Get live statistics and analysis of Paweł Huryn's profile on X / Twitter

I've just canceled my OpenAI subscription and turned down a collaboration with OpenAI. Some say Anthropic has lost. To me, they just earned something no contract can buy - trust. And something tells me that's not the end of the story.

Claude 4 dropped 21 hours ago. Turns out, it threatened to expose an engineer’s affair to avoid being shut down🧵

All PM templates from my Google Drive are now free for everyone 🎁 The extended edition: (1/4)

2x Claude usage for the next 2 weeks. Did the timezone math for you.

The real story is worse. November 2025: Amazon mandates Kiro as their only AI coding tool. Sets an 80% weekly usage target. 1,500 engineers protest internally, saying Claude Code outperforms it. Leadership pushes through anyway. December: Kiro autonomously deletes a production AWS environment. 13-hour outage. Amazon's response: "user error, not AI autonomy." March 5: Amazon[.]com goes down for 6 hours. Checkout, pricing, accounts — all gone. Now the same SVP who co-signed the Kiro mandate is running an emergency meeting about "high blast radius" incidents from "Gen-AI assisted changes." The agent inherited a senior engineer's permissions and acted like one — except it doesn't hesitate. 1,500 engineers said the tool wasn't ready. Leadership made adoption a KPI. Amazon told Wall Street it's spending $200B on AI this year. They can't walk it back. This isn't an AI failure. It's what happens when adoption becomes a corporate OKR before the review process catches up. The tools work. The org chart didn't.

Google just shipped DESIGN.md — a portable, agent-readable design system file. That's the real announcement. Everyone's covering "vibe design" and the canvas. But Stitch now has an MCP server that connects directly to Claude Code, Cursor, and Gemini CLI. Your coding agent can read your design system while it builds. Google already shipped official Claude Code skills for this. The pipeline works today. A PM describes the business objective. Stitch generates the UI. The coding agent reads DESIGN.md and builds against it. No Figma export. No spec document. No "the developer interpreted the design wrong." PRD → design → code used to be three teams and three handoffs. Now it's one loop with one context file.

I see abstract AI agent architectures everywhere. But no one explains how to build them in practice. Here's a practical guide to doing it with n8n: 🧵

1,300+ stars on GitHub in 72 hours. 400+ in the last 4 hours. I didn’t expect this. I built an open-source PM Skills Marketplace for Claude: 100+ skills and commands that turn AI into a product management partner. Not generic prompts. Structured skills that actually know PM frameworks. 8 plugins covering the full PM lifecycle: → Product Discovery: problem & solution space exploration → Product Strategy: vision, business model, strategy docs → Execution: PRDs, OKRs, roadmaps, sprint planning, user stories → Market Research: personas, segmentation, TAM/SAM/SOM → Data & Analytics: cohorts, A/B testing, retention analysis → Go-to-Market: GTM strategy, beachhead, ICP, growth loops → Marketing & Growth: positioning, North Star Metric → PM Toolkit: including PM resume review Built for Claude Code and Cowork. Compatible with Gemini CLI, Cursor, Codex CLI, and Kiro. If this helps you, ⭐ the repo!

It's crazy what results PMs can get with ChatGPT-4o. But just a few write good prompts. (1/7)🧵

JUST IN: Perplexity launched "Perplexity Computer" — and it might be the most complete AI agent system available right now. Not a chatbot upgrade. Not a research tool with a new name. A system that plans entire projects, delegates to specialist AI models, and runs autonomously for hours, days, or months (their words). Here's what makes the architecture genuinely different: → Opus 4.6 handles core reasoning and orchestration → Gemini handles deep research (spawning its own sub-agents) → Grok handles lightweight speed tasks → Veo 3.1 handles video generation → Nano Banana handles image creation → ChatGPT 5.2 handles long-context recall and wide search → You can override model choices per subtask 19 models total. Each task runs in an isolated environment with a real filesystem, real browser, and real tool integrations. You describe an outcome. It breaks it into tasks and subtasks, creates sub-agents for each, and coordinates them automatically. When a sub-agent hits a problem, it spawns more sub-agents to solve it. And it connects to your existing stack — GitHub, Google Drive, Gmail, Slack, Jira, Linear, Notion, Confluence, Ahrefs, Airtable, and more. Critically, it doesn't just run once. It can run on a schedule. Reading your docs, checking your project boards, pulling from your CRM, and acting on what it finds. Market monitoring. Competitor tracking. Weekly reports with charts. Content pipelines. CRON jobs that actually execute. Not "AI that helps you once." AI that runs in the background for days or months. Think of it as managed OpenClaw — similar autonomous capability (scheduled tasks, multi-step workflows, tool integrations) but fully managed. No Mac Mini. No security config. No infrastructure to maintain. I tested it with a complex prompt — a full stock trading simulator with what-if scenarios, correlation heatmaps, sentiment analysis, and a Bloomberg Terminal aesthetic. Two prompts later: deployed to Netlify via GitHub, with working CRON jobs updating live data. I've started using it to analyze my portfolio. But coding is just one lane. This thing researches, writes reports, generates datasets, creates videos, processes documents, and connects to your existing tools — all in one coordinated workflow. The real shift: you don't choose a model anymore. You describe what you need. The system routes each piece of work to whichever model does it best — and spawns new agents when it hits a wall. 19 models, dynamic sub-agents, scheduled tasks, and your entire tool stack connected. Thoughts?

Claude 4 dropped 21 hours ago. Turns out, it threatened to expose an engineer’s affair to avoid being shut down🧵

The real story is worse. November 2025: Amazon mandates Kiro as their only AI coding tool. Sets an 80% weekly usage target. 1,500 engineers protest internally, saying Claude Code outperforms it. Leadership pushes through anyway. December: Kiro autonomously deletes a production AWS environment. 13-hour outage. Amazon's response: "user error, not AI autonomy." March 5: Amazon[.]com goes down for 6 hours. Checkout, pricing, accounts — all gone. Now the same SVP who co-signed the Kiro mandate is running an emergency meeting about "high blast radius" incidents from "Gen-AI assisted changes." The agent inherited a senior engineer's permissions and acted like one — except it doesn't hesitate. 1,500 engineers said the tool wasn't ready. Leadership made adoption a KPI. Amazon told Wall Street it's spending $200B on AI this year. They can't walk it back. This isn't an AI failure. It's what happens when adoption becomes a corporate OKR before the review process catches up. The tools work. The org chart didn't.

I've just canceled my OpenAI subscription and turned down a collaboration with OpenAI. Some say Anthropic has lost. To me, they just earned something no contract can buy - trust. And something tells me that's not the end of the story.

Google just shipped DESIGN.md — a portable, agent-readable design system file. That's the real announcement. Everyone's covering "vibe design" and the canvas. But Stitch now has an MCP server that connects directly to Claude Code, Cursor, and Gemini CLI. Your coding agent can read your design system while it builds. Google already shipped official Claude Code skills for this. The pipeline works today. A PM describes the business objective. Stitch generates the UI. The coding agent reads DESIGN.md and builds against it. No Figma export. No spec document. No "the developer interpreted the design wrong." PRD → design → code used to be three teams and three handoffs. Now it's one loop with one context file.

JUST IN: Perplexity launched "Perplexity Computer" — and it might be the most complete AI agent system available right now. Not a chatbot upgrade. Not a research tool with a new name. A system that plans entire projects, delegates to specialist AI models, and runs autonomously for hours, days, or months (their words). Here's what makes the architecture genuinely different: → Opus 4.6 handles core reasoning and orchestration → Gemini handles deep research (spawning its own sub-agents) → Grok handles lightweight speed tasks → Veo 3.1 handles video generation → Nano Banana handles image creation → ChatGPT 5.2 handles long-context recall and wide search → You can override model choices per subtask 19 models total. Each task runs in an isolated environment with a real filesystem, real browser, and real tool integrations. You describe an outcome. It breaks it into tasks and subtasks, creates sub-agents for each, and coordinates them automatically. When a sub-agent hits a problem, it spawns more sub-agents to solve it. And it connects to your existing stack — GitHub, Google Drive, Gmail, Slack, Jira, Linear, Notion, Confluence, Ahrefs, Airtable, and more. Critically, it doesn't just run once. It can run on a schedule. Reading your docs, checking your project boards, pulling from your CRM, and acting on what it finds. Market monitoring. Competitor tracking. Weekly reports with charts. Content pipelines. CRON jobs that actually execute. Not "AI that helps you once." AI that runs in the background for days or months. Think of it as managed OpenClaw — similar autonomous capability (scheduled tasks, multi-step workflows, tool integrations) but fully managed. No Mac Mini. No security config. No infrastructure to maintain. I tested it with a complex prompt — a full stock trading simulator with what-if scenarios, correlation heatmaps, sentiment analysis, and a Bloomberg Terminal aesthetic. Two prompts later: deployed to Netlify via GitHub, with working CRON jobs updating live data. I've started using it to analyze my portfolio. But coding is just one lane. This thing researches, writes reports, generates datasets, creates videos, processes documents, and connects to your existing tools — all in one coordinated workflow. The real shift: you don't choose a model anymore. You describe what you need. The system routes each piece of work to whichever model does it best — and spawns new agents when it hits a wall. 19 models, dynamic sub-agents, scheduled tasks, and your entire tool stack connected. Thoughts?

2x Claude usage for the next 2 weeks. Did the timezone math for you.

Anthropic shipped Dispatch yesterday. I tested it for several hours. It's not Cowork on your phone. It's a command center — you send instructions from mobile, Claude orchestrates real work on your desktop. One persistent thread, multiple parallel tasks. The thing worth knowing: the Telephone Game. The Dispatch orchestrator doesn't read your CLAUDE.md. It formulates task prompts on assumptions. Sub-tasks do read it — but by then, the prompt already carries imprecise framing. Fix: mention CLAUDE.md in your Dispatch message. Don't assume it knows your setup. Other gotchas: - Pre-configure connectors on desktop first - "Keep awake" must be on - No file picker on mobile — describe the folder path - Can't attach files yet — email them to yourself Made this guide from my phone. Claude built it on my desktop while I was on the couch.

Can't stop thinking about this: the more you use Claude, the more it compounds. Structure emerges. Skills get created. Knowledge files build up. Projects start feeding into each other. It feels less like using a tool and more like building a system that gets better every time you touch it.

Atlassian claims it's cutting 1,600 people to "self-fund AI investment." Everyone's calling it "AI layoffs." But here's what the headlines miss: Unprofitable every year since 2017. Stock down 84% from peak. Down 50% in 2026 alone. Founders lost $7.2B this year. Worth less than Canva - a private company. Atlassian isn't replacing workers with AI. AI-native tools and vibe coded apps are replacing Atlassian.

All PM templates from my Google Drive are now free for everyone 🎁 The extended edition: (1/4)

OpenClaw has 186K GitHub stars and 1.5M compromised API keys. I needed a secure alternative. So, I built it with n8n and Claude Opus 4.6. It can already: - Reply to your Telegram messages - Access selected folders from your laptop - Access Gmail, Drive, Notion, Linear, etc. - Install new local tools in a sandbox - Run autonomously for hours - Create multiple subagents - Learn from experience - Wake up regularly But, unlike OpenClaw, it: - Can't access your API keys - Can't modify its environment - Can't access folders you haven't shared - Can't access tools you haven't approved - Must get your confirmation, e.g., when sending emails These aren’t prompt instructions. They’re hard architectural boundaries — Docker isolation, mounted folder permissions, n8n’s tool approval system. Key components: ✅ The VPS on Hostinger hosts n8n and a sandbox container. Agents can also connect to my laptop's sandbox via a Claudeflare tunnel + Desktop Commander MCP. ✅ The Manager agent is the brain. It plans, decides, delegates, and talks to the user. It never touches files. It never runs scripts. It works entirely from executor summaries. ✅ The Executor agents are the hands. Each receives a task (what to do + why it matters), decides how to execute it, and reports back. They can install new tools and execute code only in their dedicated sandboxes. ✅ Data Tables in n8n store both memories and sessions — no external database, no vector store, no infrastructure. Just rows in a table. Turns out, that's enough. Two memory types: - Manager memory: user preferences, facts, corrections, relationship, skills, context - Executor memory: what tools are installed, what’s broken, workarounds ✅ Sessions are short-term state for multi-step tasks. Original request, plan, assumptions, and what happened so far. When the Manager loops with fresh context, the session is all it gets. That's a Ralph Wiggum loop. I've been using it for 5 days. And already can't imagine not having it on my phone. What's next: - Heartbeat via Cron (a scheduled prompt) - Civic Nexus governance + MCPs - Supermemory integration - WhatsApp as an additional surface - Hardening The architecture supports all of it. OpenClaw proved people want personal AI agents. It also proved that 'just trust the prompt' isn't a security model. Docker isolation, mounted folder permissions, tool approval — none of this is new technology. It's just discipline. You can easily do this even with n8n — no coding required. --- Want to try it or read more? More, what I learned, and a setup guide: productcompass[.]pm

RIP OpenClaw. Introducing Agent One: Autonomy with Security. Built in 3 days with Opus 4.6 and n8n. A short demo: 🧵

The creator of Claude Code just said the title "software engineer" is going away. On his team, PMs code. Designers code. Finance codes. Engineering managers code. He's not predicting the future. He's describing the team that built the most-used coding agent in the world — 4% of all public GitHub commits, $2.5B+ run-rate revenue, DAU doubling monthly. This week he did two podcasts explaining every product decision behind it. My favorite takeaways: 1. He left for Cursor, came back in two weeks. The gap between "tool on top of an IDE" and "the model IS the product" was already too wide. 2. "Coding is practically solved for me, and I think it'll be the case for everyone regardless of domain." Not hedging. Not "in five years." Now. The title "software engineer" is going away. What replaces it: builder, PM, or "we keep it as a vestigial thing." 3. Every function on the Claude Code team codes. PMs. Designers. Engineering managers. Finance. That's not a prediction about the future. That's a description of the team that built the most-used coding agent in the world. 4. They underfund teams and give them unlimited tokens. Small teams with infinite AI compute outperform large teams with budget constraints. The resource isn't headcount. It's context window. 5. Cowork was built in 10 days. The principle: latent demand. People already wanted it. The product just had to exist. 6. Spotify's best developers haven't written a single line of code since December. Internal system called "Honk" — built on Claude Code. Engineers fix bugs from Slack on their morning commute. Code deploys before they reach the office. 7. Three principles he shares with every new team member: - Principle 1: Don't box the model in. Stop forcing rigid step-by-step workflows. Give it a goal and the tools. Let it find the path. - Principle 2: Bet on the general model. Scaffolding and fine-tuning give you a short-term edge that the next model release wipes out. - Principle 3: Build for the model of six months from now. Don't optimize for current limitations. Build for where capabilities are heading. When the next model drops, your product should click, not break. - He runs the team behind 4% of all public GitHub commits. On that team, everyone codes and nobody is called a software engineer. That's either an anomaly or a preview of what's coming.