Melissa Denby
Generate an AI action
This project builds on the previous one — Orion, the SRE, has created actions to help resolve incidents, but sometimes the incident is more complex and he needs more help.
That's where AI comes in. I led the design team in creating a new user flow that allows AI to recommend and generate scripts for users. Because AI touches multiple areas of the product, I coordinated across teams to ensure the design fit into the broader strategy.
​
01
Gather information
The team was among the first at IBM Instana to use AI as part of the design workflow. Since there was a lot to consider, I took an AI Fundamentals for UX Designers course to better understand the challenges. Afterward, I joined an internal group of designers working in AI to keep learning.
02
Collaborate
I met with the team to whiteboard — asking questions and discussing ideas since this was updating an existing design. Together we worked through user flows and talked through concerns about introducing AI.
• When to trust AI vs. using a standard action
• Where AI needs to be accessible within the product
• Who needs access to AI features (RBAC)
• Future considerations as part of the broader strategy
03
User scenarios
I created user scenarios for two contexts — resolving an active incident, and creating a new action using AI. This was a highly collaborative effort, working with the content designer to educate users about AI, and the visual designer to ensure the design aligned with the Carbon Design System.
​
This was also part of a larger, cross-team transition to Carbon across the entire product — a significant effort that affected design and development teams alike. Coordinating across those teams meant ensuring patterns were consistent and the implementation was feasible for everyone involved.
04
Final designs
The final designs made AI visible and transparent — educating users about how AI was being used rather than hiding it. The result was a faster, more confident way for users to create actions and resolve incidents, and it set the standard for how AI would be introduced in other areas of the product.
