BrowserBook
The Browser Automation IDE
224 followers
The Browser Automation IDE
224 followers
BrowserBook is an AI-powered IDE for building fast, reliable browser automations. It pairs a Jupyter-style notebook with a context-aware AI coding assistant and an inline browser, enabling developers to write, test, and debug automations all in one place. With built-in auth management, data extraction, screenshot tools, and API deployment, you can go from idea to production-ready automation in minutes, not hours.
BrowserBook
Hey Product Hunt! 👋 I’m Chris, co-founder of BrowserBook here with teammates Jorrie and Evan.
We’re excited to share BrowserBook, an AI-powered IDE for building reliable, deterministic browser automations. It combines a notebook-style interface, an inline browser, and a context-aware coding assistant to help developers write, run, and iterate on Playwright scripts faster with built-in tools for screenshots, data extraction, and managed auth.
Why we built this
Jorrie and I started a healthcare automation company last summer, where we spent lots of time building back-office workflows (think insurance followup, medical coding, etc.) with custom browser agents. During this time, we ran into four major issues with browser agents:
💰 They’re expensive - we burned through tokens with all the workflow context we needed to provide
🐢 They’re slow - all that context let to super high latency on each request
😬 They’re unreliable - even with detailed instructions and tools, agents still drifted on multi-step tasks
🐞 They’re impossible to debug - when they drifted, there was no clear root cause; we often resorted to trial-and-error to resolve issues.
We found ourselves giving our agents scripts to execute at each step of the workflow, and eventually came to the conclusion that scripting was just the better solution. We decided to put the agent at the coding step rather than the execution step, using LLMs to rapidly write scripts based on DOM context, and ultimately built BrowserBook as the tool we wished we had.
So what's included?
The core IDE experience is purpose-built for web automation; some of its features include:
🌐 A fully-interactive inline browser instance that you can run Playwright automations against with the click of a button
📒 A Jupyter-notebook-style interface, so you can just run parts of your automation instead of the whole thing every time
🤖 A context-aware coding assistant so you don’t have to go digging for selectors
🤝 Helper functions for common actions like taking screenshots, data extraction, and managed auth profiles supporting username/password and TOTP for authenticated workflows
When you’re done building, you can run your automation manually through the IDE or via API for use in external agents or apps!
Our initial use case was healthcare automation, but if you’re building automated tests, writing browser-based RPA workflows, web scraping, or have an agent that needs to perform deterministic actions on the web, give us a try - we’d love to hear what you think!
How do I use it?
You can download for Mac at our website: https://browserbook.com
Cheers,
Chris
@cschlaepfer This looks awesome! After starting with healthcare automation, what are some of the most unexpected ways you’ve seen people use Browserbook so far?
BrowserBook
@dnsbty Appreciate it! So far we've seen early users going after a few key use cases:
We're actually continuing to see a lot of interest in the healthcare automation space. This industry is particularly in need of automation solutions because a) APIs & interoperability in EHR and practice management software is really lacking, and b) the market is extremely fragmented, which means there aren't really any catch-all solutions
Startup teams building agents: we've seen a lot of startups building agents that need to interact with data that isn't publicly accessible via API, who up until now have been hacking together one-off solutions and doing things that don't scale particularly well.
Web scraping, which BrowserBook's data extraction and screenshot capabilities lend themselves well to
Maybe some of the more fun and surprising use cases, though, have come from one-off automations like scraping local library websites to check availability, or building a bot to book hard-to-get restaurant reservations in NYC. There's lots of little tasks out there that we think people would prefer to be automated, and we're hopeful BrowserBook can help!
BrowserBook
Hi Product Hunt, other co-founder of BrowserBook here! Chris has already explained some of the reasons why we built BrowserBook, so I'm going to share what makes us different from other web automation platforms and why you should give us a try.
The automation software we've seen falls roughly into two categories:
Software SDKs where you need to build it all yourself.
Full automation platforms that tout low or no code automations.
BrowserBook is the sweet spot between these two options.
Don’t know where to start with authentication, hosted browsers, data extraction, session recording, etc.? BrowserBook sets all this up for you with a simple interface that abstracts away the complicated parts so you can focus on writing scripts.
Nervous about using no code platforms to write your production workflows because it’s a startup and when they go out of business in three months all your carefully crafted prompts will be wasted effort? Use us instead! When we go out of business in three months, what you’ll be left with is a bunch of working playwright code.
We’re excited to see what you build!
Melder - AI for Excel
I'm constantly getting fun browser based ideas w/out any desire to rip off that implementation band aid. May even use this to solve some of my personal pains
BrowserBook
@phil_brewer Love it! We've had a lot of conversations with folks who have these sort of workflows they'd like to automate, but don't want to go through the painful implementation step. One of our main motivators is to lower that activation energy so developers can get automations off the ground easily.
Let us know if you want to chat about your use cases, and we'll reach out 😎
Melder - AI for Excel
Seems super helpful for building end-to-end tests and evals for webapp-based LLM products without having to rearchitect/reinstrument your whole app. Gonna give it a try and see if I can get a playwright automation going
BrowserBook
@ashwin_dharne Yes, writing e2e test against your prod environment is one of the things we think BrowserBook solves very well and we aim to add first class support for tests/test suites in the coming months! We want you to be able to have the fast iteration loop on writing the tests, then instantly deploy them and run them on e.g. Vercel deployment webhooks.
Our product roadmap is malleable with feedback from users, so if you have a use case in this vein we'd love to hear from you about what you'd like to see from BrowserBook!
Congratulations on the launch and I like the idea of being able to set up complex automations across any website. I enjoy using GumLoop but I sometimes feel like it's not as customizable as I would like it to be.
BrowserBook
@alexander_gifford Appreciate it Alexander! GumLoop is a great product, and one of our early iterations of BrowserBook was a similar block-based automation builder. Our motivation to shift to an IDE was:
Exactly as you described, we felt drag-and-drop interfaces didn't give us the level of control we wanted,
We wanted to prioritize the developer experience, and developers are often just as comfortable (if not more) working directly with code as they are with visual workflow tools, and
We felt code would be more durable in the long run - at the end of the day, scripts can always be exported in or out of BrowserBook, which just gives users more peace of mind that the logic behind their automations are safe.
If you give BrowserBook a shot, let us know, and feel free to reach out at any time!
Nice work boys. What's the deployment process like? Is there an API you can use to call automations you build (apologize if this is on the launch video). Use case I have: running a deep search on an address (usually real estate platforms). Currently do manually. Tried to automate with browser-use but it was pretty flaky and didn't have time to figure out the API
BrowserBook
@jack_considine1 Hey Jack, thanks for the question! Yes that's exactly right - the design here is that you use the IDE to build the automation for your use case. You can parameterize it - e.g. implement an input for address - then press the 'snapshot' button, which creates a snapshot of your automation at that moment in time.
From there, simply call the API (see examples from our trusty "API" button)! Right now, you have to query the API for results - e.g. to fetch any data you've extracted - but soon we'll implement webhooks to allow for an event based approach.
Happy to discuss in more detail, and talk through your use case. You can also find more info in our docs: https://www.browserbook.com/docs#api-based-execution
Such a great product with a unique approach. We've been working with BrowserBook, and they know the ins and outs of this space. If you need a way to do repeated browser automations, these guys have cracked it.
BrowserBook
@nimesh_chakravarthi Thanks, Nimesh! We're excited to build this product, we think there's an opportunity to make something that hits a sweet spot between no/low code platforms and having to deal with the sharp edges of building all of it yourself.
BrowserBook
@nimesh_chakravarthi Appreciate it Nimesh! Been really great working with you