Hacker News new | ask | show | jobs
by XCSme 124 days ago
I think the goal, at least for now, is to simply let the AI do the work and humans should only monitor the end results, thus the dashboards.

I have the same debated working on my self-hosted analytics platform[0], where I am torn between implementing more features to build better dashboards and working on the AI features that simply generate insights and crunch numbers, so you won't even have to look at a dashboard.

That being said, people simply like seeing numbers go up...

[0]: https://www.uxwizz.com
1 comments
ATechGuy 124 days ago
Thanks for your insights!

QQ: does uxwizz also show AI agents visiting websites? have you seen traffic from AI agents?

link
XCSme 124 days ago
I currently do not automatically detect the agents themselves, and most of the bot traffic is ignored, but for the traffic that is not ignored it usually shows as a 0s session (so you can filter for all sessions that have a 0s replay, which are usually bots).

I am still torn whether I should actually track bots/AI traffic or simply drop it, maybe I will add a toggle in the setting, maybe it's at least interesting to see how much spam the website gets and coming from where.

link
XCSme 124 days ago
Oh, and as for the agents themselves browsing the website, if the agent uses an actual browser with JS enabled (like headless puppeteer), then you would actually be able to see how the agent browsed the website.
link
ATechGuy 124 days ago
Yes, but how can you tell if it was an agent with full browser?
link
XCSme 124 days ago
If they don't set the proper UserAgent, it's not trivial.

You could add some JS to test it and store it as a tag, maybe using something like: https://stackoverflow.com/a/78629469/407650

link
ATechGuy 124 days ago
That's a good start I'd say, but I agree with you that detection is not trivial. I wonder if there's enough value in distinguishing between AI agents (with full browser) and humans. What use cases would it enable?
link
XCSme 124 days ago
For the distinguishing part, it's hard to tell if it can be done anyway, as the agent browsers are still new and constantly changing, and it's up to them if they will correctly identify themselves or not (same as with crawler/bots, the main indication is still the source IP address).

There could be use cases, like tracking if your content was stolen/parsed by an AI, maybe future pay-per-request for LLMs, etc.

link