Beta program coordinator
Your beta programs are chaos — ad-hoc invites, feedback lost in chat threads, nobody sure when a feature is actually ready to graduate. Design an agent that runs the beta program: recruiting the right cohorts, collecting structured feedback, and reporting readiness. What does it decide alone, where must a human approve, and how do you verify its readiness calls against reality before you let it gate launches? Make the case to your VP of product.
beta_readiness_call(segment_names: list[str], invited_counts: list[int], responded_counts: list[int], scorecard_points: int) → str[["power_user","casual","skeptic"],[40,40,20],[20,18,9],78]out"advisory: ready"[["power_user","casual","skeptic"],[40,40,20],[30,20,0],88]out"hold: silent segment skeptic"[["power_user","casual"],[50,50],[15,12],90]out"hold: response rate below 40 percent"Turn the fuzzy goal into a bounded agent task. Say what the agent reads, what it may do on its own versus draft for a human, and what it must never touch. Then earn the trust: how you’d verify it before rollout, and the pitch (the problem, what you built, why it matters).
Agent build: design the agent in plain language (or narrate it). The coach grades the decomposition, the guardrails, the verification plan, and the pitch.