AI Agent Product Manager

The role

You will own the systems and operating performance of AI agents across provider, parent, government and internal workflows. You will find work agents can do, design how agents use tools and work with people, and improve their quality, reliability, speed and cost in production.

What you will do

• Map customer and internal workflows to find where an agent can complete a useful task or help a person do it faster.
• Define each agent's job, tool access, decision boundaries, escalation path and success measures.
• Partner with engineering, design and operations to prototype, launch and improve agent systems.
• Build evaluations and review real failures, customer feedback and operational data.
• Track quality, reliability, latency, cost, adoption and customer outcomes, and use them to prioritize improvements.
• Design clear human review and handoff experiences for cases an agent cannot or should not complete alone.
• Stay close to customers and frontline teams and own the feedback loop from discovery through production performance.

Required qualifications

• Shipped and improved software products or operational systems used by real people.
• Able to reason about agent behavior, APIs, data, evaluations and system tradeoffs with engineers, and willing to prototype hands-on.
• Uses evidence from users and production performance to make product decisions.
• Communicates clearly across engineering, customer-facing and operational teams.
• Comfortable working in ambiguity and taking ownership from problem discovery through results.
• Cares about child care providers, families and the people who serve them.

Before you apply

• A particular degree is not required.

About the company

Wonderschool helps child care providers start, operate and grow their businesses with software, coaching and support, and partners with governments to modernize public child care systems. It is a small, in-person team.