# Agent reliability may matter more than model size

Markdown copy of https://realalpha.app/s/agent-reliability-may-matter-more-than-model-size/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Danila Shtan](https://realalpha.app/people/danila-shtan/) · Danila Shtan is CTO of Nebius.
- Host: [Jacob Effron](https://realalpha.app/people/jacob-effron/) · AI Investor, Redpoint Ventures · Growth investor in Abridge, Ramp and Physical Intelligence; ex-Flatiron Health.
- Show: Unsupervised Learning
- Episode: [The Window Before AWS Wakes Up: Nebius CTO on Racing the Hyperscalers](https://realalpha.app/v/qJkcjURcAe8/), Nov 2, 2026
- Moment: 57:53 to 1:00:38 of the episode (3 min), playing on https://realalpha.app/s/agent-reliability-may-matter-more-than-model-size/; the episode from there: https://realalpha.app/v/qJkcjURcAe8/?t=3473

## Quote

> “I think a lot of future AI adoption lies in how reliable your agentic scenarios are and how reliably you reach those outcomes.”
> — [Danila Shtan](https://realalpha.app/people/danila-shtan/) at [1:00:07](https://realalpha.app/v/qJkcjURcAe8/?t=3607) · Unsupervised Learning

## Takeaways

1. He treats larger, smarter models as a given.
2. Tools and harnesses can improve task success beyond model changes.
3. Long-running agents can consume CPU without constant LLM calls.

## About this segment

Danila Shtan sees more leverage in agent reliability than simply scaling models, with internal work on tools and task-specific harnesses. He expects outcome optimization to shape infrastructure demand.

From “The Window Before AWS Wakes Up: Nebius CTO on Racing the Hyperscalers”, Nov 2, 2026. [Watch the full episode](https://realalpha.app/v/qJkcjURcAe8/)

## Transcript

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

[57:57](https://realalpha.app/v/qJkcjURcAe8/?t=3477) Well, I stopped caring about the new models being larger or smarter. I just accepted that it's a given. I'm kind of trying to look out for new novel architectures and approaches, but I don't see any as of today. I hope somewhere deep down in a stealth lab, something new is cooking but for now i frankly don't see anything that like is a thing that i would be even like would place even a small bet on but i'm more and more interested in the whole outcome optimization part on the agent side right because like we are used to talking about models and size of models and families of models, et cetera, et cetera, et cetera.

[58:51](https://realalpha.app/v/qJkcjURcAe8/?t=3531) But now that we've shifted to this multi-turn, long-running agents that we are talking not about requests, but rather outcomes, companies are talking about bidding per outcome, right? I'm very interested in how that part will shape up. And we have like a small research group internally with the neighbors that's working on this problem, actually. is like, how do you increase the chances of getting to that outcome?

[59:18](https://realalpha.app/v/qJkcjURcAe8/?t=3558) Not by increasing the model or changing the model. That is, of course, part of the discussion. But I believe there is a lot of optimization in the part where you introduce more sophisticated or maybe more simplified tools. You introduce the harnesses that start to evolve according to a particular task. And this kind of gets us back to significant CPU consumption because a lot of modern AI workloads actually go back to becoming code.

[59:49](https://realalpha.app/v/qJkcjURcAe8/?t=3589) It's codified, it's very formal. You see quality gates, you see sophisticated tools, et cetera, et cetera, et cetera. And sometimes your agent works for mince and mince and mince. without even issuing a backend request to an LLM because the workloads start to sit on this part. And this is the part that really interests me because I think a lot of future AI adoption lies in how reliable your agentic scenarios are and how reliably you reach those outcomes.

[1:00:22](https://realalpha.app/v/qJkcjURcAe8/?t=3622) And I think the whole optimization loop outside the model is an important part of that. 100%. Well, this has been an awesome conversation. Really appreciate you coming on the show. And yeah, thanks so much for coming on. Thank you for having me.