Pulumi Copilot: A Conversational AI for Cloud Engineers
Simplifying DevOps Workflows with an AI-Powered Chat Interface
Company:
Pulumi
Role:
Product Designer
Tools:
Figma
Overview
AI is transforming how users interact with technology—and cloud infrastructure is no exception. In 2023, Pulumi launched Pulumi AI, a generative AI tool designed to help developers solve complex cloud problems using Infrastructure-as-Code. Building on that success, Pulumi introduced Pulumi Copilot, a conversational chat interface integrated into Pulumi Cloud. Copilot empowers users to manage infrastructure, troubleshoot issues, and gain insights using natural language—making cloud workflows faster and more accessible.
Team
Jonelle Boyd, Product Designer
Meagan Cojocar, Product Owner
Cleve Littlefield, Product Owner
Aaron Friel, AI Engineering Lead
Goals
Design a visually clean, intuitive interface for AI interactions
Maintain consistency with Pulumi Cloud’s existing UI design system
Ensure a seamless, fast user experience while interacting with AI features
Create distinct UI components that would cater specifically to a conversational interface
Enhance usability without disrupting the active dev cycle
Challenge
Copilot introduced a new UI paradigm to Pulumi Cloud—one that required rethinking traditional patterns while honoring existing constraints.
Key Challenges
No precedent in the design system: Conversational interfaces were entirely new within Pulumi’s product ecosystem.
Visual polish: The MVP had core functionality but lacked the refined visuals needed for production use.
Brand alignment vs. product differentiation: Copilot needed its own identity while still feeling native to Pulumi Cloud.
Ongoing dev cycles: Design updates had to be incremental and compatible with an active development pipeline.
These challenges created a space for thoughtful experimentation, focused iteration, and collaborative problem-solving.
My Approach
To design a scalable, user-friendly conversational interface, I followed a focused and iterative process:
Define Use Cases & Functionality
Collaborated with PMs and engineers to understand the technical capabilities and prioritize key user actions—such as asking deployment questions, getting IaC recommendations, and receiving system insights.Explore Patterns & Constraints
Audited popular conversational UI patterns (e.g. Slack, ChatGPT) to inform design direction, while mapping feasibility within Pulumi’s codebase and design system.Design & Prototype
Created component-level mockups and conversation flow prototypes to test layout, visual hierarchy, and accessibility. Introduced new elements like message bubbles, system responses, and hover interactions tailored for developers.Iterate with Dev & QA
Worked closely with engineering to implement designs iteratively—ensuring performance, responsiveness, and usability across browsers and devices.
Research & Insights
To better understand effective conversational AI experiences, I analyzed products such as ChatGPT and Slack, focusing on how they balanced functionality with usability. I examined conversation flow, response timing, message formatting, and interaction patterns to identify design principles that would create a natural, developer-friendly experience. I also referenced Pulumi's existing design language to ensure the AI interface felt like a seamless extension of the platform rather than a standalone feature.
Key Insights
Conversational interfaces should prioritize clarity and simplicity, allowing users to focus on the interaction rather than the interface.
Progressive disclosure helps present complex information without overwhelming users.
Thoughtful pacing and feedback create a more natural conversational experience and improve user confidence.
Consistent typography, spacing, and color reinforce trust and make AI features feel integrated with the existing product.
Familiar interaction patterns from tools like ChatGPT and Slack reduce the learning curve and encourage adoption.
Solution
Building on the validated concepts, I designed the final Copilot experience as an integrated AI assistant within the Pulumi Cloud dashboard. The interface focused on clear conversations, structured code formatting, contextual guidance, suggested prompts, and feedback interactions to support developer workflows. I designed both light and dark themes to ensure a consistent, accessible experience across environments and explored multiple branding concepts before selecting the AI Sparkle (Version 2) logo, which best aligned with Pulumi's visual identity. The final solution established a scalable foundation for future AI capabilities while remaining consistent with Pulumi's existing design system.
Integrated Copilot directly into the Pulumi Cloud dashboard.
Designed complete light and dark theme experiences. (Use the View Final Designs button above to explore the complete designs and annotations.)
Refined chat interactions, code blocks, prompts, and feedback patterns.
Explored multiple logo concepts before selecting the final AI Sparkle design.
Impact/Outcome
The Copilot redesign established a strong foundation for conversational AI within the Pulumi platform, making AI feel like a natural extension of the existing product experience. By introducing familiar interaction patterns within Pulumi's design system, the solution improved usability, encouraged early adoption, and created a scalable framework for future AI capabilities. The project also strengthened my experience designing conversational interfaces within an established product ecosystem, balancing innovation with consistency to deliver an experience that felt intuitive for developers.
Key Results & Metrics
30% increase in Copilot usage within the first four weeks of launch, indicating strong initial adoption.
25% reduction in time-to-resolution for common infrastructure issues through AI-assisted guidance.
Zero critical usability issues reported during QA testing after implementation of the new UI components.
15% increase in daily active users interacting with Pulumi Cloud's AI features.