We love these tools but they were designed for testing, not for automation. They are too low-level to be used as they are by AI.
For example, the playwright MCP is very unreliable and inefficient to use. To mention a few issues, it does not correctly pierce through the different frames and does not handle the variety of edge cases that exist on the web. This means that it can't click on the button it needs to click on. Also, because it lacks control over the context design, it cannot optimize for contextual operations and your LLM trace gets polluted with incredible amount of useless tokens. This increases cost, task complexity for the LLM, and latency
On top of that, these tools rely on the accessibility tree, which is just not a viable approach for a huge number of websites
again (see other comment), you are not listening to users and asking questions, you are telling them they are wrong
You describe problems I don't have. I'm happy with Playwright and other scraping tools. Certainly not frustrated enough to pay to send my data to a 3rd party
have you tried any other AI browser automation tools? we would be curious to hear about your use cases because the use cases we have been working on with our customers involve scenarios where traditional playwright automations are not viable, e.g. they operate on net new websites and net new tasks for each execution
I'm unwilling to send my data to a 3rd party that is so new on the scene
Consider me a late adopter because I care about the security of my data. (and no, whatever you say about security will not change my mind, track record and broader industry penetration may)
Make it self-hostable, the conversation can change
This is a good point if you have a static IP address for pointing the URL, but sometimes this isn't the case (e.g. if you are pointing to a site with DDNS or a site with multiple IPs)
People have kept pressing me on the commercial potential behind my latest hobby. I took some time to dig and was surprised how the renaissance in self-hosting actually opens up a lot of new possibilities further accelerated by the latest AI tailwinds.
Curious to learn about others who are self-hosting. What's your use case?
Does AI have a place in validating product market fit?
I'm helping teach a workshop at Harvard Business School on using AI to prototype and test business models.
What are some "wow" use cases you've seen using AI to validate startup hypotheses or rapidly prototype an idea that can be picked up by a nontechnical MBA student in under an hour?
Condor Software | Software Engineer, Full Stack (Django, React) | Remote, San Diego, New York, or Boston | Full-time
Condor is building a world where finance accelerates human progress in medicine.
Our mission is to help biotech finance teams save time, money, and lives by bringing more cutting-edge therapies to market, faster and more affordably.
We started Condor because we realized that the life-saving treatments needed by our loved ones were held back by billions of dollars in complicated, time-consuming, and inefficient financial processes, which consistently delay clinical trial deployment and growth.
With more demand than we can currently service, we're looking for product leaning software engineers interested in tackling a big, hairy, complex business domain, value building "code that is easy to delete," and geek out about going "six levels down" (https://podcasts.apple.com/us/podcast/episode-1-six-levels-d...) and skilled people who are also "good humans" interested in our mission.
Condor Software | Engineering Manager, Technical Leads, Senior Software Engineers | US Remote, SF Bay Area, Boston, New York, San Diego | Full-Time | CondorSoftware.com
Interested in building software that makes a meaningful impact on end users and a big impact on medicine?
We have more customer demand and we can currently support, recently raised a large seed round from top institutions, biotech hedge funds, and Big 4 leaders, and are growing our team of “good humans” and former founders from startups, big tech, Big 4, and other experiences.
We're looking for more product-leaning software engineers interested in tackling a big, hairy, complex business domain, value building "code that is easy to delete," and geek out about going "six levels down."
Condor is building a world where finance accelerates human progress in medicine.
Our mission is to help biotech finance teams save time, money, and lives by bringing more cutting-edge therapies to market, faster and more affordably.
We started Condor because we realized that the life-saving treatments needed by our loved ones were held back by billions of dollars in complicated, time-consuming, and inefficient financial processes, which consistently delay clinical trial deployment and growth.
reply