Project “Broker OS” Case Study: Designing AI to Bridge the Experience Gap

The Problem:

As we scaled Broker OS, we uncovered a challenge: designing a product that supports two vastly different user types.

• New Brokers: Tech-forward, lean operations, hungry to grow
• Veteran Brokers: Larger teams, traditional workflows, hesitant to adopt new systems

Adding to this: depth vs. simplicity. Power users needed robust tools, but that depth threatened to overwhelm others. We needed to surface the right features at the right time – without burying users in menus or training.

Design challenge: Could we create a UX that flexes with the user’s experience level?

---

The Opportunity: Natural Language as Interface

To address discoverability and usability, I proposed an AI assistant that acted as both navigator and operator.

The assistant would:

1. Let users skip complex flows with simple commands
   (ex: “set an appointment with Jim Roberts on May 10th at 10:00 a.m. for 30 minutes“)
2. Contextually suggest next steps based on their role, location in the app, and behavior
3. Offer a lightweight layer on top of complex dashboards for instant insights

This wasn’t about AI for novelty – it was AI as a shortcut to value.

Example Screens:

---

How We Designed It

We mapped typical broker tasks and categorized them:

1. Task-based commands: schedule meetings, contact agents, take notes, set a reminder
2. Insight-based commands: “Who are my top performers?” “How close am I to my goals?” etc.
   

For each, I built both the manual workflow and its AI-triggered equivalent. We designed natural language inputs, system prompts, fallback logic, and paired them with friendly UI responses.

---

User Testing with Two Personas

I built a focused prototype and tested with 8 users split evenly between New and Veteran brokers.

The Impact from the Solution:

The AI assistant didn’t just accelerate workflows – it reduced friction, boosted confidence, and reframed the product as approachable.

It became more than a feature – it was a virtual office admin, bridging gaps between roles, experience levels, and tech comfort zones.

“I have no idea how I could possibly get to this information today without a lot of manual work.” – The most common open-ended response to the question “How would you accomplish this today?”

---