How do you build trust in a system like that? The flowchart style have the advantage that you can decide when you want a human to review/approve as well as ensuring actions that need to happen at certain conditions do happen.

Yeah, flowchart style does have that advantage since you can add in approvals and conditions. The tradeoff is you end up limited to simpler logical flows that are easier to verify.

Our take is that trust in agent systems has to be empirical. You start with manual testing and then layer on AI based simulations (we’re adding this in Rowboat soon) to test more scenarios at scale. Splitting work into multiple agents also makes it easier to isolate and test parts separately.