The more detailed you make your prompts, the better Claude Code performs. But to get it to work correctly, you need specifications so detailed that you’ve almost done the implementation.
You’re not necessarily saving time - you’re programming in Markdown instead of code. … So, to be effective, you need to behave just like Gabriel. You need to watch Claude plotting stuff in the console. As one moment it generates sensible code, then completely loses the plot the next.
Most organisations don’t even recognise what good engineering looks like. They treat software development as a commodity – a manufacturing production line – measured by how many features are shipped rather than whether the right outcomes are achieved. Few understand the value of investing in modern software engineering best practices and design – the things that make those outcomes sustainable.
I have never been the best engineer I’ve ever met.
There are no weird files that shouldn’t belong there, no duplicate implementations, and no emojis all over the place. The comments still follow the style I want and, crucially, often aren’t there. I pay close attention to the fundamentals of system architecture, code layout, and database interaction. I’m incredibly opinionated. As a result, there are certain things I don’t let the AI do. I know it won’t reach the point where I could sign off on a commit.
In Claude Code, we’ve added checkpoints—one of our most requested features—that save your progress and allow you to roll back instantly to a previous state.
Dunno. recently I’ve been using OpenAI codex. I find I can work with much longer on the 20/month plan than I can sonnet. and I’m not nearly smart enough to detect differences in the two tools approach to solutions at this time.
Quote Citation: Anthropic, “Introducing Claude Sonnet 4.
Do I program any faster? Not really. But it feels like I’ve gained 30% more time in my day because the machine is doing the work. I alternate between giving it instructions, reading a book, and reviewing the changes.
I think this is the way. and matches what I’ve experienced. Sure you can spool code from the CLI to your editor and review via git diffs. But are you accomplishing more throughput or just offloading syntaxual structure.
Code review, however, emerged as the most significant challenge. Reviewing the generated code line by line across all changes took me approximately 20 minutes. Unlike pairing with a human developer—where iterative discussions occur at a manageable pace—working with an AI system capable of generating entire modules within seconds creates a bottleneck on the human side, especially when attempting line-by-line scrutiny. This isn’t a limitation of the AI itself, but rather a reflection of human review capacity.
Some of us lean on AI coding to push side projects faster into the delivery pipeline. These are not core product features but experiments and MVP-style initiatives. For bringing that kind of work to its first version, the speed-up is real. … output quality gets worse the more context you add. The model starts pulling in irrelevant details from earlier prompts, and accuracy drops. … AI can get you 70% of the way, but the last 30% is the hard part.
“We need to stop talking about AI as a magic fix and instead focus on the specifics: where are the biggest points of friction for developers, how can AI help alleviate that friction, and specifically how should developers use AI tools to overcome that friction and move faster?” Laura Tacho, CTO at DX told LeadDev earlier this year.
Not sure if I captured this before. but writing code was never the bottleneck in software development.
AI is increasingly automating many coding tasks, accelerating software development. As models and tools improve, we see the automation of more complex coding tasks under developers’ orchestration (like the ones we interviewed). This is already reality and no longer a future trend.
I think the reality is no one ever cared how nice my lines of code were. Anyone outside of software just wants the damn thing to work. SO using AI is just another tool.
I care about what gets merged into the codebase. I don’t care how the code got in your IDE.
I want you to care.
I want people to care about quality, I want them to care about consistency, I want them to care about the long-term effects of their work. LLMs are engineering marvels, and I have the utmost respect for the people who’ve created them. But we still need to build software, not productionize prototypes.
