Article
AI's Unexpected Role in Enhancing My Coding Skills
I Was Wrong
When I first started using ChatGPT for SQL queries, I was blown away by how it transformed hours-long tasks into mere minutes of processing. However, This staggering efficiency brought an unexpected quandary—did I still need to improve my skills if AI could outperform me so dramatically? Initially, I saw little reason to compete against such precision. Yet, this was a fundamental misunderstanding on my part. As I integrated AI more deeply into my work, I discovered its value not just in handling tasks but in significantly enhancing my coding abilities by pushing the boundaries of what I thought possible.
Exploring the Depths of SQL with AI
ChatGPT became more than a tool; it became a mentor. As I tasked it with more complex queries, each solution it provided was not only a completed task but also a lesson in advanced SQL. This AI did not just do the work—it illuminated paths I had not even considered, turning complex data manipulation and optimisation techniques into understandable, approachable concepts.
Today, my ability to leverage advanced SQL functionalities is intricately tied to my deepened understanding of the code that AI generates. ChatGPT is instrumental in this process; it deconstructs each code line, explaining its rationale and strategy. This is not just about following steps; it is about grasping the underlying principles that make those steps effective.
Now, as I deal with more complex queries involving elaborate conditions and data filtering that require high computational effort, ChatGPT also proves invaluable from another point of view. It optimises code to ease server load and explains every step, helping me understand this area. This allows me to handle previously daunting complex tasks and equips me with the knowledge to instruct AI more effectively in the future.
Looking back on the path from doubt to reliance, I am amazed at how my perspective on AI has transformed. What began as a tool to expedite mundane tasks has blossomed into a crucial element of my professional development, pushing me to learn and adapt at an unprecedented pace.
Summary
Common questions on this article's topic
Can AI actually help you become a better programmer?
How does AI serve as a coding mentor?
Is it worth learning to code if AI can write code for you?
Can AI help with SQL query optimisation?
How has the perception of AI among developers changed?
What is the relationship between AI assistance and professional growth?
If you have any thoughts, questions, or feedback, feel free to drop me a message at mail@richardgolian.com.
Related articles
Four days in Catalonia. No computer, no AI, almost no social media. I bought this notebook so that I could write down what I would think about, and what I would come across and learn on the trip.
I am building an AI system to predict the S&P 500. It runs on my own machine, uses free public data — yfinance, FRED, the Shiller dataset — and grades every forecast against reality. This series documents the build itself: the decisions, the methodology, the mistakes. What I will eventually share from the running system is a separate question, and an honest one.
Yesterday I could not tear myself away from the computer. When I lifted my head, it was half past eight in the evening. I had been sitting alone upstairs for about three hours.
More articles
Prague, 13 May 2026. On my way to work I started thinking about something that stayed with me for days. If most routine work on a computer disappears in the next ten years, and a large share of repetitive manual work disappears with it, what happens to the flow of money? Who pays whom for what? Which economic layers will exist, how large will they be, and what relationships will run between them? This is the six-layer map I sketched as an answer.
Will AI take my job? A certified Google trainer told me in June 2024 that my profession would cease to exist. Twenty-two months later, my job title has not changed — but ninety percent of what I do during the day is different. I have delegated more of my thinking to AI agents than I thought possible. I am not afraid. This is why, and what it means for anyone asking the same question.
One hour. Fifty-five minutes. That is how long it took to build what a Czech software firm had quoted at over €50,000. I built it with Claude Code. Not a prototype. Not a proof of concept. A working tool — the one the company actually needed. By the evening of the same day, it was running on staging. This is not about Claude Code. It is about what Claude Code exposes.
I have conducted roughly one hundred and fifty practical interviews over the past four years. Fifty for data specialist roles. A hundred for advertising and performance marketing specialists. Almost every one of them involved sitting down with a candidate over a practical task — something close to a real problem we actually need to solve at the company. Not theory. Not trivia. Applied problem-solving. Over time, I started noticing a pattern.
Before you can teach AI to understand anything, you need to see what it is hiding from you.
The moment other people needed access to it, the problem changed completely. It was no longer about whether the agent could learn. It was about who gets to teach it.
I wanted to build an agent that doesn't just assist. One that acts.
This is what I learned about local vs cloud AI, and why I switched to Claude Code.