Anatoly Sharifulin

I don’t want to buy your software anymore. I don’t. Here’s why: - You are making me manually input data - You aren’t using AI to automate my life - You won’t let me try for real before I buy - You don’t ship new AI features every week - You want me to sign a long-term contract when I’m not some huge enterprise - You make me talk to someone in sales that can’t even vibe code a website - I can’t just talk to your software like I talk to Replit, ChatGPT, Claude, etc. Why not? Why can’t I just tell it what I want to do? I don’t want to buy old software anymore. Not unless I have to.

We’re hiring a Growth Marketing Manager @AppFollowIO. Details and applying for the job: jobs.lever.co/appfollow/b646…

Finally 😍

@sama How did get that they “love it”?

More than 200k people downloaded the Codex app in the first day. And they seem to love it. CODEX FTW!

@recap_david UGC

Sora 2 API + n8n for UGC videos ... absolutely insane 🤯 this n8n workflow generates realistic influencer-style videos from just a product image. No watermark. Fully automated. (and I'm giving it away for free) Here's what this system does: → Analyzes your product image with AI vision → Creates the perfect influencer persona to promote it → Generates multiple UGC video scripts automatically → Uses OpenAI's Sora 2 to create realistic videos → Outputs videos ready for Instagram, TikTok, and Facebook The results? What used to take weeks and thousands of dollars now happens in minutes for under $5 per video. This isn't just about cutting costs – it's about scaling your creative production and driving your ROAS 50%+ higher due to on-demand, high-converting video content. Brands and agencies today spend $10,000+ per month hiring creators, shipping products, waiting weeks, and hoping for a few decent videos back. This changes the whole game for $1 per video. Want the full n8n template, all of the prompts, and a full step-by-step setup video? 1. Like & RT this post 2. Follow me (so I can dm you) 3. Comment "UGC" below I'll send you the entire system for free.

One of the most fun parts of OpenAI is watching people here level up so fast and do such excellent work. We are operating at a high level across many different disciplines and many of the people doing it have never done it before, and joined us at the beginning of their career. If you believe in people and give them a lot of responsibility and support (and pick the right people to bet on) you will be surprised on the upside more often than you think. I would love to see more companies operate this way and think we would all benefit. (This was also one of the most fun parts of startup investing.)

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at deeplearning.ai, teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started: deeplearning.ai/courses/agenti…

Everything shipped at DevDay [2025] 🧵

i can't believe this shit actually works

now that coding's been solved i spend most of my time thinking and thinking is honestly so much harder than writing code

i changed all our "loading..." states to "thinking.." we are an agentic AI startup now

We're heading to Cyprus with a team from September 10-12 and have some exciting plans lined up: client meetings, @AppFollowIO meetup and WN Conf. If you're in Cyprus, come join us: bxh17.share.hsforms.com/2FPJi22wSQROrZ…

Do you use Claude Code (or some other CLI) for a non-coding use case? I'd love to know how. Please share in the comments. If it's awesome, I'll feature you in the newsletter 👀

@sama Create a project from the scratch (empty GitHub repo). Now i can’t do it

if you are a power user, please send us feature requests! (i asked in reply to this message and they were interesting, so would like more)

@claudeai Hello 👋

You're absolutely right.

Claude can now read and update your @NotionHQ pages and @linear tickets directly through MCP. Connect your workspace tools and let Claude help manage your projects, update documentation, and track issues—all from one conversation.

Check out the latest article in my newsletter: Turning negative reviews around (direct workflow) linkedin.com/pulse/turning-… via @LinkedIn

Since we originally built Claude Code as an internal tool, we've heard a ton of questions about how our teams use it at Anthropic. Here’s an inside look on how our teams—from product engineering, to growth marketing, to legal—use Claude Code:

#WWDC 2025 was fantastic! 🎉 Liquid Glass in iOS 26 feels as revolutionary as the iOS 7 redesign - truly impressive work from @Apple. I loved the creative finale turning app reviews into music: youtu.be/_E821In6oKo?si… Want 6 out of 5 stars? Use @AppFollowIO! 😍