Feature gaps and roadmap planning This is one of the hardest things I've had to learn as a founder. You set out to build products to help people and solve their problems. You cobble together a MVP, emphasis on the minimum, and launch it to a bunch of users If you're
Changelog - September - Prompting guide, SVG Handling, Persistent Sessions, Advanced 2FA New Prompting Guide We just released a new prompting guide: https://docs.skyvern.com/getting-started/prompting-guide It goes into detail talking about a few gotchas. For example, did you know: 1. Skyvern works the most reliably pairing prompts with (goal, completion criteria) pairs? 1. It turns out that LLMs are
How we accidentally burned through 200GB of proxy bandwidth in 6 hours Context Skyvern is an AI agent that helps companies automate workflows in the browser. We run leverage proxy networks and run headful browser instances in the cloud to facilitate most of our automations. 😱 200GB of proxy bandwidth was approximately $500 burned over the course of 6 hours One fatal morning
The dark path to discovering our ICPs How to find ICPs to go after? This is a question I ask myself all the time. The answer is obvious, right? Who would find the most value out of Skyvern? When we first launched our product, we had no clue what kinds of things companies would want to automate
Changelog - September 4 - New pricing page, Faster live streams, and more! New Pricing page Skyvern's landing page just got a minor update – we now have a dedicated pricing page 💰! We have 2 main problems we think we can solve with a pricing page: #1: Our pricing wasn't clear at all! The only way to learn about our
How we cut token count by 11% and boosted success rate by 3.9% by using HTML instead of JSON in our LLM calls TL;DR We started using HTML instead of JSON to represent possible actions that Skyvern could take and reduced our cost by 11.8% and increased our success rate by 3.9% What’s Skyvern? Skyvern is an open source AI agent that helps companies automate browser-based workflows with AI.
Changelog - July 23 - GPT-4O Mini, Shadow DOM, CSV Support and more! GPT-4O-Mini We just launched GPT-4O-Mini support in Open Source Skyvern 🎉 OpenAI's hottest new model at a low low price-point of $0.15 / 1M input tokens.. compared to $5 / 1M input tokens for GPT-4O. https://github.com/Skyvern-AI/skyvern/commit/ec5a0a03c094bfefb5fb810cefff94935532c9e2 Retry Tasks 📃Hot off the press – you can
browser automation Changelog - 4th of July 🇺🇸 Edition #1 - Detailed billing (ie how much did I spend on that task?!) You asked, we delivered🎉 You can now see how much your tasks cost you in Skyvern's task billing page 😹 I bet you're wondering.. why did we launch Skyvern without this feature? Well... we
Analytics and attribution for an open source project a.k.a story of how we tracked an unexpected burst of traffic TL;DR: We had a spike of traffic Monday (May 6th) morning, and we looked at our metrics to find out we got featured in a french newsletter and a viral tweet Monday Morning: Random burst of traffic Last Monday morning (May 6th), we woke up to a large burst
Transitioning from Engineers to Founders -- How YC Shaped our journey As some of you may know, Skyvern is actually our third attempt at building a startup, and we’ve made every mistake under the sun in our path to get to where we are. I’m happy to say that applying to YC was not one of them, as YC
News We open-sourced and ended up #1 on Hackernews Skyvern? What’s that? Skyvern is an AI Agent that helps companies automate browser-based workflows using LLMs and Computer vision. We provide companies with a simple API that lets them automate their boring back-office workflows with natural language. How did the launch go? We spent a few hours in the