Ziray Hao

93 posts

Ziray Hao

Ziray Hao

@zirayhao

Browsing the world, past life @PalantirTech and built @try_solar

Katılım Temmuz 2019
108 Takip Edilen159 Takipçiler
Ziray Hao
Ziray Hao@zirayhao·
@browserbase Email us and we'll ship you our printed catalog of the internet for your tesla humanoid too
English
0
0
4
111
Browserbase
Browserbase@browserbase·
Introducing Browse.sh, the largest open-source catalog of skills to reliably perform any task on the internet. We've researched hundreds of sites to give your agents the playbook they need to navigate the web.
English
51
153
2K
409.6K
Ziray Hao
Ziray Hao@zirayhao·
@pk_iv we'll automate all the 3 letter acronyms, API, MCP, USA
English
2
0
8
382
Ziray Hao retweetledi
Paul Klein IV
Paul Klein IV@pk_iv·
Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.
English
130
125
726
1.7M
Ziray Hao retweetledi
Browserbase
Browserbase@browserbase·
Browserbase helps you build agents that interact with the web. But sometimes, the edge cases require a human touch. Meet Shrey, our newest Click Engineer.
English
25
15
194
23K
Kyle Jeong
Kyle Jeong@kylejeong·
I built /schedule, but with access to your authenticated accounts in a secure browser. Using the @browserbase /cookie-sync skill, I saved my local browser cookies, and injected them into the remote browser in our schedulable Functions. The opportunities are endless, build Crons with CC to do ANYTHING a human can.
Noah Zweben@noahzweben

Use /schedule to create recurring cloud-based jobs for Claude, directly from the terminal. We use these internally to automatically resolve CI failures, push doc updates, and generally power automations that you want to exists beyond a closed laptop

English
19
26
310
49.1K
Browserbase
Browserbase@browserbase·
We're excited to announce our partnership with @PrimeIntellect to allow anyone to train browser agents. General-purpose models aren't optimized for your browser workflows, BrowserEnv lets you train one that is. Checkout browserenv.com and train your own custom model in a few hours.
English
34
42
499
190.7K
Ziray Hao retweetledi
Browserbase
Browserbase@browserbase·
Browserbase lets Claude Code test your app the way a user would. The agent uses our remote browser to thoroughly QA a login flow. All with full replay so you can watch every click.
English
5
8
66
7.1K
Browserbase
Browserbase@browserbase·
Your agents should use a remote browser built specifically for them, We revamped our Browser Skill to use our custom Stagehand CLI, It's faster than MCP tools and each run uses a new browser context, avoiding prompt injection. npx skills add browserbase/skills —skill browser
English
21
31
380
40.9K
Ziray Hao
Ziray Hao@zirayhao·
@browserbase This is a big step forward in our product lineup — Browserbase code execution opens up exciting things ahead
English
1
0
4
206
Browserbase
Browserbase@browserbase·
We just built AWS Lambda with a browser built-in. Introducing Functions, a new compute paradigm that co-locates your code and browsers to build faster browser agents. Functions lets your team focus on the product, while we handle the infrastructure.
English
33
25
264
62.7K
Ziray Hao
Ziray Hao@zirayhao·
I love when bugbot runs for 17 minutes only to tell me about the edge case that if a user whose email starts with a vowel creates a workflow within UTC window 1am to 5am, with cookies disabled, then they experience a double fetch query that could cause a front end flicker that is absolutely unacceptable UX.
English
0
0
0
26
Jason
Jason@nosajio·
can we make him work faster please?
Jason tweet media
English
1
0
3
95
Paul Klein IV
Paul Klein IV@pk_iv·
AI is controlling browsers more than ever, but our tools haven't evolved. The Playwright MCP was made for testing, not high performance automation. That's why we're building Stagehand, in public and open source. Today, it's now available in most major programming languages.
Stagehand@Stagehanddev

Stagehand is now available in every programming language. Today we're launching new SDKs in Python, Go, Ruby, Rust, Java, and more. We completely rearchitected how Stagehand works to make it the best web automation framework in every language.

English
24
15
235
26.8K
Ziray Hao
Ziray Hao@zirayhao·
@pk_iv I can see people using this to QA test the apps they're building
English
3
0
11
3.6K
Paul Klein IV
Paul Klein IV@pk_iv·
I've been using Claude Code completely wrong. I gave it a custom skill and Browser CLI tools and letting it do work for me. It can open pages, click buttons, fill in forms all from your authenticated browser. Just published it to the marketplace, install it in 2 commands.
English
57
100
1.4K
229.4K
Ziray Hao
Ziray Hao@zirayhao·
@andywang @maayanalbert @liammatteson @pk_iv Fascinating, we'll make "stop" less scary sounding. Here, "stop" is really pause. You can keep talking to the agent! There's also an "end" button, that does end the entire session. Thanks for your feedback!
English
1
0
2
58
Andy
Andy@andywang·
Got it. My other suggestion could also work and allow more use cases: have a pause button where I can revise remaining instructions. Then I can just say “visit this link to verify first, then continue with […]” Otherwise it penalizes me for not getting the prompt right in one shot, and I’d lose all steps that it did accurately already.
English
1
0
0
37
Paul Klein IV
Paul Klein IV@pk_iv·
This is one of the biggest bets I've made as a founder. Today we're launching Director 2.0: a free app that enables anyone to automate web tasks with a single prompt. Powered by Browserbase and Stagehand. It's #2 on Product Hunt now - help us get #1: producthunt.com/products/direc…
English
77
87
1K
219.4K