# Managing AI agents is just like managing people

> A tech CEO discovered that managers make better AI prompters than solo engineers because they understand how to communicate expectations clearly.
- Title: Managing AI agents is just like managing people | Shortify
- Summary: A tech CEO discovered that managers make better AI prompters than solo engineers because they understand how to communicate expectations clearly. Experience…
- Keywords: ivan burazin, daytona, ai agents, prompting, management skills, ai infrastructure, tech hiring, vedran jukic, goran draganic, new york, ai-generated code, business
- Source: Business Insider — https://businessinsider.com/ivan-burazin-daytona-ai-agents-prompting-managing-people-2026-9
- Author: Aditi Bharade
- Published: 2026-09-17T04:01:01.281+00:00
- Read time: 1 min
- Topics: ivan burazin, daytona, ai agents, prompting, management skills, ai infrastructure, tech hiring, vedran jukic, goran draganic, new york, ai-generated code, business
## Managers beat engineers at prompting
Ivan Burazin, CEO of AI firm Daytona, found that staff with people-management experience are much better at prompting AI agents than solo engineers, even if those engineers are technically skilled.

> We've found that people who manage people and understand how to communicate what they want, inputs versus outputs, they're much better at running agents.
## The solo engineer problem
Engineers without management experience expect agents to understand vague requests, then get frustrated when results don't match their unstated assumptions. They skip the step of explicitly defining inputs, outputs, and expected outcomes.

> And so they never think about how to communicate, 'This is what I want. This is how I expect you to do it, or what I think the outcome should be.'
## Daytona's no-code future
At Daytona, 16 engineers each manage about five AI agents, and no one writes code anymore. The company provides secure sandbox infrastructure for running AI agents and AI-generated code in isolated environments.
## Managers need technical chops too
Burazin rejects the idea of pure people managers. Managers without technical knowledge, whether from marketing or engineering, aren't useful. Everyone should get their hands dirty with actual work.
## Smaller teams, faster growth
Burazin keeps hiring very slow because each new hire adds complexity. AI agents let Daytona maintain smaller human teams with less internal communication overhead, allowing the company to stay fast and agile.

> Agents help with that because you can have smaller human teams, hence the communication is smaller, and you can continue to be fast.
## Tech's flattening reverses course
After years of layoffs at Meta, Amazon, and Google during the Great Flattening, tech leaders now juggle coding and product work alongside management. Burazin's approach reflects this new hybrid role.
## Key takeaway

Experience managing humans translates directly to managing AI agents. The key skill is learning to communicate inputs, outputs, and expectations explicitly rather than assuming the agent will understand your intent.