We emailed back and forth several times. CEO was on the thread, was aware of my concerns, chose not to do anything. The result of the back-and-forth was the proposal I shared in the post.
We (at PostHog) have a very unique implementation of Inkeep in our community forums[1], and it's been a lot of fun working on a custom solution with the Inkeep team.
Our ultimate goal was to make our experience explicitly not feel like you're talking to AI.
So rather than trying to intercept questions from being posted to our forums, we trigger Inkeep _after_ a question is posted. If we're able to find an answer with a high degree of confidence, our "AI user" (Max) will show an answer within about 30 seconds.
The OP can then provide feedback that we're using to train further answers.
If the answer is marked as helpful, we display the answer publicly (and disclaim it as an AI response)[2]. If the answer is marked as _unhelpful_, the answer only shows to the OP and we review the feedback to figure out how we can improve (ie: do our docs need to be improved so Inkeep has better source material?).
It's been fun getting creative with the Inkeep team on a solution that worked for our specific use case. I'm planning on rolling out Inkeep more broadly in other areas of our site as we verify that our highly confident answers are genuinely useful to our users.
IMO Inkeep has been the first AI solution that hasn't sucked – and that's high praise coming from me!
Same has happened here with our 2-year old, except we didn't get to it in time and have had the fire department show up on more than one occasion before we figured out what was happening.
There were also a handful of times we could hear a voice coming through the wife's phone where we narrowly avoided a few more visits.
This was all before we discovered how she actually calling 911. It's shocking to me Google didn't make more of a deal about this new "feature" when they rolled it out.
This definitely should have been opt-IN, not opt-out. Sure smells like a classic example of tech PMs making idealistic decisions that affect people in the real world without thinking through all of the consequences.
This is really well done. Paragraph view really helps to visualize it.
CSS Font Stack [1] used to be the place for this, but that site hasn't changed in decades.
The one piece missing for me is the percentage adoption by platform (like in the above referenced site). Regardless, this is still replacing CSS Font Stack for me.
The irony is that they were both created by people named Dan.
Came here to post this as well. I was going to start making a replacement for cssfontstack, so I'm glad to see this here. But also feel that the percentage adoption was a huge value to me, as it helped me prioritize fonts in my chosen stack to maximize consistency. I'd love to see stats that include popular mobile OS's as well.
Not any of your logos per se (rather, I haven't done a deep dive yet :P), but when I usually see a SaaS say that they partnered with so and so BigCorp, I just assume it's one developer trying out the product, as compared to a team using it for an extended duration (granted, everyone's doing that). So I just skip that testimonials section now.
