[joeroot]

Hi sarreph. We hope to delight by understanding what each individual likes. From out initial testing, we've found that our first article is a pretty good starting point for tech "people" when we use their Twitter markers to inform us. From there we get a lot better if the user offers us valuable data points - either by reading the article or even better replying to our suggestions with feedback.

We'd all become tried of algorithms claiming to know who you are. We wanted to take this back to first principles and try to understand what captivates people.

[sarreph]

That's an interesting initiative. However, aren't you, by definition, using an algorithm to track Twitter usage in order to tailor results?

[joeroot]

No. We go through a user's followers by hand; identify common influencers and interests; cross reference these against interesting content from a range of sources. We will eventually look for scalable aspects, however right now we're trying to figure out what works best on an individual level.

[sarreph]

Okay. Are you identifying common influencers and interests off the top of your head though, or is that computed somehow?

[joeroot]

Right now no. We use intuition to extract these. We're taking notes though!

[sarreph]

Good luck then in that case! :)