ATRIUMsearch → argument graph
ClaimVideo · 47:32 — 49:52

AI harnesses will persist as a valuable layer because they are more composable than traditional apps, allow developers to own user relationships, and are easier for AI to orchestrate due to their Unix-based architecture.

Alex Atallah argues that harnesses (AI coding tools like Cursor) are more composable than traditional apps, more inspectable for developers, and Unix-based architecture makes them easier for AI to orchestrate—giving non-model-lab developers a way to own user relationships. ✦ AI generated

Alex Atallah · 20VC · 2026-08-10 · original ↗

starts at this moment · 47:32

Elicited by

Is the router absorbed into the agent framework before it it ever has the chance to be independent when you have the agent and the harness together?

The nice thing about the harnesses compared to the apps is that they're more composable. Like I can have a harness call another harness. I can have a harness spin up another harness in a sandbox in the cloud. ... it's much more reliable and and deterministic and sort of easy for users to grok with a harness because um the harnesses are Unix based. They all have and and the models are so well trained on on Unix, on bash commands ... Very very very very few unknown unknowns when you're composing around a harness. So I just think it just gives developers more flexibility um and flexibility that they can inspect.

verbatim transcript · starts at 47:32

Transcript · around this moment

47:32published like a good a good uh article about this where they showed that like, "Oh, we got like we got rid of stuff from the system prompt and suddenly fewer contradictions showed up later on with user prompts and the model performed better." Um and we and we're seeing like a lot of the harnesses right now are like deleting code in order to perform better with the latest frontier models. I I

47:55think means that harnesses are bad. I In fact, I think we'll see more harnesses come up in the future because it's a way of building a user experience on top of models. It's a way for developers who are not model labs to own a user relationship, and that is just going to be incredibly valuable for the economy to have that layer. >> I'm going to get killed for this. What's

48:19the difference between a harness and an app? Feels like it's word wank if I ever have to talk about harnesses and a harness. I'm like is that not an app? Like hello. >> Yeah. >> The nice thing about the harnesses compared to the apps is that they're more composable. Like I can have a harness call another harness. I can have a harness spin up another harness in a sandbox in the cloud.

48:42Um >> Is that not what APIs did for apps? >> Yes, but uh it's much more reliable and and deterministic and sort of easy for users to grok with a harness because um the harnesses are Unix based. They all have and and the models are so well trained on on Unix, on bash commands, whereas like you know, if I'm like telling a harness to go orchestrate an app in the cloud,

49:12it's going to be like oh boy, does this app like how do you log into this app? Is like do I need your password? Do I need a uh do I need to fire up a virtual browser? It's going to be pretty slow. I'll figure it out. Okay, I I like fired up a browser and like now I need your password and I'm going to like try to

49:30find the input where to put it in and I apparently there's probably an API in this app somewhere. I need to like look up the docs to figure it out. And okay, now I've got the API. There's so many like unknown unknowns when you're composing around an app. Very very very very few unknown unknowns when you're composing around a a So I just think it just gives developers more

49:52flexibility um and flexibility that they can inspect. Like API calls, you're just seeing a whole bunch of code flying around the screen. A harness, oh, I can like jump into the harness and like look at what's going on and talk in English about it. So, it's much more user-friendly. >> We've seen Meta and Muse really be a focus for Zuck. We've seen Alice wiring front and center much more. Were you

50:14impressed by what Meta delivered with Muse? >> They've been doing a good job, yeah. Um I mean like it takes a while to set up a whole new model lab from scratch and [clears throat] yeah, I'm sure a lot of like uh organizational debt to deal with. Um you know, like >> Do you think they will be a serious challenger? >> I do. I think they're I think they

Around this claim