Is your AI team actually efficient? #ai #tech #programming

The speaker introduces the concept of a 'five-person strike team' as one valid model for AI-assisted work, specifically suited for missions where correctness is the primary concern. The framing acknowledges that both small and large team structures can be appropriate depending on the goal, but focuses here on the case for small, focused teams.

The structural advantage of the five-person model, according to the speaker, lies in its built-in review layer. Because the team is small and tightly coupled, every AI-generated output passes through at least one other person who has enough shared context to catch errors at the right level of abstraction. This is not just a quantity-of-reviewers argument, but a quality-of-context argument — reviewers must understand the work at the correct conceptual level to provide meaningful oversight.

The speaker extends this to agentic coding systems specifically, noting that designers of such systems operate above the code level but still benefit from a shared context layer that enables real error-catching. Finally, the speaker argues that five people can collectively cover the key disciplines — product, engineering, design, data, and domain expertise — not by each person wearing a single hat, but through the team collectively spanning those areas.