Peter Yang - AI Agents for Facility Operations

Hello!

AI Product DesignEnterprise SoftwareFacility OperationsCode Prototyping

Overview

Where I Started

Problem Statement

Facility teams had to monitor faults, high-risk work orders, assignments, costs, and potential over-investment across disconnected workflows.
Important signals competed for attention, leaving operators to manually determine what required action, why it mattered, and what to do next.

Context

The opportunity was not simply to add a chatbot. It was to create a coordinated set of agents that could turn complex building data into focused, role-relevant actions.
The design challenge was balancing automation with transparency, ensuring that users could understand and verify recommendations before acting on them.

What I Did

Responsibilities & Contributions

Defined the agent framework: Structured four operational domains into specialized agents with clear responsibilities, triggers, and user outcomes.
Designed an action-first experience: Organized recommendations around urgency, context, and next steps so users could move from signal to decision without navigating multiple tools.
Established trust and control patterns: Made recommendations understandable by surfacing supporting evidence, system reasoning, and opportunities for user review.
Prototyped in the production codebase: Used Claude Code to build the interactive experience directly in the product environment, testing design decisions against real components and technical constraints while creating a shared artifact for Product and Engineering alignment.

Impact

4 specialized agents

Covered diagnostics, risk management, work allocation, and investment oversight.

1 prioritized action view

Brought cross-workflow recommendations into a single weekly experience.

4 operational workflows

Connected complex signals to clear next steps through a shared interaction model.

1 reusable AI pattern

Established a foundation for adding future agents without creating separate experiences.

What I Learned

Key Insights

AI becomes valuable when it reduces decision effort, not when it produces more information. Recommendations needed to connect evidence, urgency, and next steps in one flow.
Trust came from visibility and control. Users were more willing to act when they could understand why an agent made a recommendation and confirm its scope.

Critical Constraints

Building data quality and confidence varied by source, requiring the interface to communicate uncertainty without overwhelming users.
High-impact operational decisions required human review, clear accountability, and a path to investigate the underlying evidence.