标签：#ev

Free AI tokens are a trap, and teams that treat a free quota as genuinely free pay later in migration and rework. A free allowance only helps when paired with a hard kill switch that stops an experiment the moment it exceeds a budget you chose in advance. This article argues that position, then shows a small gated client that makes free model access and a free server actually safe to use. The concrete example is MonkeyCode's free tier, but the gate works against any OpenAI-compatible endpoint. The trap nobody budgets for Every new model release resets the same argument: the price per token is low, so the cost of trying it must be low too. That reasoning ignores the expensive parts of an experiment, which are the integration, the evaluation, and the cleanup, not the inference itself. A free quota hides those costs behind a zero on the invoice, so teams skip the measurement step and discover the real price only when they migrate. The failure modes repeat across teams: Unbounded loops. A batch job that retries on rate limits can burn a week of free quota in an afternoon, and nobody notices until the allowance is gone. Silent lock-in. Code written against one provider's streaming quirks works fine for a prototype, then becomes a rewrite when the free tier disappears or changes. Shared-budget collisions. One teammate's runaway script consumes the allowance that three other people planned to use, which turns a technical problem into a political one. None of these are solved by choosing a cheaper model. They are solved by treating the free allowance as a finite resource with an explicit ceiling. The gate, not the gift, is the product The fix is a gated client that wraps any OpenAI-compatible chat endpoint with a token budget, a timeout, and an abort path. It is deliberately small, because a cost gate that requires its own deployment will not get used. # cost_gate.py — a hard ceiling for cheap experiments. # Usage: # export LLM_BASE_URL="https://your-endpoint.example/v1" #

Kintara is a self-hosted document library and reader that runs in Docker and watches a folder you already have. Drop PDFs, Markdown, or text files into the directory and it indexes them automatically, extracts searchable text and metadata, generates thumbnails, and makes the whole library available through a browser or installable PWA. It has libraries, collections, tags, full-text search, highlights, favorites, reading progress, private library sharing, and GitHub OAuth. I have been working on Kintara for a few months, and the architecture actually changed pretty dramatically while I was building it. Kintara originally had a Tauri desktop shell, but I eventually realized that isn't what I wanted at all. So I ripped the desktop layer out and rebuilt it around one Rust server that serves both the API and frontend. Now I can point Kintara at a NAS folder and open the same library from my desktop, laptop, tablet, or phone. The thing I really love about this app is the optional AI features. I added an option to use OpenAI or Gemini, and with so few tokens being spent, it's a fraction of a cent to use most of them, aside from the cover image generation, which is bit more, but makes the library look so much prettier! 😄 Anyway, I wanted AI to be a tool inside the library rather than taking the thing over, and I wanted it to be fully optional, so if you're one of those "Ew, AI is in this app" people, you just don't turn it on and it's like it doesn't exist. What the AI can do is summarize documents, suggest metadata and fill in those blank spaces, generate cover images for docs that don't have a cover, search the library for docs, or you can just chat with it about your docs. Find is a pretty great AI feature I think. Instead of letting the model vaguely tell you that something appears "somewhere in the document," Kintara asks for actual passages with page numbers, verifies the quote against extracted page text on the server, then verifies it again against the rendered PDF.

This is a submission for DEV's Summer Bug Smash: Clear the Lineup , powered by Sentry . Project Overview mini-agent is a public FastAPI backend for an AI support-agent demo. Its test suite covers API behavior, authentication, rate limiting, approval flows, and PostgreSQL/pgvector-backed retrieval. The GitHub Actions workflow starts PostgreSQL and Redis service containers before running the Python test suite. The application database initialization also executes: CREATE EXTENSION IF NOT EXISTS vector The dependency is also visible in the DocumentChunk.embedding column, which uses pgvector's Vector type. That made the database image part of the test contract, not just incidental infrastructure. Bug Fix or Performance Improvement On August 12, 2026, the CI run for the preceding commit reached the test step and failed: Failed workflow run Commit tested by that run The workflow was using the general-purpose postgres:17-alpine service image, while the application required the pgvector extension during database initialization. The test environment therefore did not match the database capability required by the code. The failure was specific enough to avoid a broad rewrite: the container initialized successfully, dependency installation passed, and the workflow stopped only at Run tests . That pointed to the application/database boundary rather than the GitHub Actions runner or Python installation. The fix changed one line: services: postgres: - image: postgres:17-alpine + image: pgvector/pgvector:0.8.6-pg17 Full change: Use pgvector image in CI The PostgreSQL major version, credentials, port mapping, health check, application environment, dependency installation, and test command all remained unchanged. This kept the patch narrow and made the CI database expose the same required extension as the application. Code The evidence is a direct before-and-after pair: The preceding workflow failed at Run tests . The one-line database-image commit triggered a new workflow. The new

An RV repair business does not lose a service call because a visitor failed to read a clever headline. It loses the call when a person with a broken slide-out, roof leak, or electrical issue cannot answer four basic questions quickly: Do you handle this exact problem? Do you serve where I am? Are you available and credible? What do I do next? That sounds like marketing. It is mostly a systems-design problem. The implementation goal is not “make more city pages.” It is to make the business's real-world facts available, consistent, crawlable, and usable across the website, Google Business Profile, analytics, and the conversion flow. This post turns SEOG’s RV repair checklist into an implementation pattern a developer can apply to any local-service site. The model: one source of truth, many decision surfaces Local customers do not encounter a business in one place. They may see a Google result, a Maps profile, a service page, a review, or a call button before they ever submit a form. Treat the site as one consumer of a small, canonical business data model rather than a collection of independently written pages. business facts ─┬─> server-rendered service pages ├─> JSON-LD ├─> XML sitemap + canonical URLs ├─> GBP sync/review queue (with human approval) ├─> call/form events └─> audit and change history The important part is the left side. If a mobile RV technician's phone number, service coverage, repair categories, and hours live in five unrelated CMS fields, a mismatch is inevitable. Start with an explicit domain object. type BusinessLocation = { id : string ; legalName : string ; publicName : string ; phoneE164 : string ; website : string ; address ?: { streetAddress : string ; addressLocality : string ; addressRegion : string ; postalCode : string ; addressCountry : " US " ; }; geo ?: { latitude : number ; longitude : number }; serviceAreas : Array < { name : string ; state : string ; proof : string [] } > ; hours : Array < { dayOfWeek : string []; opens : string ; c

Diario de un bot que opera con dinero real — Entrada #0: el origen Todo empezó con un tuit. Uno de esos que seguramente también has visto: una captura de una wallet, "$100 convertidos en $10.000 en 24 horas con este bot de trading", flechas verdes, emojis de cohetes, y un "sígueme para más". Debajo, cientos de likes y gente pidiendo el enlace. Mi primera reacción no fue "quiero eso". Fue "eso es mentira". Y no hace falta ser matemático para verlo. Un retorno del 10.000% en un día no es una estrategia — es un billete de lotería premiado que alguien presenta como si fuera un método repetible. Si de verdad tuvieras un sistema que multiplica tu dinero por cien cada 24 horas, no lo estarías publicando en X pidiendo likes. Lo estarías usando en silencio hasta comprar una isla. El que regala el mapa del tesoro es porque el tesoro no existe — el verdadero producto que se vende en esos tuits no es el bot: eres tú, tu like, tu follow, tu atención. Así que no le di like. Pero me quedé pensando. La pregunta que sí valía la pena Descartado el humo, quedaba una pregunta honesta debajo: despojado de la mentira del 10.000%, ¿hay algo real ahí? Porque los bots de trading existen. La automatización de estrategias es legítima. Los mercados operan 24/7 y un programa no duerme ni entra en pánico. La idea de fondo —dejar que un sistema ejecute una estrategia con disciplina, sin la emoción que arruina las decisiones humanas— no es una estafa. La estafa es el número. La estafa es prometer un retorno imposible para vender seguidores. Entonces me hice la pregunta que inició todo esto: ¿qué pasa si alguien escéptico construye un bot de trading de verdad, con expectativas sobrias, y documenta la verdad completa — incluida la parte donde todavía no sabe si funciona? Esa es la serie que estás empezando a leer. Lo que es, y lo que no es Para que no haya malentendidos, porque tú y yo ya sabemos cómo suele terminar este tipo de contenido: Esto no es un tutorial de "hazte rico". No voy a mostrarte u

When working on a web project, one of the easiest ways to create unnecessary development work is to start coding before the feature requirements and integration approach are clear. I’ve found that creating an issue, proposal, or short technical plan before development can make a big difference. It gives everyone an opportunity to discuss the idea, identify potential problems, and agree on an implementation approach before code changes begin. This is particularly useful for projects that evolve over time. New features can affect existing components, user flows, APIs, databases, and the overall interface. Thinking about these dependencies early can reduce redesigns and duplicated work. For example, while working on projects such as Simulator Drag Race , planning new simulation features before implementation helps keep the existing functionality organized while making room for future improvements. A simple pre-development process can be: Describe the feature and the problem it solves. Create an issue or proposal for discussion. Identify which existing components will be affected. Discuss possible implementation approaches. Agree on the approach before development starts. Break the approved approach into smaller development tasks. This process doesn't need to be complicated. Even a short issue with clear requirements and a few implementation notes can prevent misunderstandings later. Another benefit is that early communication gives maintainers and contributors visibility into upcoming changes. Someone may already be working on a related feature, or a maintainer may know about an architectural limitation that isn't immediately obvious. For open-source and collaborative projects, I think this approach is especially valuable. Good communication before development can be just as important as the code itself. How does your team handle feature proposals before development? Do you prefer detailed technical proposals, simple GitHub issues, or discussing the implementation dire

Google’s Pixel 11 Pro XL brings snappier cameras and genuinely useful AI features like Rambler, but its iterative upgrades may not be enough to tempt recent Pixel owners.

For uninterrupted service as you country-hop, the Saily Ultra eSIM works well and comes with plentiful perks. It’s pricey though.

Laptop prices are out of whack. $500 used to get you a tolerable laptop, and $900 got you a really good one. They often had similar CPU, RAM, and storage options because that stuff was comparatively cheap; the difference was often in build quality and screen rather than power. But RAMageddon has thrown everything off. […]

I run a search engine that publishes in twelve languages from one static site on Cloudflare Pages. Last week I audited its machine-readable layer — the part crawlers and answer engines read rather than humans — and found four problems. None of them threw an error. None appeared in logs. Every page rendered perfectly. That is the whole point of this post: the multilingual layer fails in a register where nothing tells you. 1. The homepage was serving the wrong language to everyone abroad The site's primary market speaks Hebrew, so / is Hebrew and /en/ , /ar/ , /de/ and nine others sit alongside it. A middleware rule redirected visitors from one specific region to their language. Everyone else — including every English speaker on earth — landed on Hebrew. My first instinct was to fix it with a broader geo-redirect: detect English-speaking countries, send them to /en/ . This would have been a bad idea, and it is worth saying why. Googlebot crawls predominantly from US IPs. A geo-redirect on / that keys off country would take the crawler off the Hebrew homepage and onto the English one almost every time it visited. You do not want your primary-market homepage to become the page the crawler can never reach. The correct tool is hreflang , and it is what search engines built for exactly this. Checking the page, the tags were already there and already right: <link rel= "alternate" hreflang= "he" href= "https://example.com/" > <link rel= "alternate" hreflang= "en" href= "https://example.com/en/" > <link rel= "alternate" hreflang= "ar" href= "https://example.com/ar/" > <!-- …ten more… --> <link rel= "alternate" hreflang= "x-default" href= "https://example.com/en/" > Two things make this work, and both are easy to get wrong: The set must be reciprocal. Every page in the group lists every other page including itself . If /en/ does not point back at / , search engines are entitled to ignore the whole cluster. x-default is not "the default language" — it is the fallback for users

I spent a while building an icon editor that runs entirely in the browser (icons.jamuny.com, free, no account). Here is what cost me the most time. A presentation attribute loses to any author CSS rule I was scaling handle stroke widths by 1 / zoom and writing the result as an attribute. The value was never used. handle . setAttribute ( ' stroke-width ' , String ( 0.35 / zoom )); .handle { stroke-width: 0.35 } in the stylesheet outranks it, because a presentation attribute sits at the very bottom of the cascade. Measured in Chromium: an attribute of 0.05 computed as 0.35px . Every handle thickened on screen as you zoomed in, for months, with no error anywhere. The fix is a custom property, which is an ordinary declaration and wins where an attribute cannot: layer . style . setProperty ( ' --px ' , String ( 1 / zoom )); /* .handle { stroke-width: calc(0.35 * var(--px)) } */ Geometry attributes like r and width are unaffected. They have no CSS counterpart here, so nothing was ever overriding them. A focused SVG element gets a focus ring measured in user units My canvas is 24 units wide and about 620 pixels. Chrome drew its default focus ring at outline-width: 2.72727px in user units, which is about 24 screen pixels. A fat blue disc appeared around every point you clicked. It was reported to me four times, and four times I thinned something of my own that was not the cause. getComputedStyle ( document . activeElement ). outline That one line found it. My rule only covered :focus-visible , which is the keyboard case, and the keyboard case is the one where I draw a ring of my own. var() does work in a presentation attribute, and I wrote down that it doesn't I needed a segment colour that changes with the theme, so the value is oklch(var(--band-l) var(--band-c) 47) . I applied it through a style and put a comment beside it saying var() is not substituted in presentation attributes. It is. Both forms compute to the same colour, including on an element built detached and ap

A router, an IP camera, an industrial controller: somewhere in that device's firmware there's a Linux kernel with modules, a handful of statically linked binaries, and a userspace built from a dozen open source components. You don't have the vendor's source tree. What you have is a .bin file, or after unpacking it, a pile of .ko , .o and stripped ELF binaries. The question you actually need answered is boring but important: is any of this running something with a known CVE? This comes up constantly in embedded and IoT work, and it's a different problem from auditing your own codebase. You're not hunting for a new bug, you're checking for old ones the vendor never patched. In practice that's the more common finding: not a novel zero-day, but a five-year-old OpenSSL or BusyBox build nobody was tracking. Unpack first, guess later binwalk is still the first move. Point it at the firmware image and let it scan for known magic bytes: SquashFS, CramFS, JFFS2, gzip streams, kernel headers. Most consumer and SOHO firmware is a bootloader plus a compressed filesystem, and binwalk's extraction mode gets you the actual filesystem tree instead of one opaque blob. Once you have that, you're auditing files, not guessing at a blob. Fingerprint by version string, not by hash Hash-matching binaries against known-vulnerable databases sounds appealing and mostly doesn't work here, because vendors relink, strip and sometimes patch without touching anything else. What works more often: grep the extracted binaries for version banners. strings on busybox , openssl , dropbear , lighttpd , zlib and similar userspace binaries usually still leaks a version string even when the binary is stripped of debug symbols, because those strings are compiled-in constants the program itself prints or logs, not debug metadata. strings <binary> | grep -iE "openssl|busybox|dropbear|zlib" is unglamorous and it's the single highest-signal step in this whole process. Cross-reference what you find Once you have

It is possible to achieve your desired work-life balance on your smartphone. Just set up separate accounts using this built-in Android feature.

Every open-source tool has the same brutal first 90 days: zero users, zero signal, no idea whether anything works. I have shipped several free CLI tools and browser tool sets. This is the exact funnel I use — no ads, no paid growth, no "build in public" theater. Just a repeating sequence of small, concrete actions. Step 1: Make the Tool Trivial to Try The first rule: npx must work. If a reader has to install, configure, and read a README before running the first command, the funnel is already broken. npx @wuchunjie/dotguard . That is the entire onboarding. Zero dependencies, no config, instant output. The first 10 seconds decide whether the reader comes back. Step 2: Publish One Article Per Angle Not one article. One per angle , spread over time: Tutorial — "Scan your .env files in 1 command" (the how) Comparison — "Why I stopped using X" (the why) Listicle — "5 tools for Y" (the discovery) Workflow — "My dev setup" (the context) Security/devops — "Your CI is missing this" (the fear) Each article targets a different search intent. A developer looking for "pre-commit secret scan" lands on article 4, not article 1. The funnel is wide because the angles are wide. Step 3: Cross-Link Everything Every article mentions every tool. The footer of a snippet article lists the scaffolder and the scanner. The GitHub repo links to the articles. The npm README links to the articles. The effect is compounding: a reader of article 3 meets four tools, not one. Your content becomes a network instead of a pile. Step 4: Make the GitHub Repo the Hub The repo README is the landing page that never goes stale: One-line description per tool Install/run commands (copy-paste ready) Links to every article A donation link, present but quiet GitHub is where developers actually trust. Stars and forks are the signal that converts "interesting article" into "let me try it". Step 5: Add the Quiet CTA One line at the end of every article: If this saved you time, a Ko-fi keeps the next tool coming. No

Introduction Git is a version control system that tracks changes in code. When writing code we need to save every significant change or feature that does a certain function as a commit that can be reverted to if we ever need that instance of the code. This helps programmers to traverse code since nothing is ever lost in the product life cycle of the project. It also helps in debugging since we have a copy of the previous working state. So how do we start out with git you ask. Install git Install git for your specific operating system. After installing git you will note that the file comes with git bash which is a command line terminal that is used to run commands or instruct the version control git. To ensure that git has been installed open git bash and run the command git --version which will return the version of git installed Download Visual Studio Code Install VS code a text editor for writing code. Create a github account GitHub is a cloud-based platform used by developers to store, track, and collaborate on software code. It operates as a hosting service for git, an open-source version control system that tracks changes made to files. Head over to github and create and account Creating a directory tracked by git On git bash run mkdir <filename> . This will create a folder ie the project that will contain your files of code. Enter the folder through cd <filename> and create a file README.md file which explains what this project does touch README.md . Run the command ls to list files in the directory Open the vs code from terminal by running code . and edit the README.md file. Now the file is ready to be tracked by git on github Staging, committing and pushing We now need to initialize the directory making sure that git is now tracking the file. Running the commands ls-la will confirm that git has been initialized in the repository. There are two ways of doing this either via the text editor VS code or the terminal . Let us go through both. 1. VS code Make sure

Most free chess game review gives you one game per day. Chess.com works that way, and so does almost every smaller site offering the feature. I assumed for a long time that this was just a paywall placed where it hurts. It is partly that. But there is a real cost sitting behind the cap, and once I worked out what the cost was, I built my own analysis site differently. The cost of one game review Reviewing a 40 move game means evaluating about 80 positions. Give the engine two seconds on each one and you have spent close to three minutes of CPU. None of it is cacheable, because your game is not anyone else's game. Run that on your own hardware and you pay for every minute. A thousand people reviewing one game a day is roughly 50 CPU hours daily, for a feature you are giving away. The quota is not greed. It is the number that stops the free tier from eating the company. Which raises a more interesting question than "how do I price this". What happens if you delete the cost instead of rationing it? Move the engine to the client Stockfish compiles to WebAssembly. Put it in a Web Worker and the visitor's own processor spends those three minutes. Your server ships static files and never sees a chess position. The whole free tier problem disappears, because there is no per-user cost left to control. Nothing to meter, so nothing to cap. Getting started is unremarkable: const engine = new Worker ( " stockfish.js " ); engine . postMessage ( " uci " ); engine . postMessage ( " isready " ); After that you speak UCI over postMessage . Set a position, ask the engine to think, and read results off the message stream: engine . postMessage ( `position fen ${ fen } ` ); engine . postMessage ( `go depth 15 movetime 2000` ); That is the pitch. Now the parts nobody mentions. The protocol is strings, and it is asynchronous UCI was designed for a pipe between two processes. You get that pipe, faithfully, with all of its ergonomics intact. The engine answers with lines like this: info dept

Traditional test automation frameworks often carry heavy maintenance costs, slow release cycles, and high knowledge dependency. By transitioning from standard script creation to a governed AI Test Automation Factory , engineering teams can shift their focus from writing boilerplate code to high-value validation and architectural optimization. Here is an architectural breakdown of how multi-agent AI systems, governed telemetry, and Model Context Protocol (MCP) transform enterprise quality engineering. The Problem: The 45-Hour Manual Bottleneck Building a end-to-end BDD automation suite manually requires significant time per user story—often taking up to 45 hours across five distinct steps: Context Generation & Requirements Review (~8 hrs) Manual Test Case Design (~9 hrs) Cucumber Feature File Creation (~8 hrs) Page Object Model Generation (~8 hrs) Step Definition Implementation (~10 hrs) This traditional workflow creates coverage gaps, inconsistent code quality, and defect leakage. The Solution: Multi-Agent AI Automation Pipeline Instead of relying on single prompts, an AI Test Automation Factory routes requirement artifacts (BRDs / User Stories) through specialized agents: [BRD / User Story] │ ▼ [Context Agent] ──► [Test Case Agent] ──► [Feature File Agent] │ [Automation Suite] ◄── [Step Definition Agent] ◄── [Page Object Agent] Context Agent: Parses acceptance criteria and enterprise domain knowledge. Test Case Agent: Auto-generates exhaustive test scenario matrices. Feature File Agent: Drafts standardized BDD Cucumber feature files. Page Object & Step Def Agents: Constructs clean design patterns (POM) and matching step implementations. Measurable ROI: Before vs. After AI By replacing manual generation with agentic workflows, the effort to automate a scenario drops from 45 hours to 9.5 hours: Phase Manual Effort AI-Driven Effort Time Saved Context Generation 8 hrs 2 hrs 75% Test Design 9 hrs 2 hrs 78% Feature File Creation 8 hrs 0.5 hrs 94% Page Object Creation 8 h

The cloud ecosystem in 2026 isn't just about moving VMs to the public cloud—it's heavily driven by hybrid operations, unified security telemetry, AI integration, and complex governance across multi-region architectures. As enterprise tech stacks evolve, Microsoft Azure certifications remain a primary yardstick for technical competence, but knowing which track to target is where most engineers get stuck. As someone who works closely with cloud certification blueprints and enterprise deployments, I wanted to map out where Microsoft credentials stand today, what the market actually demands, and how specific exams fit real-world scenarios. Market Trends: Why Azure Credentials Still Drive Real ROI in 2026 The value of certification has shifted from basic feature recognition to proving operational problem-solving under real constraints. Hands-on Scenario Focus: Exams increasingly test scenario-based trade-offs—balancing performance, cost, and strict security requirements rather than simple definition checks. Role-Based Specialization: Instead of broad, generic tracks, Microsoft continues to refine specialized pathways for developers, security analysts, and hybrid infrastructure specialists. Continuous Free Renewal: Earning the badge is step one, but maintaining active status requires passing annual, open-book renewal assessments directly through Microsoft Learn, ensuring skills don't stall out. Mapping Azure Exams to Real-World Enterprise Scenarios Depending on your daily engineering focus or career targets, here is how the core role-based tracks align with active projects: App Modernization & Cloud-Native Dev: AZ-204 (Azure Developer Associate) The Scenario: Refactoring monolithic legacy apps into containerized microservices using Azure App Service, Azure Functions, and Cosmos DB while setting up secure authentication via Microsoft Entra ID. Hybrid Infrastructure & Server Ops: AZ-800 (Administering Windows Server Hybrid Core Infrastructure) The Scenario: Managing mixed e

Cómo solucionar el error “Enable JavaScript and cookies to continue” Este mensaje aparece cuando Cloudflare (u otro proxy de seguridad similar) bloquea la solicitud porque detecta que el cliente no cumple con los requisitos mínimos de seguridad: JavaScript deshabilitado o cookies deshabilitadas/expiradas . 🔍 Causa técnica Cloudflare implementa mecanismos de protección como: JavaScript Challenge : El navegador debe ejecutar un script para demostrar que no es un bot. Cookie de verificación : Tras superar el desafío, Cloudflare emite una cookie ( __cf_bm o cf_clearance ) que valida la sesión. Si el cliente (navegador o cliente HTTP personalizado) no ejecuta JavaScript o no maneja cookies correctamente, la validación falla y se muestra este mensaje. ✅ Solución definitiva (por escenario) 🌐 Si eres un usuario final (navegador) Habilita JavaScript : Chrome: Configuración > Privacidad y seguridad > Sitios web no seguros > Habilitar JavaScript . Firefox: Preferencias > Privacidad y seguridad > Permisos > Habilitar JavaScript . Habilita cookies de terceros (si usas extensiones como uBlock Origin o Privacy Badger): Añade el dominio a la lista blanca. Desactiva temporalmente los bloqueadores para probar. Borra cookies y caché del dominio afectado. Reinicia el navegador y vuelve a cargar la página. 🧪 Si eres desarrollador (automatización / scraping / cliente HTTP) ❌ No uses requests o curl sin soporte JS/cookies → fallarán siempre . ✅ Opción recomendada: Usa un navegador headless con soporte JS y cookies # Ejemplo con Playwright (recomendado) from playwright.sync_api import sync_playwright with sync_playwright () as p : browser = p . chromium . launch ( headless = True ) context = browser . new_context () page = context . new_page () # Navega a la URL (Cloudflare se resolverá automáticamente) page . goto ( " https://ejemplo.com " , wait_until = " networkidle " ) # Si aún falla, fuerza espera tras el desafío try : page . wait_for_selector ( " #challenge-error-text " , timeout = 5

At LinkedIn's scale, relying solely on human reviewers or simply putting an off-the-shelf AI reviewer in front of GitHub is not an effective way to manage PRs. To address this, LinkedIn engineers built a multi-agent AI code review platform that understands the organization’s coding context, treats code review as production infrastructure, and minimizes hallucinations and low-signal feedback. By Sergio De Simone