A Note on Samples
These tools were built for internal AWS workflows and are not available for external demonstration. What I can share is how they worked, the problems they solved, and the measurable impact they had. The experience I gained building these systems has only deepened since—I continue to explore and build with new AI capabilities as they emerge.
Problem Solved
Documentation tickets often require repetitive analysis: understanding the request, locating relevant source files, determining the appropriate fix, and implementing changes. This manual process created bottlenecks.
How It Worked
I developed an agentic system that automated ticket analysis and resolution:
- Ticket parsing: Takes ticket URL as input, extracts requirements and context
- Codebase navigation: Automatically locates relevant XML source files in the documentation repository
- Action planning: Breaks down the ticket into discrete steps with clear acceptance criteria, balancing short-term fixes and longer-term impact
- Multiple output modes: Can generate diff-style changes, direct source XML updates, or flagged sections for human review
- Searchable flags: Inserts markers in output for easy location of changes requiring attention
Results
- Reduced routine simple ticket resolution time significantly
- Helped identify longer-term underlying documentation issues
- Standardized approach to common documentation fixes
- Freed up writer time for more complex, high-value work