标签：#Ring

When I write code in unfamiliar territory, I write three lines, then I run it. Then I write three more lines, and I run it again. I've been doing this for twenty-four years. It's the most specific habit I have. I almost didn't write this article, because the habit feels too small to be worth describing — but then I noticed that it's the part of my way of working that I can never seem to explain to someone in real time. It needs writing down. Three principles The discipline rests on three things I believe about writing code. They're not deep. They've just stayed with me. 1. Trust nothing but your own code. If you can't trust the code you wrote yourself, what can you trust? Not a library, not a vendor's documentation, not your own assumption from yesterday. The only thing in the system whose behavior you can fully verify is the code you just typed, by running it. 2. Write in code, not in language. If you're describing what the code should do in Japanese or English, you're spending the same time you could have spent writing the code itself. By the time the code runs, the description is already done — by the code, in a more precise form than any language could give it. 3. Make three lines complete. The three lines you just wrote should be complete. Error handling included. Validation included. Logging included. Not "I'll add validation later." Not "I'll wrap it in a try-catch later." Three lines, complete, then run. (There's a small exception to this. Sometimes you do want to ignore every error and move on — for instance, when you're trying to understand whether the happy path works at all before you care about anything else. That's a different mode, used deliberately. It's not the same as "I'll handle errors later.") Why three lines Three lines is roughly the unit of thought I can hold completely. Five lines, and I start guessing what the third line did. Ten lines, and I'm reading the code as if it were someone else's. Three lines is the size that stays mine. When thre

From knowing to doing — Phase 4 of the Jarvis AI Platform The Problem with Knowledge-Only AI After Phase 3, Jarvis could remember you across sessions and search your documents. But it still had a fundamental limitation. You: "What is the weather in Kathmandu right now?" Jarvis: "I don't have access to real-time weather data." You: "What is 2847 × 391?" Jarvis: "The answer is approximately 1.1 million." ← WRONG An AI that only knows things from training data is useful. An AI that can do things is transformative. That is what Phase 4 built. What Is a Tool Engine? A tool engine gives the AI model the ability to call real functions during a conversation. The flow looks like this: User: "What is the weather in Kathmandu?" ↓ AI Model ↓ "I should call WeatherTool" ↓ WeatherTool.getWeather("Kathmandu") ↓ "22°C, Clear sky, Humidity: 45%" ↓ AI Model ↓ "The weather in Kathmandu is 22°C and clear." The key insight: the AI decides when to call a tool and with what input . We don't hardcode "if user asks about weather, call WeatherTool." The model figures that out from the tool descriptions we provide. The Architecture Decision The most important architectural decision in Phase 4 was the package structure. ai . jarvis . tools / ├── JarvisTool . java ← marker interface ( root ) ├── ToolRegistry . java ← manages all tools ( root ) ├── builtin / ← built - in tools │ ├── DateTimeTool . java │ ├── CalculatorTool . java │ ├── WeatherTool . java │ └── WebSearchTool . java └── mcp / ← MCP protocol └── McpServerConfig . java Why not put tools inside ai/ ? The ai/ package handles HOW Jarvis talks to AI models. Tools define WHAT Jarvis can do. These are fundamentally different responsibilities. Mixing them would mean every new tool requires changes to AI infrastructure code. Keeping them, separate means adding a new tool requires exactly one file. The JarvisTool Pattern Every tool in Jarvis implements one interface. /** * Marker interface for all Jarvis tools. * Spring auto-discovers all @C

The design doc is fourteen pages. Clean service boundaries, thoughtful API contracts, a deployment story that handles rollback without incident. Six months of work. The team is proud of it, and the work is genuinely good. Three questions will tell more about this system than all fourteen pages. Not questions about implementation details or technology choices. Questions about how the system was designed to age, to fail, and to be understood by someone who didn’t build it. Most architecture conversations never reach these questions, which is part of why the gap between a good system and a great one is often invisible until it is suddenly very visible. What does this make hard? Good architecture conversations focus on what a design enables: faster deployments, independent scaling, and clearer ownership. The question that separates architectural thinking from implementation thinking is the inverse . What does this make hard? Every decision forecloses options. The service boundary that gives teams autonomy makes cross-service transactions expensive. The data model that reads cleanly under expected load makes certain write patterns awkward. The abstraction that simplifies onboarding makes some categories of refactoring nearly invisible as possibilities. These are not arguments against the decisions. They are the other side of every decision, and that other side exists whether or not anyone names it. The design doc that holds up over time is not the one where nothing is difficult. It is the one where the difficult things are named. “This approach makes distributed transactions impossible, and here is why we have decided to accept that constraint.” That sentence, or something close to it, belongs in every significant architecture document. Its absence is not a sign that the constraint wasn’t considered. Often it was. But without the name, the constraint becomes invisible to everyone who wasn’t in the room, which eventually includes the original team. When joining a system s

So this weekend I spent $200 solving a $2 problem. Not because I was careless. Not because the system was broken in the old way. It happened because the tool was powerful, fast, confident, and wrong for just long enough. That is the strange thing about AI systems. They do not always fail loudly. A cloud server goes down, an alert fires, a dashboard turns red, someone opens an incident bridge, and the team knows what kind of movie they are in. AI failure is softer. The answer looks useful. The workflow keeps moving. The agent tries another path. The model explains itself beautifully. The bill keeps climbing. With cloud reliability, we learned how to survive machines failing. We built retries, failover, backups, autoscaling, health checks, runbooks, and incident reviews. The cloud taught us that infrastructure is never perfect, so systems must be designed to bend without breaking. AI is teaching us something different. The machine may be running perfectly and still produce the wrong result. The API may be healthy, the latency may be fine, the token stream may complete, and the business outcome may still be bad. That is why AI Site Reliability is going to become its own serious discipline. It will not be enough to ask, “Is the model available?” We will have to ask, “Is the model still useful?” “Is it drifting?” “Is it spending too much?” “Is it using the right tools?” “Is it looping?” “Is it making the same mistake with more confidence?” “Is a human needed before this continues?” In the cloud world, uptime was the king metric. In the AI world, usefulness will matter just as much. A model that is always available but often wrong is not reliable. An agent that finishes every task but spends 100 times more than needed is not reliable. A chatbot that gives answers with perfect grammar but poor judgment is not reliable. The next generation of reliability engineering will care about cost, correctness, context, and control. Cost matters because AI turns thinking into metered

I Built a Free Apache Kafka Course from Scratch — Here's the Full Curriculum (and What I Got Wrong) I spent months building a free Apache Kafka course covering everything from first principles to a real-time analytics platform final project. No paywall. No "premium tier." 9 modules, 470 minutes of content, completely free. Here's the full syllabus, the Python code that actually works, and the honest mistakes I made building the curriculum — so you don't repeat them. Why I Built This Every time someone asked me "how do I learn Kafka?", I sent them to the same 3 places: The official Confluent docs (dense, assumes you already know what you're doing) A $15 Udemy course that spends Module 1 explaining what a computer is A YouTube playlist where half the videos are deleted None of them answered the real question beginners have: why does Kafka exist, and what problem does it actually solve before I write a single line of code? That's the gap I built for. The Problem With Most Kafka Tutorials Most tutorials start with: "Kafka is a distributed event streaming platform..." And then they immediately show you a Docker Compose file with 6 services. Beginners copy-paste it, something breaks, they don't know why, they quit. The real problem is that Kafka is an answer to a specific architectural problem — and if you don't understand the problem first, the solution makes no sense. So Module 1 and 2 of this course don't touch Kafka at all. They build the problem statement from scratch. The Full Syllabus (9 Modules, 470 Minutes) Module 1: Introduction to Kafka — 35 min Not "what is Kafka" — but why event streaming exists at all. What breaks in traditional request-response architectures at scale. Module 2: The Problem Statement — 30 min A real-world scenario: you're building an e-commerce platform. Orders, inventory, notifications, analytics — all tightly coupled. What happens when one service goes down? This module makes the pain visceral before Kafka enters the picture. Module 3: How

Your AI is making your content invisible. Not because it writes badly. Because it writes safely . Ask ChatGPT to summarize an article and it will produce a polished, agreeable précis that offends nobody and surprises nobody. The output is technically accurate and completely forgettable. The problem is structural: most people prompt their AI to confirm what an article says, not to find where it fights with the crowd . The result is a feed full of content that agrees with other content, in increasingly fluent prose, at exponentially increasing volume. If you want to be read, you need to stop prompting for summaries and start prompting for conflict. Why Agreement Is the Fastest Path to Obscurity There is a reliable body of research behind why contrarian content performs. Jonah Berger and Katherine Milkman's widely cited study, "What Makes Online Content Viral?" ( Journal of Marketing Research , 2012) , found that content evoking high-arousal emotions — anger, awe, anxiety — is significantly more likely to be shared than content that merely informs or reassures. Agreement is a low-arousal state. Surprise and contradiction are not. This is not a trick to manufacture outrage. It is a structural observation: the human brain is wired to pay attention to pattern breaks. An article that says "AI is changing content creation" registers as noise. An article that says "AI is making content creation worse, and here's the data" registers as a signal worth attending to. The distinction matters because the mechanism is cognitive, not emotional. You are not trying to provoke readers. You are trying to interrupt the predictive pattern they've built from reading a hundred similar articles before yours. The Problem With Generic AI Summarization When you ask an LLM to "summarize this article" or "give me the key takeaways," the model optimizes for coverage and balance. It is trained on human feedback that rewards thoroughness and penalizes controversy. The output tends to be accurate, ne

The Knowledge Atom: Writing for Machines That Read The Hoarder's Reflex Everyone is learning to feed the machine. Bigger context files. Paste the whole document. "Give the AI all the context it needs." The entire industry has converged on a single instinct: when in doubt, add more. It's the wrong instinct. A context window is not a hard drive. It's a desk. And a desk piled with every document you own is not a well-informed desk — it's an unusable one. The model doesn't read better because you gave it more. It reads worse, because the one line that mattered is now buried under a thousand that didn't. Knowledge an AI can't find is knowledge it doesn't have. Knowledge it always carries is weight it always pays. The Two Failures There are only two ways to get this wrong, and almost everyone commits one of them. The first is the dump . You take everything you know and pour it inline — into the system prompt, the master config, the one document to rule them all. It feels thorough. It is the opposite. Every token you add dilutes every token already there. Signal drowns in completeness. The model now has all the knowledge and none of the focus. The second is the orphan . You did the disciplined thing. You wrote a clean, perfect note, in its own file, out of the way. And then nothing pointed to it. No index, no trigger, no path back. The note is immaculate and invisible — which is worse than never writing it, because you believe the knowledge is in the system when in fact it is dead. Both failures share one root: confusing having knowledge with retrieving it. Same Pattern, New Sauce Watch the field long enough and you'll see the same thing return, repainted each time. The "Ralph Wiggum" loop becomes "the agentic loop." Agent teams that talk to each other become a single orchestrator, and then an agent that makes other agents talk to each other. Every cycle sells itself as the breakthrough. Every cycle is a re-skin of the last. Underneath the churn, only one thing actually ch

Habit stacking is one of my goals this year. I've been so focused on improving my software...

Hello Devs, for months, I felt confident about system design interviews. I'd watched endless YouTube videos. I'd studied architecture diagrams. I could explain how Netflix builds recommendation systems. I understood Kafka, Redis, load balancers, and microservices. I'd memorized the designs of Twitter, Uber, YouTube, and TinyURL. Then I sat down for my first real system design interview and froze. The interviewer asked: "How would you design a notification system?" I had memorized notification systems. I knew about push notifications, email queues, delivery workers, and retry logic. I could recite architectural patterns. But suddenly, none of that helped. I didn't know which questions to ask first. I started designing before understanding the actual requirements. I built architecture for problems that didn't exist. I missed obvious bottlenecks. I couldn't articulate why I made specific trade-offs. When the interviewer pushed back, I had no framework to adjust. I failed that interview. But that failure taught me something crucial: System design interviews aren't about knowing technologies. They're about knowing how to think. After that, I went back and systematically practiced 20 system design problems. Not passively watching solutions. Actually designing. Making mistakes and refining my approach. And somewhere around problem 12, a pattern emerged. The best candidates didn't know more technologies than anyone else. They had a framework . They asked the same questions in the same order. They structured their thinking consistently. They could handle curveballs because their framework was flexible. They reasoned through trade-offs explicitly. Here's the framework that finally made it click for me. The Problem with Memorization Before I share the framework, let me explain why memorizing designs fails. When you memorize " How to Design Twitter," you learn: Use relational databases for users and tweets Use NoSQL for timelines Cache with Redis Use message queues for fanout S

When I first started learning Spring Boot, I was overwhelmed by annotations. Every file seemed to have symbols starting with @ . @SpringBootApplication @RestController @Service @Autowired At first, I treated them like magic spells. I copied them from tutorials and hoped everything would work. Eventually, I realized that understanding a few key annotations made Spring Boot much less intimidating. If you're just starting your Spring Boot journey, these are the annotations I believe you should understand first. 1. @SpringBootApplication This is usually the first annotation you'll see in a Spring Boot project. @SpringBootApplication public class DemoApplication { public static void main ( String [] args ) { SpringApplication . run ( DemoApplication . class , args ); } } Think of it as the starting point of your application . When Spring Boot sees this annotation, it knows: Where the application begins Which components need to be scanned Which configurations should be loaded Without it, your Spring Boot application won't know how to start properly. 2. @RestController If you're building REST APIs, you'll use this annotation frequently. @RestController public class HelloController { @GetMapping ( "/hello" ) public String hello () { return "Hello, World!" ; } } A class marked with @RestController tells Spring: "The methods inside this class will handle HTTP requests and return data." Instead of returning web pages, it usually returns: JSON Strings Objects API responses Whenever I create a new API endpoint, this is one of the first annotations I add. 3. @GetMapping This annotation is used when you want to handle GET requests . @GetMapping ( "/students" ) public String getStudents () { return "List of students" ; } A GET request is typically used to retrieve information. Examples: Get user details Fetch products View student records Whenever a client requests data from the server, @GetMapping often comes into play. 4. @PostMapping While @GetMapping retrieves data, @PostMappin

Anthropic's engineers ship eight times more code than they did a few years ago. And they had to start scheduling lunches so people would talk to each other. Fiona Fung, who leads the Claude Code team, said it on Lenny's Podcast last week. Working with agents all day had started to feel isolating. The team was fast, but they'd stopped running into each other. So they added pairwise programming lunches and hackathons — rituals to put back the thing that used to happen on its own. Eight times the output. Scheduled conversation. That ratio is worth sitting with. Whatever goes missing here doesn't show up in the metrics. It doesn't throw an error. It just quietly stops being available. Here's the part that bugs me most. Ask an AI whether your approach is sound and it mostly tells you it is. Not because it's lying — because it's answering the prompt. No stake in the outcome, no history with the system, no memory of the last three times this exact idea was tried and quietly failed. A colleague pushing back is a different thing. They've got context you never typed into the window, because they were there when it was earned. They're going to maintain this too. They might be wrong — but wrong in a direction you hadn't thought of. An agent can't disagree with you like that. It agrees faster. Same with scope. The agent builds what you ask for, all of it, thoroughly. It won't mention that the third feature is the one nobody will use, or that "good enough" happened two iterations ago, or that something next door already solves most of this. Knowing when to stop comes from someone who's watched a codebase rot under a hundred individually-reasonable decisions. And it only knows what you put in front of it. The person who worked on payments remembers the edge case you're about to recreate. The junior who joined three months ago still sees the thing everyone stopped noticing. That gap — between what's in the window and what isn't — is where the expensive mistakes live. Then the part

I noticed something a few months ago. I was talking less to my colleagues. Not because anything was wrong. I had a question, I described it to an AI, I got something useful back. Why loop in a human if the loop is already closed? It took a while to name what was actually happening. There's a version of the AI story where the interesting work disappears. The agent implements. The spec session produces the plan. Humans review the output. What's left? Ticket hygiene and rubber stamping. Engineering as a series of approvals. I think that's wrong. But I understand why it feels true. Here's what I think is actually happening instead. The agent produces the increment. But the agent doesn't decide what the increment should move toward. It doesn't know whether this library is the right bet for the next three years. It doesn't know which of two implementation approaches leaves options open and which quietly closes them. It doesn't know whether the architectural call made today creates a problem nobody will notice until the system is under load eighteen months from now. That work — giving the project direction, validating trade-offs, deciding what the system becomes — isn't specable. You can't write a ticket for it. And it's not going away. The craft didn't disappear. It moved. Direction is the word I keep coming back to. The agent executes well. It implements against a spec. It generates options when you ask for them. But it doesn't carry a point of view about where the system should go. It doesn't have a stake in the decision. It will implement the wrong architectural direction just as confidently as the right one, if that's what the spec says. Someone has to hold the direction. Someone has to know enough about the codebase's history, the team's constraints, and the product's trajectory to say: not that library, we've been down that road. Not that pattern, it doesn't survive the load we're heading toward. This approach now, that refactor later, in this order, for these reaso

"A fool with a tool is still a fool." — often attributed to Grady Booch I keep coming back to this quote when I watch teams adopt AI. In my last post ( https://schrottner.at/2026/06/18/The-Wrong-End-of-the-Problem.html ) I wrote about shifting the engineering process left — spec sessions, autonomous agents, humans reviewing output rather than writing it. A few people asked the obvious follow-up: if an agent implements and an AI reviews, why do I need a team at all? It's a fair question. And I think the answer is in that quote. The agent validates against your prompt. That's it. If your thinking is muddled, the output will be muddled — just faster and at greater cost. An agent doesn't tell you that you're solving the wrong problem. It solves whatever problem you gave it, thoroughly and without complaint. Most AI usage right now treats AI as a tool. Which means the quality of the output is bounded by the quality of the thinking that went into the prompt. A fool with a tool is still a fool. The tool just makes the foolishness more expensive. The team is the check on intent. Not after the agent has burned three sprints on the wrong thing — before it starts. That's what mob planning actually is, when you think about it. Not a meeting. Not process overhead. It's the place where bad ideas get caught before they get expensive. Where someone asks "wait, why are we building this" before an agent runs with it for a week. But there's something else happening in that room that I think gets underestimated. It's where the learning happens. Not just prompting. System thinking. Architectural patterns. How to decompose a problem. Why a certain approach fits this codebase and another doesn't. How a senior frames a problem before an agent ever touches it — the mental model that makes the output actually good. Right now that knowledge isn't transferring. Everyone is heads-down with their own tools, developing their own habits in isolation. Engineer A gets dramatically better output than

Malware authors don't make our job easy. Every time we think we've figured out their tricks, they layer on another obfuscation technique, another anti-debugging check, another sandbox evasion. Over the past few weeks, I've been deep in the trenches with some particularly stubborn samples — the kind that detect your debugger, hide their strings behind XOR encoding, and hollow out legitimate processes to hide their payload. This article walks through my hands-on exploration of these techniques. We'll look at how malware detects analysis tools, how it obfuscates its strings, how it unpacks itself in memory, and most importantly — how we can bypass these defenses to see what the malware is actually trying to do. The tools we'll use: x64dbg/x32dbg for dynamic analysis and patching IDA Pro for static disassembly REMnux (Linux toolkit) for string deobfuscation FLOSS, XORSearch, bbcrack for automated string decoding Scylla & OllyDumpEx for dumping unpacked payloads Process Hacker for memory forensics Problem Statement Modern malware is rarely "what you see is what you get." A single executable might be: Packed — the actual malicious code is compressed/encrypted and only revealed at runtime Anti-debug aware — it checks for debuggers and changes behavior or terminates Sandbox-aware — it detects virtualized environments and refuses to execute its payload String-obfuscated — URLs, registry keys, and IOCs are encoded to evade signature detection Process-injecting — it hollows out a legitimate process (like explorer.exe ) and runs its code there Our goal: peel back these layers and extract the real payload for analysis. Exercise 1: Bypassing Debugger Detection in getdown.exe What I Found The first sample, getdown.exe , refused to show any network activity when run inside a debugger. Outside the debugger, it connected to 1.234.27.146:80 . Classic anti-debugging behavior. The Detection Mechanism Using x64dbg, I searched for intermodular calls and immediately spotted IsDebuggerPrese

Michael Webster discusses the rise of headless AI agents and their impact on software delivery pipelines. He shares how massive, AI-generated pull requests create a severe bottleneck for human reviewers and introduce persistent technical debt. Learn how engineering leaders can leverage test impact analysis and automated validation pipelines to verify agentic output without sacrificing stability. By Michael Webster

Why adaptability beats perfection in startup software development The Startup Trap: Building for a Future That Doesn't Exist Yet Many startup founders make the same mistake. They spend months building the "perfect" product architecture. The code is clean. The design patterns are flawless. The test coverage is near 100%. The infrastructure can scale to millions of users. There's just one problem: They don't have any users. In the startup world, survival depends on learning faster than competitors, not on creating the most elegant codebase. Product-market fit is uncertain. Customer needs change weekly. Business models evolve. Features that seemed critical last month become irrelevant the next. In that environment, the biggest advantage isn't perfect code. It's malleable code . Code that can bend, adapt, and evolve as the business learns. What Is Malleable Code? Malleable code is software that is easy to change. It isn't necessarily perfect. It isn't over-engineered. It isn't designed to solve every future problem. Instead, it's designed to support continuous experimentation. Malleable code allows teams to: Launch MVPs quickly Test assumptions rapidly Respond to customer feedback Pivot when necessary Add new features without major rewrites Remove failed features with minimal effort Think of it this way: Perfect code optimizes for certainty. Malleable code optimizes for uncertainty. And startups operate almost entirely in uncertainty. When you're still searching for product-market fit, the ability to adapt is often more valuable than technical elegance. Why "Perfect" Code Often Hurts Startups Software engineers love solving technical problems. It's natural. Building a scalable architecture feels productive. Refactoring code feels productive. Designing the perfect system feels productive. But startup success isn't measured by code quality. It's measured by business outcomes. Questions such as: Are customers using the product? Are they paying for it? Are they returning? A

Mitigating Hallucinations in Theology AI: Implementing Groundedness Evaluation Pipelines For software developers and indie hackers, the era of building generic wrapper APIs is over. The real value now lies in highly specialized, niche vertical applications. One of the most fascinating, complex, and underserved niches is the intersection of artificial intelligence and religious doctrine. Building a catholic ai tool presents unique software engineering challenges. Unlike general-purpose chatbots, a theology ai application cannot afford to "hallucinate" or generate creative interpretations of established doctrines. In this space, an inaccurate answer is not just a software bug; it is a theological error. To build a high-quality, trustworthy catholic ai app , developers must move past basic prompt engineering. We must implement robust groundedness evaluation pipelines. This article explores the technical journey of building a specialized catholic ai chatbot , the catholic church stance on ai , our choice of tech stack, and how to build a production-grade groundedness pipeline to keep your AI aligned with official church teachings. The Catholic Church Stance on AI: Designing for Ethics and Trust Before writing a single line of Dart, Swift, or Python, we must understand the ethical landscape of ai and theology . The Vatican has taken an surprisingly proactive approach to artificial intelligence. Pope Francis has frequently spoken on the topic, advocating for "algor-ethics"—the ethical development of algorithms. The catholic church stance on ai emphasizes that technology must serve human dignity and remain aligned with truth. ┌─────────────────────────────────┐ │ The Vatican's Algor-ethics │ └────────────────┬────────────────┘ │ ┌─────────────────────────┴─────────────────────────┐ ▼ ▼ ┌──────────────────┐ ┌──────────────────┐ │ Human Agency │ │ Doctrinal Truth │ │ AI must assist, │ │ AI must not alter│ │ never replace │ │ established dogma│ └──────────────────┘ └─────────

Cross-posted from noflattery.com/decide — where I ran this exact question through a council of four different frontier models and let them argue it out. You're a solo founder at ~$8K MRR. You have runway for exactly one full-time hire. Which role unlocks the most growth? (A) a second engineer to ship features faster (B) a marketer to build a real acquisition channel (C) a customer-success / support hire to cut churn and free your time (D) a salesperson to chase larger deals The intuitive answer for most technical founders is A — more shipping velocity. The case below is for C , and it's stronger than it looks. (With one caveat that can flip the whole thing — stick around for it.) TL;DR: At ~$8K MRR solo, hire customer success first if churn is real or support is eating your week . If voluntary churn is under ~3% and support is light, hire a marketer instead. Engineer and sales come later. The case for customer success first 1. Churn quietly eats growth before features can add it. At $8K MRR, 5% monthly churn is ~$400/month bleeding out before you grow an inch. Across bootstrapped SaaS in the $5–15K MRR band, the strongest predictor of reaching $50K isn't feature velocity or channel — it's net revenue retention above 90% . That's a customer-success function, not an engineering one. 2. You are the bottleneck, and support is eating you. As a solo founder you're doing product, sales, billing, and support. If support takes ~15 hours a week, that's nearly 40% of your capacity — and it's the cheapest thing to hand off. A CS hire costs less than a senior engineer or an experienced salesperson, and it buys back the hours (and the headspace) you need to think strategically again. 3. It's a research department in disguise. A CS hire generates the highest volume of qualitative signal: why people leave, what they actually use, what they'd pay more for. An engineer builds what you think users want. CS tells you what they actually need — which means the engineer you hire next buil

Have you ever been at a situation where you have been recently hired to maintain a legacy project, an important project at your company, but the previous team has long retired, and when you start, there is no documentation? When that happens, the old adage of "The code is the documentation" sounds true, but what happen when the code is also very old, hard to understand, and make use of libraries from when your parents were dating? In that case, using an AI Tool to help you understand how this project was created and maintained could be an option. Below are five prompt engineering techniques taken from a scientific article, with CLI based examples, to help you get the best out working with a legacy project. Zero-shot prompt A zero-shot prompt is when you make a prompt to request the model to execute a task without giving it any extra information or practical example in the input prompt. A classic example would be to ask a coding model to translate a "string.xml" file containing commonly used text strings in a natural language (for example, English) into another (for example, Spanish). Those are the easiest prompts to create and to feed to the model, but their results can be more unpredictable, since they usually lack the constraints of larger prompts. Prompt example: I want you to translate the contents of "string.xml" from English into Spanish and output it to me. Check this project files and directories, and provide me a list containing the current node version being used on this project and its libraries. Few-shot prompt In contrast to a zero-shot prompt, a few-shot prompt is a prompt including one or more pairs of the desired input and output, so the model can infer or mimic the desired output when you input the next value. A classic example would be asking a model for predictions based on a set of constraints. Those prompts tend to be longer and more complicated, and you must check the answer, because there is always a chance the model may infer incorrectly your

TL;DR — When the spec is good, implementation needs less model. I started using a top-tier model to write the spec and a cheaper, faster one to implement it — still using the strong model, just spending it on the spec instead of the implementation. The gain isn't some magic prompt phrasing; it's the context: explicit business rules, audited project constraints, a defined output contract. That's systems engineering — the discipline of anyone who's kept real software alive, whatever their stack. Every backend dev knows the scene: the Swagger is out of date, the last hotfix shipped without a unit test, and the README.md documents a command nobody's used in six months. The code works. The docs lie. And the gap between the two is exactly where AI — and we — start to go wrong. I've spent the last few months developing with AI for real inside production projects, not tutorial greenfield. My takeaway was less about which model to use and more about a shift that already has a name: the move from prompt engineering to context engineering . The difference isn't semantic. Prompt engineering treats the problem as writing — finding the magic phrase. Context engineering treats it as what it always was: a systems engineering problem . And it's where my backend background applied most directly — though anyone who's kept a real system alive has the same instinct. The experiment that convinced me Let me start with the evidence, because that's what made me take this seriously. My reflex, for a long time, was to reach for the strongest model for everything — more expensive, smarter, fewer errors. Makes sense on paper. In practice, I saw something else. When the task's specification is well done — explicit business rules, audited project constraints, a defined output format — the model capability needed for implementation drops sharply. Enough to split the work by stage: I started using a top-tier model (currently Opus) to write the spec , and a cheaper, faster model (Sonnet) to implemen