Clear Thinking in Data, Cloud, and AI

The world of software development is in constant flux, but few forces have driven as profound a shift as artificial intelligence. What once seemed like science fiction is now an everyday reality, with AI tools seamlessly integrating into developer workflows, promising not just incremental gains but a fundamental redefinition of productivity. In 2025, developers are finding themselves empowered by intelligent assistants, automated guardians of code quality, and even AI “colleagues” capable of tackling complex engineering tasks.

I have written a bunch of articles in CODE Magazine about AI. All of them have focused on learning AI, such as image generation, creating a local chat bot, and more. But what if you’re not an AI developer? Maybe you’re a ReactJS developer writing front-end code all day long. Or maybe you write REST APIs using Python all day long.

Let’s be honest, AI is exciting, but many of us are still working day-in-day-out delivering business functionality code, things your employer needs today. Should you ignore AI? Far from it. This article explores how AI is boosting developer productivity across the software development lifecycle, complete with practical examples to illustrate its transformative power.

The AI-Powered Developer: A New Paradigm

As of today, at its core, AI for developers isn’t about replacing human creativity; it’s about augmenting it. By offloading repetitive, time-consuming, and error-prone tasks, AI frees developers to focus on higher-level problem-solving, architectural design, and innovative solutions. This shift fosters a more engaging and less frustrating development experience.

Let’s dive into the key areas where AI is making a tangible difference.

There are many ways I see that AI can help you as a developer. This is by no means an exhaustive list, if you have ideas do share.

AI as Your Pair Programmer

The most visible and widely adopted application of AI in development is in code generation and intelligent completion. There are many competing tools you can use. Tools like GitHub Copilot, Tabnine, and Amazon CodeWhisperer act as highly intelligent pair programmers, anticipating your next move and suggesting relevant code snippets, entire functions, or even boilerplate structures. In fact, there are VSCode extensions that let you plug into any AI model to get specific help for your scenario. You can even use Ollama to run things locally if you’re in an air-gapped secure environment. Of course, the capabilities of cloud-based models are far ahead of what Ollama on your local machine can do, but Ollama with a local model is still superpowers that you didn’t know you had.

There are many benefits of incorporating AI as your pair programmer.

The first is, of course, speed. Using AI drastically reduces the time spent on writing repetitive code or searching for syntax. How often do you find yourself struggling to find the right syntax for a particular thing you’re trying to do? Or writing repetitive code that you know you can write, but would rather have a helper write for you, and maybe even write it better than you? Like, find username out of a jwt token. I know how to do this, I just wish I didn’t have to do this in every project I land in. Yes you decode the token, which means first convert base 64 to JSON, oh wait, first separate the three parts of the token, validate the signature, blah blah! Dear AI: Just do this for me, please?

The other obvious advantage is accuracy. Using AI minimizes typos and common syntax errors, leading to fewer debugging cycles. When I was a programmer in my teens, I took great pride in my accuracy and typing capabilities. I could type at > 140WPM without errors. Alas, as time has passed, my fingers have too grown older. I do make mistakes now. Unfortunate mistakes that take forever to find the errors they introduce. All because of a stupid typo. If I can have Microsoft Word correct my spelling mistakes, wouldn’t it be nice if AI can fix the errors my IDE cannot catch?

And finally, like any good pair programmer, I learn from my AI buddy. See I’ve never been a fan of pair programming. I know I know, you can put those daggers back in their sheaths. But I learn differently from others. When I’m deep into programming, I don’t want another person interrupting my thought process, or constantly interrupting asking questions. Pair programming may be great for the new person on the team, but as an experienced programmer (sorry for putting myself on a pedestal), I found pair programming was a lot of giveth and not enough taketh. I want to pair program with someone better than me, and those can be hard to find.

…this article is continued online. Click here to continue

AI is like working with an inept wizard. (Yes, I have a lot of metaphors for this.) When you ask the wizard a question, he responds with the intellect and rapidity of someone who has access to the knowledge of the cosmos. He’s read everything, but he’s a bit dotty. He’s lived his entire life in his lair, consuming his tomes. Despite his vast knowledge, he has no idea what happened in the world yesterday. He doesn’t know what’s in your inbox. Moreover, he knows nothing about your contact list, your company’s proprietary data, or the fact that your cousin’s birthday party got bumped to next Friday. The wizard is a genius. He’s also an idiot savant.

Therein lies the paradox. We have designed amazing tools, but they require a lot of handholding. Context has to be spoon-fed. You can paste an entire mountain of reference documents and a virtual novel of a prompt. That amount of work can often eliminate any benefit you get from using an LLM at all. When it does work, it’s a victory but it feels like you’ve wrestled the LLM into submission instead of working with it.

Users have been cobbling together ad hoc solutions for this problem. Plug-ins. Vector databases. Retrieval systems. These Band-Aids are clever, but fragile. They don’t cooperate with each other. They break when you switch providers. It’s less “responsible plumbing” and more “duct tape and prayer.”

This is where Model Context Protocol (MCP) comes in. It establishes a foundational infrastructure rather than creating one more marketplace for custom connectors. MCP sets up standardized rails for integrating context. This shared framework enables models to request context, retrieve it from authorized sources, and securely use it. It replaces the current kluge of vendor-specific solutions with a unified protocol designed to connect AI to real world systems and data.

As AI transitions from an experimental novelty to practical infrastructure, this utility becomes crucial. For the wizard to be effective, he needs to be able to do more than solve one-off code hiccups or create content for your blog. For true usefulness at scale in a professional environment you need a standardized way to integrate context. That context has to respect permissions, meet security standards, and be up to date.

The Problem of Context in AI

Models tend to make things up and they do it with confidence. Sometimes they cite fictional academic papers. Sometimes they invent dates, statistics, or even people. These hallucinations are a huge problem, of course, but they’re a symptom of a much larger issue: a lack of context.

The Context Window Problem

Developers have been trying to develop workarounds by providing relevant data as needed. Pasting in documents, providing chunks of a database, and formulating absurdly robust prompts. These fixes are great, but every LLM has what we call a context window. The window determines how many tokens a model can remember at any given time. Some of the bigger LLMs have windows that can accommodate hundreds of thousands of tokens, but users still quickly find ways to hit that wall.

Bigger context windows should be the answer, right? But there’s our Catch 22: The more data you provide within that window, the more fragile the entire set up becomes. If there’s not enough context, the model may very well just make stuff up. If you provide too much, the model bogs down or becomes too pricey to run.

The Patchwork Fixes

The AI community wasn’t content to wait for one of the big players to provide a solution. Everyone rushed to be first-to-market with an assortment of potential fixes.

Custom plug-ins let the models access external tools and databases, extending their abilities beyond the frozen training data. You can see the issue here. Plug-ins designed for one platform won’t work with another. Your workspace becomes siloed and fragmented, forcing you to rework your integrations if you try to switch AI providers.

Retrieval Augmented Generation (RAG) converts documents to embed them into a vector database so that you can pull only the most relevant chunks during a query. This method is pretty effective but requires significant technical skills and ongoing fine-tuning based on your organization’s specific requirements.

… this article is continued online. Click here to continue