Building the infrastructure behind better AI-powered products.
AI is changing how software gets designed, built, and shipped. But faster production does not automatically lead to better products.
Teams still need to make the right decisions, preserve customer and business context, translate intent into implementation, and validate what gets delivered.
I build AI-enabled product systems and practical tools that help connect those decisions across the product lifecycle.
My work brings together product strategy, UX research, design systems, structured documentation, AI-assisted engineering, and quality validation to create workflows that are repeatable, measurable, and built for real-world delivery.
The problem I'm solving
As AI accelerates product development, the distance between deciding what to build and delivering the right thing can become harder to manage.
Research gets separated from requirements. Design intent gets lost in implementation. AI agents produce output without sufficient context. Teams ship features without a clear, consistent way to evaluate whether the result meets the original intent.
More output is not the same as better outcomes.
The opportunity is to build systems that give people and AI the context, constraints, evidence, and feedback they need to make better decisions throughout delivery.
How I approach it
02 / Approach- 01
Structure the context.
Organize research, business rules, product requirements, design standards, and technical guidance so they remain useful throughout development.
- 02
Connect the workflow.
Create repeatable processes that bridge product strategy, design, and AI-assisted engineering rather than treating each as an isolated activity.
- 03
Make quality visible.
Build in validation, traceability, accessibility considerations, and feedback loops to help teams identify gaps before they become expensive downstream problems.
- 04
Keep human judgment in the process.
Use AI to accelerate analysis and execution while keeping product decisions, accountability, and quality standards explicit.
Design Sprint Intelligence
Connecting design intent to implementation evidence.
Design Sprint Intelligence is an open-source tool I created to help teams examine the relationship between design work and code changes.
In fast-moving product teams, design and engineering can move in parallel without a clear, shared view of what changed, what was implemented, and where further review may be needed.
Design Sprint Intelligence is designed to help make that handoff more visible.
It combines a local Git change collector with a report workflow and a Claude Code skill, with planned evidence collection across design and development sources. Its goal is to make design-to-code review more structured and traceable.
What it helps teams explore
- 01Which code changes occurred during a sprint or defined development window
- 02How implementation evidence can be organized for review
- 03Where design and engineering handoffs may need additional attention
- 04How to create a more repeatable review process instead of relying entirely on manual inspection
The larger direction
Design Sprint Intelligence is one example of a broader practice: designing the systems around AI-enabled product development, not just the interfaces those systems produce.
I am continuing to explore tools and workflows that help teams move from research and strategy to implementation, validation, and continuous improvement with greater clarity and control.
The objective isn't simply to build faster. It's to make faster product development more intentional, connected, and accountable.
Have a complex product challenge or an AI-enabled workflow worth improving?
Let's talk about what you're trying to solve.
Start a conversation