Factory AI

Design Reviews & UI Validation

During feature reviews, my primary goal was to ensure every design aligned with Tracxn's existing product ecosystem before moving into implementation. Instead of manually auditing multiple screens, I used Factory.ai to identify similar components, review interaction patterns, and verify whether existing UI elements could be reused. This helped uncover inconsistencies early, reduced duplicate components, and ensured new designs remained consistent with the design system. By entering stakeholder reviews with validated design decisions, the team was able to finalize UI changes more quickly while minimizing implementation risks and review cycles.

Quick Filters – Research to Product Fit

Quick Filters required balancing discoverability with workflow efficiency. I began by researching filtering patterns used across enterprise SaaS products to understand different approaches to placement and interaction. Once promising patterns were identified, I used Factory.ai to evaluate how those ideas could fit within Tracxn's existing architecture, reusable filter components, and interaction model. This allowed me to eliminate solutions that conflicted with the current product, adapt only the most relevant patterns, and move from exploration to implementation-ready designs much faster. The result was a solution that felt familiar to users while remaining practical for engineering to build.

Advanced Filters – Simplifying Complexity

The Advanced Filters experience involved managing a large number of filtering options without overwhelming users. Instead of focusing solely on visual design, I used Factory.ai to better understand the current filtering structure, relationships between filter groups, and opportunities to simplify the overall experience. This helped shape a more logical hierarchy, improve information organization, and create a filtering workflow that could easily accommodate future business requirements. By validating the structure early, I reduced unnecessary design iterations and delivered a solution that balanced usability with long-term scalability.

Column-Level Filtering – Workflow Optimization

Introducing filters directly into table headers was driven by the goal of reducing user effort during data analysis. I explored how enterprise products surface contextual actions within tables and then used Factory.ai to understand Tracxn's table architecture, reusable column components, and implementation constraints. This enabled me to evaluate different approaches for indicating active filters, ensuring users could immediately recognize filtered columns without adding unnecessary visual noise. The outcome was a streamlined interaction model that reduced clicks, improved workflow efficiency, and integrated naturally into existing table behaviors.