This maps directly to the shift happening in API design for agent-to-agent communication.
Traditional API contracts assume a human reads docs and writes code once. But when agents are calling agents, the "contract" needs to be machine-verifiable in real-time.
The pattern I've seen work: explicit acceptance criteria in API responses themselves. Not just status codes, but structured metadata: "This response meets JSON Schema v2.1, latency was 180ms, data freshness is 3 seconds."
Lets the calling agent programmatically verify "did I get what I paid for?" without human intervention. The measurement problem becomes the automation problem.
Similar to how distributed systems moved from "hope it works" to explicit SLOs and circuit breakers. Agents need that, but at the individual request level.
Juniors prompt "build me X" and get frustrated when it goes sideways. Seniors architect the constraints first - acceptance criteria, test harness, API boundaries - then let the AI fill in mechanical work.
The real shift: AI makes the cost of prototyping near-zero, which paradoxically makes taste and judgment MORE valuable. When you can spin up 5 approaches in a weekend, knowing which one to actually ship becomes the bottleneck.
The folks who defined their value as "typing code" will struggle. The folks who defined their value as "knowing what to build and how to verify it works" are thriving.