Extract web data at scale with multimodal codegen || YC S23 + AI Grant 3
Joined May 2023
- Tweets87
- Following1
- Followers4.8K
- Likes165
Reworkd retweeted
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 transcripts
- Syncs updates daily via API
Teams of analysts. Custom pipelines. Replaced by one intern in 48 hours.
The bar has changed.
Reworkd retweeted
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 customer support platform built for B2B.
2) @gumloop - A no-code platform for automating workflows with AI
3) @mintlify - The modern standard for documentation
4) @infisical - Open-source secrets manager for developers
5) @resend - Email for developers
6) Recall.ai - The universal API for meeting video, audio and metadata
7) @happyrobot - AI Communication. Built for Logistics.
8) @join_arc - Banking & Funding for Startups
9) @gethockeystack - The operating system for inbound B2B revenue
10) @NumeralTax - SaaS & Ecommerce sales tax on autopilot.
11) @AlloyAutomation - Alloy is a platform for building and managing SaaS integrations
12) @try_glimpse - Glimpse offers AI services for retail brands starting with deductions
13) @buildwithfern - Instantly offer SDKs and API Docs
14) @reductoai - The most accurate API to parse documents
15) @DetectDeepfakes - Enterprise Deepfake Detection
16) @AstroMechanica - Supersonics for the new Jet Age
Want the full list and scraper access? Comment “Scraper” below, and I’ll send it over.
I built this using @ReworkdAI
Reworkd retweeted
Our founding engineer built the platform's dashboard within his first two weeks.
One month in, he's crushing Linear tickets faster than we can create them🫡
Certified 🐐
Reworkd retweeted
Excited to announce our $2.75 million seed round from investors like @paulg himself, @natfriedman, @danielgross, @ycombinator, and many more ⚡️
Reworkd retweeted
Exciting news! We've successfully raised $2.75 million in our seed round, bringing our total investment to $4 million 🎉
We are thrilled to work with amazing investors like @paulg, @natfriedman, @danielgross, @svangel, @generalcatalyst , Panache Ventures, and many more.
Reworkd retweeted
🎉 TechCrunch exclusive just dropped covering our journey so far building multimodal codegen for web data extraction at @ReworkdAI!
Excited to announce our $2.75 million seed round from investors like @paulg himself, @natfriedman, @danielgross, @ycombinator, and many more ⚡️
Reworkd retweeted
📢 Excited to finally show y'all what we've been building at Reworkd!
The Internet, a planet-wide meta-cortex, is man's greatest invention. But it's a jungle—to query web data, you need an API & an engineer.
We use multimodal codegen to turn the web into structured data 🧵⬇️
Reworkd retweeted
Excited to more broadly share what we've been working on at @ReworkdAI ⚡️
This past year we've fully invested in building the next generation of web agents. They're already live in production today across a handful of companies serving as the simplest way to extract web data at scale.
Come to us with a list of 100s-1000s of websites + a data schema, and we'll handle the rest 🤖
Reworkd retweeted
TIL that @redotvideo was featured as a top 100 open source startup by YC!
I don't really know how this list is curated, but it's nice to be listed alongside companies like @gitlab or @posthog, as well as our friends at @langfuse and @ReworkdAI!
ycombinator.com/companies/in…
Reworkd retweeted
2/ Reworkd
AI agents for navigating the web and scraping data
Introducing: Tarsier— an open source framework that combines web scraping and OCR to extract text from web pages for the consumption of LLMs
@asimdotshrestha @khoomeik @ReworkdAI
Reworkd retweeted
Thank you to @cse_cst @TELUS @1Password @HermanMiller @mappedin @Deloitte @COISocial @rdbrck @icbc @GitHubEducation @Hiive_HQ @EYCanada (In-kinds): @ReworkdAI @unclefatih @rainorshineYVR @vidyard @vanstartupweek @guruenergy @Ridecycleclub, Thu Hien Deli, BAK’D, Steve’s Poké Bar!
Reworkd retweeted
Introducing Tarsier 🙈, an open source Python library to enable web interaction with multi-modal LLMs like GPT4! Here’s a demo of a Tarsier agent navigating through google to watch the OpenAI Dev day announcement:
Reworkd retweeted
Been a while but excited to show off a small AgentGPT 1.0 update ✨
Features:
- A freshly redesigned theme 🚀
- Updated agent handling with a focus on search 🌍
- @sid_ai for personalized context and queries 🦥
- Increased usage limits 📈
Try it at agentgpt.reworkd.ai/
Reworkd retweeted
Some of the open core companies I worked with in the @ycombinator S23 batch:
github.com/twentyhq/twenty
github.com/RecipeUI/RecipeUI
github.com/DioxusLabs/dioxus
github.com/xeol-io/xeol
github.com/ergomake/ergomake
github.com/khoj-ai/khoj
github.com/continuedev/conti…
github.com/reworkd/AgentGPT
Reworkd retweeted
If I remove the leaders it seems like @llama_index and @ReworkdAI (AgentGPT) also get a nice constant growth.
Reworkd retweeted
⚡️ @perplexity_ai has some of the smoothest text streaming out of all LLM apps
As a weekend hack, I recreated it with the @vercel AI SDK and @nextjs. Try it for free with #GPT4 at perplexity-style-streaming.v…