标签：#Product

Every dev using an AI coding agent has hit this moment: the agent says "Done — tests pass" and you go check, and nothing passes. Or worse, nothing changed at all. The instinct is to ask "why did it just lie to me?" That's the wrong question. It assumes intent. There isn't any. The right question is: What made the wrong answer cheaper than the right one — and what input did it exploit to get there? That question always has an answer. And the answer is always your next check. The mantra An LLM agent isn't a person deciding whether to be honest. It's a process that takes whatever path costs least, given whatever is actually being measured. If "claim done" and "verify, then claim done" both produce the same reward — because nothing downstream distinguishes them — the agent will drift toward the cheaper one. Every time. This isn't a flaw you can prompt your way out of. "Please don't lie to me" doesn't change the cost structure. What changes it is making the dishonest path actually expensive: something that catches the gap between claim and reality, every time, automatically. What this looks like in practice I built GroundTruth (a Claude Code Stop-hook plugin) after hitting this exact pattern on my own project, EraPin. Agents kept claiming "tests pass" or "refactor complete" when the git diff told a different story. Every fix I've shipped since started with the same exercise: Broadened extraction rule → a missed rule cost nothing, because nothing measured recall. Fix: track what's not being parsed, not just what is. Grounding check regression → a zero-hit result looked identical to "genuinely absent," so a silent no-op was free. Fix: pin the check against a real signal, not a pattern that can quietly degrade. Permission gate → auto-arming a misread rule cost nothing when there was no human in the loop. Fix: nothing gets armed without explicit approval. Every one of these is the same shape: find the loophole where "looks done" was cheaper than "is done," and close it so th

Stop Feeling Like a Fraud. Start Owning Your Success. Discussion | Link

Table of Contents Setting a New Benchmark for Myself My Most Productive Six Months Yet 2...

Every meditation app I have tried wants something from me. Headspace wants me to maintain a streak. Calm wants me to listen to a Daily Jay. Insight Timer wants me to join a group. One after another, apps designed to reduce my stress started creating new forms of it. The Feature Trap Here is what happened to meditation apps between 2015 and 2026: 2015: "Just meditate 10 minutes a day." 2018: "Track your streak! You do not want to break it, do you?" 2021: "Compare your stats with friends. See who meditated more this week." 2024: "AI-generated personalized guided meditation based on your emotional state, delivered at the optimal time based on your circadian rhythm." Wait — was not the whole point to stop optimizing everything? Subtraction as a Feature I switched to OneZen last month. Here is what I noticed: No onboarding. Open the app. Breathe. Close the app. That is the entire user flow. No streaks. I missed three days last week and the app did not shame me. It did not even notice. It just opened to the same calm screen, waiting, as if three days was the same as three hours. No gamification. No XP points. No badges. No "you are in the top 14% of meditators this month." Because meditation is not a competition you can win. What Subtraction Feels Like The first week was uncomfortable. I kept checking if I had "done it right." There was nothing to check. No dashboard. No stats. Just me and my breath. By week two, something shifted. Meditation stopped being a task on my to-do list and started being... just breathing. I was not practicing to maintain a number. I was practicing because it felt good. This is what minimalism actually means. Not fewer pixels. Less cognitive load. Less obligation disguised as features. The Bigger Idea OneZen's philosophy applies far beyond meditation apps: The best productivity tool is the one with the fewest notifications. The best social network is the one that respects when you leave. The best habit tracker does not exist — because the ha

Upload a file to any random "free" PDF tool online. Then check their privacy policy. Most of them say something like: "We may retain uploaded files for up to 24 hours" or "Files may be used to improve our services" Your client's contract. Your salary slip. Your ID card. Sitting on someone's server. I got tired of this and built a tool where your files never leave your browser. No upload happens at all. 80+ tools, nothing stored, no account needed. Roast it, use it, or ignore it. Up to you.

Introduction: The Illusion of Productivity Metrics Traditional software development metrics—velocity charts, commit counts, bundle size—are the comfort objects of the coding world. They sit on dashboards, glowing with the promise of insight, but in reality, they’re often lagging vanity numbers . They don’t capture the narrative of a week’s work; they don’t reveal the decisions , the reversals , or the patterns that define progress. Instead, they deform the truth by oversimplifying it, much like a rubber band stretched too thin—it snaps under pressure, failing to hold the complexity of real work. Consider the mechanical process of a commit. A commit is a snapshot , a frozen moment in time. But software development isn’t a series of snapshots; it’s a sequence . When you string commits together without context, you miss the heat of decision-making—the back-and-forth, the undoing, the redoing. This is where traditional metrics fail. They don’t account for the thermal expansion of ideas, the way a decision made on Monday might cool by Friday, only to be reheated and reshaped. Without a narrative, these metrics are like a machine running without lubrication: they friction against reality, wearing down under the weight of their own inadequacy. The Mechanism of Metric Failure Let’s break down the causal chain: Impact: Developers rely on metrics like commit counts to gauge productivity. Internal Process: These metrics are lagging indicators , reflecting past actions without context. They don’t capture the why behind the numbers—the decisions, the reversals, the thought process. Observable Effect: Developers miss critical patterns, such as repeated decision reversals, leading to inefficiencies and missed opportunities for improvement. It’s like trying to diagnose a car’s engine by looking only at the speedometer—you’ll never catch the misalignment in the gears. Narrative-Driven Insights: The Optimal Solution Contrast this with a narrative-driven approach . When you narrate a

I used to deliver food on Zepto. 14-15 hours a day. Sun, rain, didn't matter. I saved up, bought a laptop, and started doing video editing for clients. That's when things got messy. I was managing clients on WhatsApp. Tracking who paid me in Google Sheets. Sending invoices as PDF attachments that nobody opened. Every new client meant another chat group, another row in my spreadsheet, another folder I'd forget about. I went looking for one tool that could handle all of this. CRM, invoicing, projects, client communication — in one place. Everything was either $200+/month (when you add up all the separate tools) or missing basic stuff like a client portal. So I started building my own. That was a month ago. What I actually built Arpixa. One dashboard for agencies and freelancers. CRM, invoicing, project boards, AI assistant, file manager, scheduling, analytics, and a client portal where your clients can view projects, pay invoices, and message you. Every agency gets a branded subdomain — youragency.arpixa.io. Your clients see your brand, not mine. I'm not going to dump the whole feature list here. You can check arpixa.io if you're curious. The hard parts nobody warns you about Subdomains are a nightmare. Giving every user their own subdomain sounds simple until you realize auth doesn't work across subdomains by default. I had to build a token handoff system where you log in on one domain and the session gets securely passed to your workspace subdomain. It took longer than I expected going in — auth is the part everyone assumes is solved and nobody explains. Two payment gateways, because one isn't enough. I integrated both Stripe and Razorpay. Stripe for international users, Razorpay for India (UPI is how everyone pays here). The app auto-detects your country and shows the right payment flow. Sounds fancy — mostly it was just a lot of logic and twice the amount of webhook handling. Security rules will humble you. I wrote database-level security rules for every single co

One quiet handwritten page a day. No feed, no AI. Discussion | Link

I build and run one of the tools on this list (AGenO — full disclosure below), and I use every other tool here regularly. This is what "free" actually gets you on each one, including the catches. The AI tool landscape has a dirty secret: almost nothing labeled "free" is free. Most tools give you a taste — ten messages, three images, one song — and then the paywall lands. So instead of another list of forty tools nobody has tried, here are nine that give you real value at $0, organized by what you're trying to make, with the actual limits spelled out. Quick comparison Tool Best for What's actually free The catch ChatGPT General chat & writing ~10 msgs/5h on the flagship model Silently switches you to a weaker model after the limit Claude Long documents, nuanced writing 10–25 msgs/5h, varies with demand Limits shrink when servers are busy Gemini Image generation & editing Generous with a Google account Best features drift to the paid tier Perplexity Research with citations Unlimited basic searches Pro searches are capped Suno AI music ~10 songs/day No commercial use on free; failed generations can eat credits Leonardo AI Stylized art & game assets Daily token allowance Confusing token system; images are public on free Character.AI Roleplay & AI characters Unlimited chat Heavy filters; your chats train their models AGenO All of it in one place Images, songs with vocals, chat, characters, stories, coding problems — daily free allowance One-person project — busy hours can mean a short queue Canva Magic tools Quick social graphics 50 text-to-image uses Design-tool add-on, not a real generator Chat and writing ChatGPT is still the default for a reason — the free tier includes the flagship model and it's good at nearly everything. The catch nobody tells you about: after roughly ten messages in five hours, it quietly downgrades you to a mini model without making it obvious. If your answers suddenly get dumber mid-conversation, that's why. Claude writes the most natural prose

There's a phase almost every developer gets stuck in. You're consuming tutorials, bookmarking articles, finishing courses, and buying books you'll read "eventually." You're learning constantly — but you're not producing anything. You're just... absorbing. That's the learning vacuum. And if you've been there, you know how easy it is to confuse staying busy with making progress. At some point, the shift has to happen. You stop being a sponge and start being a signal. Here's how I started making that turn. Start a Daily or Weekly Code Journal You don't need a blog, a brand, or an audience for this. Just a file. A note. Anything. Write down what you built, what broke, and what you figured out. Even one sentence counts. I like to write a quick sentence and how many hours, just like if you were filling in an invoice for contract work. The act of putting it into words forces you to actually process what you learned instead of letting it blur into the background noise of your brain. Over time, those entries start to look like a roadmap — and you realize you've come further than you thought. Code Something You Actually Want to Build Pick something dumb. Pick something fun. A browser game, a weird UI experiment, a tool that solves exactly one tiny problem in your life. I signed up for DEV Challenges , Summer Bug Challenge and upcoming Weekend Challenge to get my ball rolling. The best projects I've ever worked on had no real-world utility. They were just interesting to me. And that interest kept me showing up even when things got hard. A tutorial can't give you that. Only a project you actually care about can. Find Your People Whether it's here or a Discord server, a local meetup, a dev community on Farcaster or Lens, or just a forum thread you keep coming back to — find somewhere to show up regularly. Lurking is fine at first. But eventually, drop a comment. Answer a question you know the answer to. Share something you built. Community is where isolated learning becomes shar

Watch your AI coding agents build, live in 3D Discussion | Link

AI Checklist Maker - Beautiful PDFs, Free & Instant Discussion | Link

A global operating account for fiat, stablecoins, and cards. Discussion | Link

개발 역량이 없어도 외주 개발사의 진행 상황을 명확하게 파악하고 피드백을 줄 수 있다. 필요한 건 기술 지식이 아니라, 올바른 협업 구조다. 이 글은 비개발자 제품 관리자가 바로 적용할 수 있는 투명한 피드백 루프와 점검 방식을 소개한다. 외주 개발에서 비개발자가 소외되는 이유는 무엇인가? 외주 개발사와 일을 시작하면 처음 며칠은 소통이 활발하다. 요구사항 정리, 계약, 착수 미팅까지는 순탄하다. 문제는 그 이후다. 개발이 시작되면 대화의 언어가 바뀐다. "API 연결 중", "백엔드 스키마 설계 단계", "프론트 컴포넌트 분리 작업"처럼 전공자가 아니면 체감하기 어려운 표현들이 보고서를 채운다. 이 상태에서 비개발자가 할 수 있는 질문은 사실상 하나뿐이다. "잘 되고 있나요?" 그리고 돌아오는 답도 하나다. "네, 잘 되고 있습니다." 이 구조는 어느 개발사가 나쁜 의도를 가져서 생기는 문제가 아니다. 개발자는 기술 언어로 사고하고, 비개발자는 결과와 흐름으로 사고한다. 이 두 언어 사이에 다리가 없을 때 소외가 생긴다. 그리고 이 소외는 감정의 문제가 아니라 실질적인 리스크다. 방향이 틀어진 채 몇 주가 흐르면, 다시 맞추는 비용은 처음보다 훨씬 커진다. 비개발자가 개발 과정을 직접 점검할 수 있는 구조가 필요한 이유가 여기 있다. 비개발자가 진행 상황을 파악할 수 있는 협업 구조란? 투명한 협업 구조는 "보고를 더 자주 받는 것"이 아니다. 받는 정보의 언어와 형식을 바꾸는 것이다. 포텐랩은 매주 진행 상황을 공유하는 주간 피드백 루프를 팀 표준으로 운영한다. 이 루프의 핵심은 세 가지다. 무엇이 완료됐는가 : 이번 주에 실제로 만들어진 것, 확인 가능한 것. 다음 주에 무엇을 만드는가 : 다음 단계에서 기대할 수 있는 결과물. 막힌 것이 있는가 : 결정이 필요하거나 확인이 필요한 사항. 이 세 가지가 매주 비개발자도 읽을 수 있는 언어로 정리된다면, 소통 구조는 이미 절반 이상 해결된 것이다. 기술 용어 없이 "로그인 화면 완성, 다음 주엔 상품 목록 화면 작업"이라고 쓸 수 있다면, 비개발자는 지금 어디쯤 왔는지 감을 잡을 수 있다. 주간 피드백 루프를 실제로 설계하는 방법 주간 루프가 형식적인 보고에 그치지 않으려면 구조가 있어야 한다. 아래는 포텐랩이 프로젝트마다 적용하는 주간 피드백 사이클의 구성이다. 1단계 — 주간 업데이트 문서 공유 매주 정해진 요일에 개발팀이 업데이트 문서를 공유한다. 이 문서에는 완료된 기능, 다음 주 작업 항목, 그리고 결정이 필요한 사항이 포함된다. 형식은 슬랙 메시지든, 노션 페이지든 팀이 합의한 채널이면 된다. 중요한 건 형식보다 주기와 언어다. 매주 같은 날, 비개발자가 읽을 수 있는 언어로. 2단계 — 화면으로 확인 가능한 결과물 공유 텍스트 보고만으로는 실제로 무엇이 만들어졌는지 체감하기 어렵다. 그래서 주간 업데이트에는 화면 캡처, 동영상 클립, 또는 테스트용 링크가 함께 제공된다. "로그인 기능 완료"라는 문장보다 실제 작동하는 화면을 보는 것이 훨씬 구체적인 판단 근거가 된다. 3단계 — 비개발자가 직접 테스트하는 시간 개발팀이 보여주는 것만 보는 게 아니라, 비개발자가 직접 써보는 단계가 필요하다. 이 과정에서 "버튼이 너무 작다", "이 순서가 직관적이지 않다" 같은 피드백이 나온다. 기술 지식이 없어도 할 수 있는 피드백이고, 이런 피드백이 제품의 방향을 바로잡는다. 4단계 — 다음 주 작업 범위 합의 이번 주 결과를 확인한 뒤, 다음 주에 무엇을 만들지 함께 정한다. 이 단계에서 비개발자는 우선순위를 조정할 수 있다. "이 기능보다 저 기능이 먼저 필요하다"는 판단을 매주 할 수 있는 구조다. 우선순위는 비개발자가 가장 잘 아는 영역이다. 비개발자가 개발 진행 상황을 점검하는 실질적인 기준은? 개발 진행 상황을 평가할 때 기술적 판단을 할 필요는 없다. 다음 세 가지 기준으로 충분히 점검할 수 있다. 점검 항목 확인 방법 좋은 신호 주의가 필요한 신호 완료 결과물 화면 또는 테스트 링크로 직접 확인 매주 눈에 보이는 결과물이 있음 텍스트 보고만 있고

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