Real Alpha
Watch modeSubscribed

The TWIML AI Podcast · 3 min · Oct 15, 2026

Large mesh models relate multiple event streams

Zoe Weil says event models generalize over a single stream, while mesh models relate several streams and inform frontier rankers. The distinction clarifies how Sequen builds representations for downstream ranking.

ZW

Zoe Weil

Zoe Weil is co-founder and CEO of Sequen.

About this segment

Zoe Weil says event models generalize over a single stream, while mesh models relate several streams and inform frontier rankers. The distinction clarifies how Sequen builds representations for downstream ranking.

From “Optimizing AI Recommendations for Revenue with Sequen Founder Zoe Weil”, Oct 15, 2026. Watch the full episode

“Then we built what we called large mesh models, which were like large event models, but they're much more relationally focused.”
ZWZoe Weilat 45:42 · The TWIML AI Podcast45:42

Takeaways

  1. Event models generalize over streams of behavior.
  2. Mesh models look at relationships across multiple streams.
  3. Both contribute to specialized ranking models.

In this episode

Full episode
  1. 4:17Retail ranking should optimize purchases, not just relevance7:35
  2. 15:52Sequen personalizes a session without tracking user identity2:57
  3. 39:29Recursive updates compound ranking gains without rebuilding models4:45
  4. 32:12Ad and organic revenue can rise together3:51
  5. 27:11Recommendation ranking changes after a shopper commits2:22

  6. 44:16Large mesh models relate multiple event streams2:31

  7. 18:53Sequen chose Rust for low-latency feature serving2:49Up next
  8. 48:46Sequen is prioritizing ranking models over representations2:51

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 44:20

    Is that just an instance of one of your ranking models or is that a particular architecture or? It's one kind. It started as the thing that we did. Let me be very clear. that in itself was insanely difficult for us to do to create these models that were able to generalize to stream of events it sounds extremely intuitive and it is but getting it to generalize across customers and domains is insanely difficult like intuitively it makes a lot of sense but to get it to work in travel and media and retail at a different cross points different geographies without relying on any end user identity is really, really, really difficult to do.

  2. 45:09

    So that was one of the hardest things that we began to work on. What's the input? Is it a stream of events? It's just a stream of events. And each event kind of has a label and a value, for example? Yeah, so it would be like hover combinations, right? So it would be the query, the embedding for the query, and that query could either be literally the source item or it could be an actual query of words that a user searched for or whatever.

  3. 45:38

    That was the first, very, very first thing that we worked on and it was the black box model on top of which we built rankers. Then we built what we called large mesh models, which were like large event models, but they're much more relationally focused. So now I'm looking not only at streams, but i'm looking at many streams simultaneously and looking at the relationship between those streams together and trying to create generalized representations out of that right um then we started creating different classes of what we called frontier ranking models which were independent of large event models and large mesh models but which large mesh models and large event models contributed to, right? And so we built these collection of many, many, many now in the hundreds of thousands of frontier ranking models that we have that are proprietary, that are not

  4. 46:37

    published anywhere. A lot of them with very novel architectures. And that then became the first