标签：#product

Unpopulate opinion: Fewer PRs done with proper prompting, review, and refinement usually win long term. 3 thoughtful PRs a day > 40 poorly thought ones no matter how many AI agents reviewed them.

Cuando un SaaS quiere recuperar usuarios de prueba que se quedaron a medio camino, casi siempre empieza por email. El problema es que una sola prueva mal hecha puede mezclar cohortes, disparar métricas falsas y dejar a marketing discutiendo con backend sobre datos que nunca fueron confiables. Ese tipo de campaña merece más cuidado del que parece. A simple vista solo hay que revisar asunto, CTA y enlace final, pero en la práctica también hay que comprobar segmentación, ventanas de tiempo, estados de cuenta y eventos analíticos. Si alguien en tu equipo busca cosas como facebook temp email para crear usuarios rápidos, en el fondo está intentando resolver eso: probar sin tocar bandejas reales ni contaminar reportes. Por qué los correos de reactivación confunden más de lo que ayudan Un correo de reactivación no se envía a cualquiera. Sale cuando una persona creó cuenta, probó algo, se quedó quieta y entra en una regla específica. Si esa regla se valida con datos sucios, el equipo termina optimizando un mensaje para usuarios equivocados. En SaaS esto pega fuerte porque marketing y producto suelen mirar la misma campaña con preguntas distintas. Marketing quiere saber si el copy reabre interés. Producto quiere saber si el usuario vuelve al flujo correcto. Backend quiere confirmar que la automatización no reenvía a quien ya convirtió. Cuando esas capas no se prueban juntas, aveces el correo “funciona” y aun así el experimento sale mal. Si ya estás ordenando tus pruebas de onboarding en SaaS , el siguiente paso natural es tratar la reactivación como un flujo distinto. Tiene otra intención, otra ventana de tiempo y otro riesgo de mezclar datos. Paso a paso para probar una campaña sin mezclar cohortes La forma más segura es preparar un escenario por cohorte. En vez de mandar varios usuarios de prueba al mismo inbox, creá un usuario, asignale una condición clara y validá un solo recorrido de punta a punta. Este proceso suele ser suficiente: Crear una cuenta de prueba que realmen

I've noticed something about myself. It's become much harder to get things done. I see less movement compared to my previous self. And sometimes, when I see people get so much done, tasks, projects, anything, I wonder why I can't make progress like that. Now I'm not comparing myself to Elon Musk here, I'm just wondering if I'm doing my best. For the longest time, I've wanted to build a portfolio website. But for some reason or another, I never actually ended up making it, or should I say, starting it. Whenever I had a free block of time, I wouldn't know where to start. I also have this side project I've been wanting to work on. I started it, then never made any more progress beyond the initial feasibility analysis. Why did I never allocate time to either? The Overthinking Starts Early I wanted the portfolio website to be really good. I wanted cool additions, beyond the usual "about me" and "projects" sections, I wanted things like "songs I'm obsessed with right now" and "last night I slept at." I was also looking if my fitbit has an API to show my live heart-rate on my portfolio (why would someone do that?). I was obsessed with the features, and with using the right tech to make it as efficient as possible. What stack should I even use for a portfolio? Same story with this very blog. Before writing a single word, I was wondering what stack to use. I looked into a ton of existing blogs for inspiration, how do I track views, what about comments, how do I stop a DDoS from flooding my DB if I'm storing comments, should I require auth just to leave a comment, should I support font and background color changes, themes, what's the best tool to do all of that? I've noticed this pattern with almost everything I do. I'm so obsessed with doing things right on the first attempt that I never actually make the first attempt, because "doing it right" is just too demanding. Or a related trap, when I want to do something perfectly , I discover prerequisites, and those prerequisites

AI that fights customer service for you Discussion | Link

The current Claude models give you an effort knob with five settings: low , medium , high , xhigh , max . The docs tell you what each is for. I wanted numbers, so I ran the same three real tasks across all five levels and measured tokens, latency, and quality. The results changed how I set effort, and one of them surprised me. Here is the data and what I do with it now. What effort controls Effort is not just "how much the model thinks." It controls overall token spend: how much it thinks and how it acts. Lower effort means fewer, more consolidated tool calls, less preamble, terser output. Higher effort means more exploration before answering. The default is high if you omit it. const response = await client . messages . create ({ model : " claude-opus-4-8 " , max_tokens : 16000 , thinking : { type : " adaptive " }, output_config : { effort : " medium " }, // the knob messages , }); The three tasks I picked tasks that span the range of what I actually do: Classification : label a contract finding as low/medium/high/critical. Short, scoped. Code generation : write a TypeScript function with edge-case handling. Medium difficulty. Multi-step audit : analyze a 200-line contract for vulnerabilities across functions. Hard, agentic. I ran each at all five effort levels, three times, and averaged. I scored quality against a known-correct answer for tasks 1 and 3, and by manual review for task 2. The results Task 1, classification. Quality was flat across every effort level. The right label is the right label, and the model nailed it at low just as well as at max . But token usage climbed steeply: max used roughly 8x the tokens of low for an identical answer. Latency tracked tokens. The lesson: for genuinely simple, scoped tasks, high effort is pure waste. I set classification to low . Task 2, code generation. Quality improved from low to high , then plateaued. At low the model sometimes skipped an edge case. At high it caught them. xhigh and max produced essentially the sam

By Vilius Vystartas This is the follow-up to What Actually Changed in Two Weeks . That one was about setting up a project for AI-speed delivery. This one is about something I keep re-learning on every fast delivery. You start shipping faster with AI. The code works, the feature lands, it feels good. Then a few weeks later the feedback comes back, and some of it catches you off guard. Not because anything is broken — but because a few things that seemed obvious to you weren't obvious to the other side. No drama. It happens. Here are five things I'm learning to check earlier. 1. What does "done" look like from their side? To me, done means working software. To someone else it might mean pixel-match with a design. Both are valid. What helps: A quick "what does good enough look like to you?" before the work starts. One sentence can save a lot of back and forth. 2. When will they actually look at it? Sending something doesn't mean it gets reviewed immediately. It lands in a queue like everything else. What helps: Naming a review date alongside the delivery date. "I'll share this Tuesday — could you take a look by Friday?" Turns silence from a mystery into a signal. 3. What needs to be perfect vs what can be improved later? Not everything in the feedback is the same weight. A label change and a broken flow are different things. Without saying so upfront, everything looks like an emergency. What helps: Two buckets agreed early. "Here's what I'll get right before it ships. Here's what I'd revisit in a follow-up." Makes the first feedback session more productive. 4. Could they see something before the full delivery? The first time someone sees your work often sets the tone. Showing one page or one flow halfway through can catch mismatches before they multiply. What helps: A mid-point check-in. "First page is ready — want to see if this matches what you had in mind?" Five minutes that can save a round of revisions. 5. Do they have the full picture? You've been living in this

Claude for investing in perpetuals Discussion | Link

Record Once, Send Confidently Discussion | Link

Welcome to My Generative AI Learning Journey Artificial Intelligence is changing the way we work, learn, build software, and solve problems. Every day, new AI tools, models, and technologies are being released, making it difficult to know where to begin. Instead of randomly watching videos or reading articles, I've decided to follow a structured learning path—and I'm inviting you to join me. This blog marks the beginning of a long-term Generative AI learning series. Whether you're a student, software developer, freelancer, entrepreneur, or simply curious about AI, this roadmap will help you understand what we'll learn together over the coming weeks and months. The goal isn't just to understand AI theory. It's to build practical skills that can be used in real-world projects and professional development. Why Learn Generative AI in 2026? Generative AI is no longer a futuristic concept. It is already transforming industries such as: Software Development Healthcare Education Finance Marketing Customer Support E-commerce Human Resources Design and Creativity Companies are actively seeking professionals who can build AI-powered applications, automate workflows, and integrate AI into existing systems. Learning Generative AI today means preparing for the next generation of technology. What You Can Expect from This Series This series is designed for beginners but will gradually move toward advanced concepts. Each article will build upon the previous one, making the learning process simple and structured. We'll focus on: Understanding AI concepts Learning industry terminology Exploring popular AI models Writing effective prompts Building AI applications Working with APIs Using open-source models Creating AI-powered software Deploying AI projects By the end of this journey, you'll have both theoretical knowledge and practical development experience. Complete Learning Roadmap Phase 1: AI Fundamentals We'll begin by building a strong foundation. Topics include: What is Generativ

There is a fascinating, quiet tension happening in the software engineering community right now. If you listen closely to late-night developer chats, team syncs, or tech forums, you will notice that our industry has rapidly split into two distinct schools of thought regarding the rise of AI coding tools like Cursor, Claude Code, and Copilot. On one side, you have the Traditional Developers. They argue that software engineering is a disciplined art form that cannot be replaced by text prompts. To them, unchecked AI coding is a recipe for buggy, unreadable spaghetti code, creating a technical debt nightmare for the future. On the other side, you have the Vibe Coders. This is a fast-moving generation of builders, both technical and non-technical, who believe in shipping fast, prompting quickly, and adjusting on the fly. They do not see a need to obsess over syntax when the AI can translate their intent into a working application in minutes. The reality is that both sides are entirely right. If we stop arguing over who is ruling the current meta and actually look at the core truths each camp holds, we can see exactly where the future of software development is heading. 1. The Traditional Developer is Right: Guardrails Matter The traditional development camp is fundamentally right about structure. Building a beautifully designed UI that works on a surface level is vastly different from building an enterprise-ready, scalable architecture. When you prompt an AI to build a feature, its primary objective is to satisfy the literal words in your core prompt. This is the "as long as it works" mentality. Unless you are practicing strict, spec-driven development and explicitly dictating your architectural doctrines, security protocols, and API patterns, the AI will make assumptions for you. Historically, those assumptions are optimized for speed and not long-term stability. Without deep technical oversight to catch anti-patterns, edge cases, and hidden security flaws, fast-shippe

Everyone needs a safe way to listen to music on outdoor runs. We’ve found the bone conduction headphones to grab on your way out the door.

Thanks to the AI-driven chip shortage, prices for phones, computers, and consoles are sky-high—and still climbing.

Avoid phone FOMO with our favorite smartphones that aren’t officially sold stateside but are available in markets like the UK and Europe.

Lighten your pack this summer—skip the sleeping bag and carry one of our favorite ultralight backpacking quilts instead.

If you are still using a vanilla installation of VS Code, you are leaving massive amounts of productivity on the table. We all know the standard extensions: Prettier, ESLint, GitLens. But what about the tools that actually change how you write code? Here are 7 hidden VS Code extensions that feel almost illegal to use because of how much time they save. 1. Error Lens Stop hovering over red squiggly lines. Error Lens highlights the entire line and prints the error message inline, right next to your code. You instantly know what is wrong without moving your mouse. Once you install this, you will never be able to code without it again. 2. Console Ninja Tired of switching back and forth between your browser console and your editor? Console Ninja prints console.log output and runtime errors directly in your editor, right next to the line of code that triggered it. It is like magic. 3. Turbo Console Log Highlight a variable, press Ctrl+Alt+L , and this extension automatically inserts a perfectly formatted console.log statement with the variable name and its value. It saves you hundreds of keystrokes a day. 4. Mintlify Doc Writer Writing documentation sucks. Mintlify uses AI to instantly generate beautiful, accurate JSDoc/Python docstrings for your functions. Just highlight the function and hit a button. 5. CSS Peek If you work with large HTML or React files, CSS Peek allows you to hover over a class name and instantly see (and edit) the CSS attached to it in a floating window. No more hunting through massive .css files. 6. Code Spell Checker There is nothing worse than pushing a PR and having a senior developer point out a typo in a variable name. This extension highlights spelling errors in your code, keeping your codebase looking professional. 7. WakaTime Do you actually know how much time you spend coding? WakaTime generates beautiful dashboards showing exactly which languages, projects, and files you spent your time on each week. It is incredible for tracking your own

Know what your team actually shipped today Discussion | Link

Spent the week deep-diving into my dev-publish tool, focusing on durability and orchestrator resilience. 21 commits across two repos, with a massive cleanup of the publishing logic and some much-needed architecture documentation. TL;DR There is a specific kind of satisfaction that comes from taking a tool you use every day and finally giving it the "production-grade" treatment it deserves. This week was exactly that. I spent most of my time in the guts of dev-publish , moving past the "it works on my machine" phase and into "it works even if the world is on fire" territory. With 21 commits and over 11,000 lines of code churn, I focused on making the publishing orchestrator resilient and the state durable. What I Built The star of the show this week was dev-publish . If you’ve ever tried to automate cross-platform technical writing, you know that the edge cases are where the real pain lives. I pushed 16 commits here, touching about 45 files. The diff was pretty wild: +6,926 additions and -4,289 deletions. That net positive tells part of the story, but the deletions represent me ripping out brittle logic that just wasn't cutting it. Hardening the Orchestrator The biggest win was a massive fix to make the publish state durable and the orchestrator resilient. In the previous iteration, if a network request to an API (like Dev.to) failed halfway through a multi-platform push, the state was... let's just say "vague." I spent a lot of time in src ensuring that the orchestrator can now pick up where it left off. I also documented the published-flag semantics and re-run resilience in the README. It sounds like a small thing, but knowing that a re-run won't accidentally double-post your article is a huge weight off my mind. I also spent some time on the "boring but important" stuff. I normalized how tags are handled to make them safer across different platforms and implemented a much stricter resolution for cover images. If a local image is required but missing, the tool now

For decades, developers were judged by one thing: How much code they could write. The best programmers wrote faster. Debugged faster. Built faster. That era is ending. The next generation of developers won't spend most of their time writing code. They'll spend it directing AI. Welcome to the age of the AI Orchestrator. The Evolution of Software Development Software development has always evolved. First, developers wrote machine code. Then came assembly. Then high-level languages. Then frameworks. Then cloud platforms. Then DevOps. Each evolution removed repetitive work and let developers focus on bigger problems. AI is simply the next step. But this time, it isn't replacing a tool. It's becoming a teammate. Coding Is Becoming a Smaller Part of the Job Building software isn't just writing code. A typical project includes: Understanding requirements Researching documentation Designing architecture Writing code Reviewing code Debugging Testing Writing documentation Deploying applications Monitoring production Fixing incidents Only one of those is coding. Everything else is coordination and decision-making. That's where AI is changing the game. From Programmer to Orchestrator Think about how modern teams work. A tech lead rarely writes every line of code. Instead, they: Assign work. Review solutions. Provide feedback. Make architectural decisions. Remove blockers. Developers are beginning to work with AI in much the same way. Instead of writing every function, they'll: Define the goal. Provide the right context. Choose the right tools. Review AI-generated code. Run tests. Improve weak areas. Approve the final result. The value shifts from typing code to guiding its creation. What Does an AI Orchestrator Do? An AI orchestrator doesn't ask one question and accept one answer. They manage a workflow. For example: Break a large project into smaller tasks. Give each AI the context it needs. Decide when to retrieve documentation. Decide when to search the codebase. Ask AI to g

At the beginning of June I started a “ Claude withdrawal ” challenge. The plan was to run MiniMax 3 for a month, to see if I can get the same level of quality, but at 5x less the price. Until then, Claude Code was my main driver, with MiniMax on the backup, for when I was running out of quota, or sometimes for code review. The monthly bill for Claude was $100 on the Max plan, whereas for MiniMax I would pay $20 for the Token plan. All in all, it seemed like an interesting experiment. Then, half way through the challenge, Grok came into the picture. I got a very interesting offer at $35 for 3 months, then $35/month. But Grok has something neither Claude, nor MiniMax can give me out of the shelf: video and image generations. The only unknown was if switching from Claude Code to Grok will still maintain the same coding power. So I instantly took the offer, and did whatever I had to do to understand if this was the right path. And here comes the “whatever I had to do”, in plain technical terms. Switching from Claude Code to Grok – the Actual Steps The switch itself was interesting because I didn’t want to lose the Claude Code interface. I like the harness. The way it works with my codebase, the commands, the flow. So I used a helper called cliproxyapi . It’s a small proxy that sits between the Claude Code client and whatever model you point it at. You run it locally, tell it to forward requests to Grok’s API instead of Anthropic’s. Then you launch Claude Code the same way you always do, but it talks to Grok under the hood. Here’s how it goes in practice. Step 1: Install the proxy. I used brew to install it, I’m on a Mac, and also because I wanted to have it started as a service. Step 2: Set two environment variables. One is the target API base URL, for Grok that’s something like https://api.x.ai . The other is your API key. "env" : { "ANTHROPIC_BASE_URL" : "http://localhost:8317" , "ANTHROPIC_API_KEY" : "cliproxy-local-key" } , Notice how we use “cliproxy-local-key”, be

Terminal-based AI agents have evolved considerably over the past few months, and several changes are significant enough that developers relying on these tools should be aware of them. Most notably, Google has begun retiring Gemini CLI for individual users in favor of Antigravity CLI — a closed-source successor that has drawn some pushback from the community that built out Gemini CLI's open-source ecosystem. Meanwhile, Claude Code has moved to the Opus 4.8 and Fable 5 models with a 1M-token context window, and OpenClaw, the open-source "always-on" agent, has grown into one of the most-starred projects on GitHub — alongside a documented CVE worth knowing about before deployment. I've just published an updated, fact-checked comparison covering: What actually changed with Gemini CLI's retirement, and what it means if you have scripts or CI/CD pipelines depending on it Claude Code's current model lineup, context window, and new Dynamic Workflows feature OpenClaw's architecture, extensibility via ClawHub, and the security considerations that come with deep system access A full feature-comparison table (cost, context window, open-source status, setup complexity) A practical case study walking through how all three tools can work together on a real project Would be curious to hear which of these you're using day-to-day, and whether the Gemini → Antigravity transition has affected your workflow. Full article here: Devlycan - Technology & Programming Insights Devlycan - Technology, programming, AI, lifestyle, and future trends—simple insights for the new digital generation. devlycan.com