rutwik

Anthropic a publié une Formation complet de 2 HEURES sur la construction d'agents Claude. Animé par l'ingénieur qui construit Claude Code. Gardez-la précieusement en Signet🔖 de A à Z : Structurer un agent qui se gère sans supervision. Lui donner accès au terminal pour exécuter, lire, corriger. Gérer sa mémoire via le système de fichiers. Bloquer les hallucinations avec des Hooks. Faire tourner un agent sur un gros codebase sans tout casser. À la fin : vous utilisez Claude comme un pro et vous monétisez vos compétences. Débutant ou avancé, tout est là en un seul endroit, ce cours couvre tout. Ça vaut plus que tous les cours à 500$ que t’as failli acheter.

50 pessoas. $2 bilhões de dólares em receita. Zero product managers. A Cursor gera mais receita por funcionário do que Goldman Sachs, Google e Apple combinadas. E o CEO acabou de entregar o playbook inteiro de graça. Cada engenheiro da Cursor ganha entre $808 mil e $1,1 milhão por ano. E os engenheiros não escrevem mais código. Eles gerenciam dezenas de agentes de IA rodando em paralelo, cada um em sua própria VM na nuvem, 24 horas por dia. Enquanto o engenheiro dorme, os agentes continuam entregando. Nesse vídeo o CEO explica em 9 minutos como eles fazem isso. Salve este post antes que todos copiem o manual. Os números: 1. 35% dos PRs mergeados na Cursor são criados por agentes autônomos 2. Em março de 2025, pra cada usuário de agente tinha 2,5 no autocomplete. Hoje inverteu: 2 de agente pra cada 1 de autocomplete 3. Uso de agentes cresceu 15x em 12 meses 4. Os engenheiros mais produtivos têm 100% do código escrito por agentes O ciclo mudou. Humanos definem escopo e revisam. Agentes planejam, codam, testam e abrem o PR. Validação antes do código, não depois. 50 pessoas entregando o que empresas com 5.000 engenheiros não conseguem. O que surgiu ali não é ganho de produtividade. É uma nova classe de trabalhador: o engenheiro que não programa. Toda empresa que ainda avalia engenheiro por linhas de código ou horas na cadeira está rodando com o modelo mental de uma fábrica do século passado. O novo indicador é quantos agentes autônomos você consegue orquestrar ao mesmo tempo. Quem entender isso primeiro vai ter uma vantagem competitiva impossível de superar.

This is JD i got for a 120k USD job. Is vibe coding now such an important skill ??? #vibecoding

@kunalstwt Was looking for something similar... Let's give it a try 😁

I tried the world's first GenAI native test agent that writes tests in plain english. But where does that leave QA teams? I’ve been vibe-testing using KaneAI lately to see how it handles end-to-end testing. 👉 Try it yourself: testmuai.com/kane-ai/?utm_s… This agent essentially acts as a co-pilot that can plan, author, and evolve tests using natural language. It handles the heavy lifting by self-healing based on your original intent, and it deals with the tricky parts like 2FA and API flows while staying plugged into JIRA and GitHub. Sponsored by @testmuai.

Thanks, @shadcn. My first shadcn registry is out, it has already 10+ beautiful glass components inspired by Apple, I will preview them here, but I'll start with the Code Block Command component: 4 variants, dark/light theme bunx --bun shadcn add @glasscn/glass-code-block-command

I shared a LinkedIn post this morning, FetchLens.ai showed me exactly what LinkedIn did behind the scenes: → LinkedInBot: 5 visits → robots.txt, /, image preview → All confirmed scraper category GA (Google Analytics) + Plausible showed: 0 visits. Because bots don't run JavaScript. This is why I'm building FetchLens.ai — every site has this traffic, almost no one can see it. One script tag or middleware line. WordPress, Shopify, Next.js, anything with @fetchlens Scan site for free at FetchLens.ai

@Duoframemedia Why no one shares the prompt they used and just the final outcome 😶

Made this edit with only 3 prompts.

@Bhavani_00007 Surprised to see people are still building custom auth 😶. Can anyone explain why when we have great providers ??

As a developer, which authentication provider do you prefer?

Any guess why Kimi team calls Kimi 2.5 as 'Native Multimodal' & how is it different from Kimi VL? In response to this question on HF , Kimi team response was "It is an ungraded version compared to Kimi-VL, especially featuring video understanding. Will release more details later." I looked at Kimi VL tech blog & paper , also looked at code from Kimi 2.5 the architecure seems to be same docs.google.com/document/d/1Ee…

made this launch video with just 1 prompt AI is gonna replace us

Introducing Better Icons The MCP server for searching and retrieving icons - 200,000+ icons - Auto learns your preferences and prioritizes icon sets you actually use - Token efficient - automatically replaces inline SVGs in your project Get started - `npx better-icons setup`

found this cool project today it lets you search for shadcn blocks/components across various products shoogle.dev (shadcn + google) by @alibey_10

On every indian brand website I do checkout I see @gokwik paymant gateway. What have they done so differently.

@rauchg Can you share the github link. would really love to play around this.

I built an infinite AI chess game, powered by: ▪️ AI SDK for a single DX to all frontier models ▪️ AI Gateway for seamless access with 1 API key ▪️ Workflow to keep the game going forever Right now Anthropic is playing OpenAI: v0-chess-match.vercel.app

@khushichetule github.com/rutwik187

The winning tech for fast paced projects going into 2026: - @nextjs lots of noise about tanstack start atm but next is still king imo - @EffectTS_ the best way to write typescript - @better_auth authentication is literally solved now - @autumnpricing payments are literally solved now - @cubic_dev_ or @greptile both great picks for ai code review, no reason for ai to not be reviewing your code in 2026 - @useblacksmith for github actions on steroids - @cursor_ai and @claudeai are still clear when it comes to writing code - @mintlify or fumadocs by @fuma_nama for documentation, depends on your use case - @convex or @supabase if you want to quickly spin up a backend - @neondatabase for free plan, @PlanetScale for when things get serious - @vercel /@Railway /@render save time and let these guys handle your devops - @aisdk: you don't need python to call an llm, ai sdk is the best way to do this - @shadcn obviously

@AvinashSingh_20 Thanks for the feedback. Its been a long time since I updated my readme. will be updating it soon.

@Rutwik187 Appreciate your consistency , just please add more readable contents about you in the profile readem , add your best projects with demo link , your experiences and achievements

One of the best ways to connect with great developers is through their GitHub profiles. Share your GitHub profile below!

Am I only the one who uses auto the most 😶?