Founder of Skyvern (https://nitter.gq/t.co/aRwSa7swlf)
Joined July 2024
- Tweets2.8K
- Following112
- Followers479
- Likes626
Pinned Tweet
1/ We just raised $2.7M to give AI "hands" to do real work. 🚀
Browser automation has been broken for 20 years. If a button moves 10 pixels, your script breaks.
Meet Skyvern: The open-source agent that fixes the "maintenance tax" of automation.
FWIW I did this with our BI tool and have never been happier
I am no longer bound by their opinionated design
You don't have these problems w @skyvernai
Every engineer that hates it isn't thinking beyond their slice of the world
When I first told @MParakhin that we were planning to move to a monorepo he said wisely:
Moving to a Monorepo is an idea that every engineer absolutely hates, and that once its there, no engineer would ever want to work at a company that doesn't use one. We will definitely do it.
The internet was FUD before it wasn't... last year may have been a canary in the coalmine
The AI jobs panic peaked in May and has faded fast since:
- News reports on AI job loss are down ~65%, back to year-ago levels
- Layoff announcements that cite AI are down ~90%, near the lowest of the year
Charts of the Week: a16z.news/p/charts-of-the-we…
🚨 🚨 WEBINAR 🚨 🚨
We're doing Skyvern's first WEBINAR this week at 10am ET! COME JOIN!
Link to sign up below
Progressive disclosure is 10x better than RAG
We rebuilt Skyvern to use it and it got 2.3x faster and 50% cheaper
skyvern.com/blog/deleting-ra…
Anthropic is now recommending that companies REMOVE unnecessary subagents from their AI systems.
This is a pretty significant shift in agent architecture, with their team finding that a single agent equipped with skills can frequently outperform complex multi-agent systems, and one customer seeing roughly 2x faster execution.
The emerging rules of thumb:
→ Skills: Teach the agent HOW to do something, including procedures, expertise, and instructions.
→ Tools / MCP: Give the agent the ability to DO things through APIs, actions, and live data.
→ Subagents: Use for parallel work, isolated context, or tasks a single agent struggles with.
The interesting part is progressive disclosure. Instead of spawning specialized agents or stuffing everything into a giant prompt, one agent discovers and loads skills and tools as needed.
Their advice is to fold existing subagents into the main loop, turn their instructions into skills, expose their actions as tools, and run evals to see if performance holds up.
As models have gotten smarter, improving agent architecture is becoming less about what you can add and more about what you can delete.
claude.com/resources/article…
How to test ideas without building a complex feature
One of our customers desperately wanted us to build a new integration out
But we weren't sure if other customers want it. We could spend weeks building it and find out, but we wanted to assert it without all of that effort
So someone had a crazy idea: What if we launched that feature behind a waitlist? Let's not build anything, just put a button that says "Join waitlist" Put the integrations you want to support in the UI.
You can start learning before you start building.
Continued use does not tell me whether people love the product
YC says: "Make sure you have 100 people that love your product before you scale"
Using your product doesn't necessarily mean loving your product. Getting that wrong can bite you in ways you don't expect.
What we need to look for is growing engagement. More agents. Volume increasing. How much of their company are they running on Skyvern.
Track whether customers keep coming back. Then track whether they keep finding more reasons to.