An intern at a YC startup needed to extract SEC filings + earnings data for all Fortune 100 companies. He shipped it in 2 days using GPT-4.1 — and got a return offer. The agent: - Scrapes each company’s investor relations page - Pulls 10-Ks, 10-Qs, earnings slides, and

Seeing this during @OpenAI Dev day was really cool

If you’re raising a Series A, you should definitely apply!! Office hour with @daltonc was one of our favorite parts of YC. His advice in our early days helped shape the company & avoid classic startup pitfalls. Reworkd wouldn’t have been possible without him.

After 12+ years, 25 batches, and the privilege of advising >1,000+ startups, I’m transitioning to Partner Emeritus at Y Combinator. YC changed my life. I’m grateful to the thousands of founders who trusted me with their journeys, my fellow YC partners and teammates, and to Paul,

https://t.co/UxLNPm4tZb

100,000 users in 7 days. $2,000/day burn. No funding. Almost bankrupt. That’s how our MVP launch went. 2 years ago, me, @asimdotshrestha , and @wtkns_ were tinkering with AI agents before they went mainstream. We built AgentGPT and applied to YC. Then we launched on Twitter.

Sign up at https://t.co/0CtoSyQM8n to build your own scrapers

Want to build better agentic pipelines? Check this out: I demoed a flow a few weeks ago in Seattle outlining some of our learnings. 🔑points: mix classical ML w/ LLMs, keep pipelines tight and the answer to everything: robust evals.

April Product Update 🎉 - Browser Traces – One viewer with Reworkd/Playwright events, console logs, network activity, and CDP events for easier debugging. - Inline Code Diffs – View side-by-side additions and deletions between the new code and the previous version. - Weekly

If you want to join an early-stage YC startup, I’ve handpicked 15 Series A companies that are currently hiring right now. Using GPT-4.1, I built scrapers that have already pulled 125+ open roles and I’ll keep adding more over the next few weeks. 1) @usepylon - The only

Build your own custom scraper at

An ecommerce tech company almost spent $450K+ on 3 engineers to build scrapers for 200 sites. GPT-4.1 now does it with just a single SWE. - Agents auto-generate site-specific Playwright code - Auto-heal when selectors break & redeploy on the fly

AI writes your code. Now it talks to your users. We raised $27M from @Sequoia to build @ListenLabs. Listen runs thousands of interviews to uncover what users want, why they churn, and what makes them convert. See how @Microsoft and @canva use it:

Revyl team is cracked - highly recommend applying if you’re interested.

since raising from @paulg & @natfriedman last year, my old team at reworkd has been applying the latest advances in codegen to help enterprise cos collect huge structured datasets from across the web now they’ve opened the tool for general availability so you can try it too!

Reworkd is your scraping co-pilot. It understands website structures and auto-generates Playwright code to take actions, visit subpages, scrape, and save data based on your custom schema. With @ReworkdAI you can simplify web data extraction at scale. https://t.co/eZhBt4PuXK

You can support us by liking our Product Hunt post and leaving a comment. Our launch is live at https://t.co/XziBVTEOnn 🫡🫡

Designed for high scalability, our solution enables you to rapidly expand your extraction efforts. Whether you’re targeting dozens or thousands of websites, our platform maintains consistent performance, letting you scale your operations effortlessly.

Monitor your scraping projects in real-time. Track outputs, scraper failures, unique results, visited pages, website review status, file downloads, and more.

Our platform seamlessly handles proxy management and anti-bot measures, including captcha solving and rotating proxy types. This ensures your scrapers remain undetected, allowing uninterrupted data extraction across even the most guarded websites.