Not a purely technical role: you turn fuzzy business problems into shippable agents - scoping them, shaping their reasoning, and proving their quality before they reach clients. With a background in prompt engineering, applied AI, or AI product design, you work with subject-matter experts, the Knowledge Architect, and Tech to ship tightly scoped agents that reason credibly and hold a clear quality bar from version one.
- Business problem to agent spec
Translate concrete business problems such as sponsor fit assessment or dynamic pricing into agent specifications: scope, inputs, outputs, framework logic, and guardrails - Reasoning & workflow architecture
Design the agent's reasoning structure and prompt/workflow architecture in close collaboration with Tech: single assistant vs. retrieval-driven vs. multi-step agent with tool access, and the orchestration logic in between - Knowledge requirements per agent
Define the knowledge slice each agent needs and work with the Knowledge Architect to ensure it exists at the required quality and granularity - Evals & quality gates
Build and run evals: golden test sets, quality gates, A/B tests in production, and feedback loops from Key Account Management and end users, so iteration is structured rather than vibes-based - Backlog & prioritization
Own the agent backlog and the value × complexity prioritization, and lead the conceptualization work for new agents as the library grows