Browserbase

860 posts

Browserbase banner
Browserbase

Browserbase

@browserbase

give your agents access to the whole web - creators of @stagehanddev & @trydirector

sf Katılım Şubat 2024
54 Takip Edilen20.2K Takipçiler
Sabitlenmiş Tweet
Browserbase
Browserbase@browserbase·
We've received hundreds of registrations for Navigate 2026. Have you submitted yours? We're not unveiling the full agenda yet, but a preview can't hurt 👀 → Anthropic on shipping and scaling browser agents with Claude Skills → Vercel and Ramp on building agent first companies → Fireworks, Modal, and Okta on the state of agent infra ecosystem → Agents in production stories from Applied Compute, Keycard, ███, ████, █████████, and ████████ Save your seat below ⬇️
Browserbase tweet media
English
2
4
33
4K
Browserbase retweetledi
Magicare.AI
Magicare.AI@magicareai·
Couldn’t have said it better ourselves ❤️ Patient data still lives behind dozens of pre-API portals. So we built agents that don’t just fetch data, they reason. Hundreds of browser agents run per case on @browserbase, turning 60-minute manual reviews into 60-second clinical decisions: 📈 200,000+ referrals 📄 2M+ documents 💬 500,000+ messages All so admissions teams can focus on patients, not paperwork. Thank you for helping us make this possible! @browserbase
Browserbase@browserbase

Magicare turned a 60-minute admissions decision into 60 seconds with Browserbase. Patient data lives behind dozens of portals built before APIs existed. The only way in is the way a human gets in: through a browser. So @Magicareai runs hundreds of browser agents per case on Browserbase: > 200,000+ referrals > 2M+ documents > 500,000+ messages Patients, not paperwork. Read the full story 👇

English
0
1
4
496
Browserbase
Browserbase@browserbase·
Magicare turned a 60-minute admissions decision into 60 seconds with Browserbase. Patient data lives behind dozens of portals built before APIs existed. The only way in is the way a human gets in: through a browser. So @Magicareai runs hundreds of browser agents per case on Browserbase: > 200,000+ referrals > 2M+ documents > 500,000+ messages Patients, not paperwork. Read the full story 👇
Browserbase tweet media
English
2
1
24
5.9K
Browserbase retweetledi
Vibrant Labs
Vibrant Labs@VibrantLabsAI·
1/n For browser agents, a major bottleneck in evaluation is truthful scoring on the live web. A task is only as good as your ability to confirm the agent actually did it, on a real site whose state keeps moving and that the agent can potentially misreport. So we took matters into our own hands. Today, we're releasing Ecom Bench on @PrimeIntellect: 40 shopping tasks on real Shopify storefronts, each run in a live @browserbase browser and graded by a deterministic verifier. vibrantlabs.com/research/ecom-…
Vibrant Labs tweet media
English
7
9
26
4.9K
Browserbase retweetledi
Jay
Jay@JaySahnan·
introducing the /competitor-analysis skill out-ship other startups by analyzing their product, landing pages and socials game changing for GTM teams to adjust marketing copy, customer stories, and more
English
22
35
489
48.5K
Browserbase
Browserbase@browserbase·
We've received hundreds of registrations for Navigate 2026. Have you submitted yours? We're not unveiling the full agenda yet, but a preview can't hurt 👀 → Anthropic on shipping and scaling browser agents with Claude Skills → Vercel and Ramp on building agent first companies → Fireworks, Modal, and Okta on the state of agent infra ecosystem → Agents in production stories from Applied Compute, Keycard, ███, ████, █████████, and ████████ Save your seat below ⬇️
Browserbase tweet media
English
2
4
33
4K
Browserbase retweetledi
christina cook
christina cook@tinathetechie·
In town for Config? Come work from the Browserbase office ☕️ Fast Wi-Fi, free coffee + matcha, a quiet place to focus, and a chance to meet designers + the Browserbase team.
christina cook tweet mediachristina cook tweet mediachristina cook tweet mediachristina cook tweet media
English
19
8
137
17.1K
Browserbase retweetledi
Shrey Pandya
Shrey Pandya@shreypandya·
New to SF? we're hosting a happy hour at @browserbase HQ with our friends from @harvey and @reductoai. come by next Tuesday to meet engineers & founders building agents automating busy work on behalf of humans. demos & drinks included🥂 (not pictured: @yash_s_gupta)
Shrey Pandya tweet mediaShrey Pandya tweet media
English
12
6
55
4.1K
Browserbase
Browserbase@browserbase·
Anything you can do in a browser, your agent can too. A Browserbase Browser is real Chromium in the cloud, built for agents with identity, login persistence, live view, and full session replay built in. You build the agent, and we'll be the boring infrastructure underneath. Read our blog explaining what a Browserbase Browser really is. 👇
English
3
6
34
2.4K
Browserbase
Browserbase@browserbase·
We’re launching the conference for the best teams shipping agents: Navigate 2026 🌎 Join us on Sept 10th in SF for: → Keynotes and firesides from Anthropic, Vercel, Ramp, Modal, Okta, and more → Technical workshops from teams running agents at scale → Deep dives on evals, orchestration, memory, and the infra layer underneath it all Register below 👇
English
23
12
144
88.3K
Browserbase
Browserbase@browserbase·
Excited to partner with Anthropic on Managed Agents, The Browse CLI gives your agents reliable access to the web for advanced tasks. Read the full documentation below.
Browserbase tweet media
Claude@claudeai

New from Code with Claude Tokyo: scheduled deployments and environment variables in vaults are in public beta in Claude Managed Agents, and dynamic workflows in Claude Code are generally available. Agents now run on a schedule, use your tools securely, and take on bigger jobs.

English
6
5
57
14K
Claude
Claude@claudeai·
New from Code with Claude Tokyo: scheduled deployments and environment variables in vaults are in public beta in Claude Managed Agents, and dynamic workflows in Claude Code are generally available. Agents now run on a schedule, use your tools securely, and take on bigger jobs.
English
251
340
5K
597.7K
Browserbase retweetledi
Kyle Jeong
Kyle Jeong@kylejeong·
Claude Fable 5's computer use blows other foundation models out of the water. On our custom task set it scores 7.3% higher than 4.8 while also being more cost efficient than sonnet 4.5. Our hybrid agent built into Stagehand significantly outperformed the native CUA harness.
Kyle Jeong tweet media
Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.

English
2
7
26
4.4K

Keşfet

@Magicareai @PrimeIntellect @harvey @reductoai @yash_s_gupta @claudeai @elonmusk @BarackObama