Increasing AI adoption across Rocket
Role
Senior Product Designer
TIMELINE
Jan 2026 to May 2026
Enabling team members to build their own agents
Scope & Contribution
As the Senior Product Designer, I led the end-to-end redesign of Rocket's internal agent builder (Catalyst) over four months. Working closely with research, product, and engineering, I focused on simplifying agent creation to make the platform approachable for every Rocket team member.
Problem
Catalyst was designed to help anyone at Rocket create AI agents to automate their work. But it was so complex that most employees never adopted it, and it ended up being used almost exclusively by developers.
"I don't know what type of agent I can create or what I want to automate. I have no idea where to start."
Rocket Team Member
Creating an agent to help create agents
Our research showed that most team members didn’t know how to build an agent. Instead of expecting users to learn a complex process, we designed an AI-powered chat experience that guided them through creation step by step.
Showing what agents can do
To help users overcome the uncertainty of starting from scratch, we created a community agent library. By showing real examples, team members could use existing solutions and find inspiration for building their own agent.
"I want to be able to see what people on my team are building to see if I can steal their agents or get ideas."
Rocket Team Member
Building confidence before launching
We redesigned the testing experience to make it easier for anyone to validate their agents before launching. AI provides recommendations on what to test, while users could run multiple tests and quickly review results in one place to ensure their agents are working as expected.
k
hours saved
m+
task automated
agents in first 60 days
x
more users
More teams building with AI
The changes we made had a tangible impact. Agents are now being built by team members across the organization, enabling more teams to automate everyday tasks and save thousands of hours each week.
"Having a guide to walk me through all the steps of building my agent is a game changer. I'm going to save several hours a week."
Rocket Team Member
Increasing AI adoption across Rocket
Role
Senior Product Designer
TIMELINE
Jan 2026 to May 2026
Enabling team members to build their own agents
Scope & Contribution
As the Senior Product Designer, I led the end-to-end redesign of Rocket's internal agent builder (Catalyst) over four months. Working closely with research, product, and engineering, I focused on simplifying agent creation to make the platform approachable for every Rocket team member.
Problem
Catalyst was designed to help anyone at Rocket create AI agents to automate their work. But it was so complex that most employees never adopted it, and it ended up being used almost exclusively by developers.
"I don't know what type of agent I can create or what I want to automate. I have no idea where to start."
Rocket Team Member
Creating an agent to help create agents
Our research showed that most team members didn’t know how to build an agent. Instead of expecting users to learn a complex process, we designed an AI-powered chat experience that guided them through creation step by step.
Showing what agents can do
To help users overcome the uncertainty of starting from scratch, we created a community agent library. By showing real examples, team members could use existing solutions and find inspiration for building their own agent.
"I want to be able to see what people on my team are building to see if I can steal their agents or get ideas."
Rocket Team Member
Building confidence before launching
We redesigned the testing experience to make it easier for anyone to validate their agents before launching. AI provides recommendations on what to test, while users could run multiple tests and quickly review results in one place to ensure their agents are working as expected.
k
hours saved
m+
task automated
agents in first 60 days
x
more users
More teams building with AI
The changes we made had a tangible impact. Agents are now being built by team members across the organization, enabling more teams to automate everyday tasks and save thousands of hours each week.
"Having a guide to walk me through all the steps of building my agent is a game changer. I'm going to save several hours a week."
Rocket Team Member
Increasing AI adoption across Rocket
Role
Senior Product Designer
TIMELINE
Jan 2026 to May 2026
Enabling team members to build their own agents
Scope & Contribution
As the Senior Product Designer, I led the end-to-end redesign of Rocket's internal agent builder (Catalyst) over four months. Working closely with research, product, and engineering, I focused on simplifying agent creation to make the platform approachable for every Rocket team member.
Problem
Catalyst was designed to help anyone at Rocket create AI agents to automate their work. But it was so complex that most employees never adopted it, and it ended up being used almost exclusively by developers.
"I don't know what type of agent I can create or what I want to automate. I have no idea where to start."
Rocket Team Member
Creating an agent to help create agents
Our research showed that most team members didn’t know how to build an agent. Instead of expecting users to learn a complex process, we designed an AI-powered chat experience that guided them through creation step by step.
Showing what agents can do
To help users overcome the uncertainty of starting from scratch, we created a community agent library. By showing real examples, team members could use existing solutions and find inspiration for building their own agent.
"I want to be able to see what people on my team are building to see if I can steal their agents or get ideas."
Rocket Team Member
Building confidence before launching
We redesigned the testing experience to make it easier for anyone to validate their agents before launching. AI provides recommendations on what to test, while users could run multiple tests and quickly review results in one place to ensure their agents are working as expected.
k
hours saved
m+
task automated
agents in first 60 days
x
more users
More teams building with AI
The changes we made had a tangible impact. Agents are now being built by team members across the organization, enabling more teams to automate everyday tasks and save thousands of hours each week.
"Having a guide to walk me through all the steps of building my agent is a game changer. I'm going to save several hours a week."
Rocket Team Member
Increasing AI adoption across Rocket
Role
Senior Product Designer
TIMELINE
Jan 2026 to May 2026
Enabling team members to build their own agents
Scope & Contribution
As the Senior Product Designer, I led the end-to-end redesign of Rocket's internal agent builder (Catalyst) over four months. Working closely with research, product, and engineering, I focused on simplifying agent creation to make the platform approachable for every Rocket team member.
Problem
Catalyst was designed to help anyone at Rocket create AI agents to automate their work. But it was so complex that most employees never adopted it, and it ended up being used almost exclusively by developers.
"I don't know what type of agent I can create or what I want to automate. I have no idea where to start."
Rocket Team Member
Creating an agent to help create agents
Our research showed that most team members didn’t know how to build an agent. Instead of expecting users to learn a complex process, we designed an AI-powered chat experience that guided them through creation step by step.
Showing what agents can do
To help users overcome the uncertainty of starting from scratch, we created a community agent library. By showing real examples, team members could use existing solutions and find inspiration for building their own agent.
"I want to be able to see what people on my team are building to see if I can steal their agents or get ideas."
Rocket Team Member
Building confidence before launching
We redesigned the testing experience to make it easier for anyone to validate their agents before launching. AI provides recommendations on what to test, while users could run multiple tests and quickly review results in one place to ensure their agents are working as expected.
k
hours saved
m+
task automated
agents in first 60 days
x
more users
More teams building with AI
The changes we made had a tangible impact. Agents are now being built by team members across the organization, enabling more teams to automate everyday tasks and save thousands of hours each week.
"Having a guide to walk me through all the steps of building my agent is a game changer. I'm going to save several hours a week."
Rocket Team Member