All projects

CompleteUpdated Added

TicketForge

An engineering ticket intake console that turns a messy user report, a repository brief, and a team template into a structured ticket where every field carries a confidence grade.

About this project

One topic I have been hearing about more and more is how AI can be used productively in the software engineering process. I found that many of these discussions suffered from the fact that the peers I was talking to often had different visions of hypothetical situations involving AI. While one developer may see an AI-enhanced process going well as they envision it, another developer may see an AI-enhanced process going poorly as they envision it. This is not particularly helpful, because the specifics of how AI is enhancing the process may not be very well defined. Therefore, assessing the potential benefits and risks is a very difficult task.

Building on my experience creating similar AI-enhanced prototypes, I pursued this project to see what it might look like for an AI agent to automatically triage a developer's ticket. I wanted to show the potential value of enhancing existing tickets with guiding information and resources to accelerate the completion of that ticket. I believe this TicketForge project helps show at least one possible way for AI to assist in the ticket triaging process.

Screenshots

The same ticket after refinement: readiness at 88%, fields sourced from clarification answers, and a What Improved list. (view full size)
After answering the clarifying questions and refining, readiness climbs from 62% to 88%.
Templates screen listing Bug Report, Feature Request and Research Spike, with the Bug Report fields and per-field AI instructions open for editing. (view full size)
Ticket templates are editable, with per-field instructions and required toggles.

Resources