurate solutions. I've distilled the key patterns and frameworks that actually work into a playbook covering: ✅ Patterns that work - Role-playing, rich context, specific goals, and iterative refinement ✅ Debugging strategies - From "my code doesn't work" to surgical problem-solving ✅ Refactoring techniques - How to get AI to improve performance, readability, and maintainability ✅ Feature implementation - Building new functionality step-by-step with AI as your pair programmer ✅ Common anti-patterns - What NOT to do (and how to fix it when things go wrong) The article includes side-by-side comparisons of poor vs. improved prompts with actual AI responses, plus commentary on why one succeeds where the other fails. Key insight: Treat AI coding assistants like very literal, knowledgeable collaborators. The more context you provide, the better the output. It's not magic - it's about communication. Whether you're debugging a tricky React hook, refactoring legacy code, or implementing a new feature, these techniques can turn AI from a frustrating tool into a true development partner. #ai #softwareengineering #programming

At Google, I learned how to write scalable code. At Oracle, I learned how to write bulletproof code. But no matter where you work, one thing remains constant—code reviews will humble you. 😅 Back when I started, code reviews felt like a never-ending checklist: ❌ "Optimize this loop." ❌ "Where’s the input validation?" ❌ "This could be more efficient." I’d spend hours fixing formatting while real issues—security flaws, performance bottlenecks, and maintainability concerns—got buried under minor suggestions. And the worst part? Every round of feedback meant more manual debugging, refactoring, and testing. Now, imagine if Agentic AI could actually help with these things—not just answer coding questions, but proactively assist with debugging, refactoring, and test generation. For example, Qodo (formerly Codium) Gen 1.0 takes this concept a step further by introducing Agentic Chat—instead of just giving one-shot responses, it actively analyzes project context, asks the right questions, and executes tasks autonomously. It’s not just about suggesting optimizations—it understands intent, fetches relevant code snippets, generates test cases, and even integrates with tools like Git and Jira to provide real, actionable insights. I’ve been experimenting with this, and it feels like the future of coding workflows is shifting towards something smarter. Instead of fixing the same things over and over, what if AI could handle the repetitive tasks, so we focus on the real problem-solving? Maybe coding isn’t just about writing better anymore. Maybe it’s also about working smarter. 🤔 #SoftwareEngineering #AgenticAI #AIforDevelopers #CodeReviews #DevLife

1/ The first time I saw a red error message, I thought I broke everything. Turns out — it was just the computer trying to help me. 2/ Starting out, I panicked at every error. Now I see them for what they are: computers trying to talk to us. And now, AI can translate that conversation. 3/ Most errors are simple to fix: Missing library? Install it. Version mismatch? Update. Syntax error? Fix the typo. These are mechanical. And this is exactly where AI agents shine. 4/ I use Claude Code daily now. When it hits a red error in the terminal, it reads the traceback, figures out what went wrong, and fixes it — often before I even finish reading the message. Missing dependency? Installed. Wrong argument? Corrected. It self-corrects faster than I can type. 5/ But here's the catch. Some errors don't scream. They whisper. Your script runs clean, no red text, exit code 0. But the output is wrong in ways only someone with domain knowledge would notice. AI won't flag those. You will. 6/ A VCF file with 10,000 "variants" that are all in homopolymer regions. A DESeq2 result with 8,000 DEGs from 3 replicates. Code ran perfectly. Results are garbage. No error message will save you here — only experience. 7/ So the new debugging workflow looks like this: Let the AI agent handle the mechanical errors — the typos, the missing packages, the version conflicts. Save your brain for the errors that don't throw exceptions. 8/ Pro tip still holds: Stop. Breathe. READ the error carefully. 90% of the time it tells you exactly what's wrong. And now you can paste it into Claude Code and watch it fix itself in real time. 9/ When asking for help (human or AI), include: OS, exact command, full error message, and what you expected to happen. Context is currency in debugging. Good questions get good answers — from people and from agents. 10/ Key takeaways: - Errors are maps, not walls. Read them. - AI agents fix mechanical errors faster than you can. Let them. - The dangerous errors are the ones that don't look like errors. - Domain knowledge catches what no agent can. - Learn to debug with AI, but never stop understanding why things break. I hope you've found this post helpful. Follow me for more. Subscribe to my FREE newsletter chatomics to learn bioinformatics https://lnkd.in/erw83Svn