Pomerleau
Overview
Pomerleau set out to modernize cost estimation by integrating predictive AI into a process traditionally driven by manual analysis and tight project timelines. I shaped the UX foundation for an early MVP that helped estimators interpret evolving machine learning outputs with more clarity and confidence, supporting teams as the models matured.
Challenge Context
The product needed to support teams working with inconsistent data, evolving AI outputs and varied estimation workflows, all while maintaining trust. During this period, Pomerleau was building aXLab, its innovation laboratory within Factry. I joined early discovery sessions with estimators and engineers, which helped clarify user needs, surface friction points and identify where AI could genuinely improve accuracy and reduce manual effort. The UX had to turn these insights into a clear and dependable experience teams could trust.
Design Approach
I collaborated with estimators to understand how they navigate cost analysis and where AI could create real value. These discussions revealed friction points and decision moments that required clarity. I mapped the estimation workflow, designed simplified layouts and created interaction patterns that surfaced predictions responsibly while keeping the process easy to trust. Close collaboration with engineers ensured the UX aligned with model limitations and operational realities.
Deliverables
I delivered workflow maps, behavioural insights and simplified layouts that made AI generated predictions easier to interpret, along with early design system components to support consistency and future scaling.
Outcomes
The UX provided a strong foundation for ongoing AI improvements and aligned with Pomerleau’s broader innovation efforts in collaboration with Scale AI.
Key Learnings
This project strengthened my ability to design clear, trustworthy experiences around emerging AI models and to help teams adopt new technology with confidence.
Photo and Video Credit
Pomerleau