Case study · HumanFirst · 2024

HumanFirst: NLU disambiguation redesign

Evolved a mission critical enterprise workflow without breaking the patterns power users relied on.

Role: UX and Product Designer
Timeline: 2 weeks
Tools: Figma
Focus: Enterprise AI platform

HumanFirst NLU disambiguation interface redesign

Overview

HumanFirst needed to evolve its NLU platform toward generative capabilities while keeping enterprise clients productive in their existing disambiguation workflows. The goal was to add clarity and speed without forcing teams to relearn the core labeling patterns they depended on.

My role

I led the UX and product redesign, mapping the critical workflow, defining a cleaner information hierarchy, and pairing with engineering to ensure the new model fit existing enterprise constraints.

The challenge

The platform had to modernize its disambiguation experience for a new generation of AI tooling without disrupting enterprise workflows that were already deeply embedded in production.

The solution

I transformed a cluttered interface into a purpose built disambiguation workspace that clarifies context, improves hierarchy, and accelerates conflict resolution.

Clear indication of disambiguation mode.
Visual distinction between conflicting intents and utterances.
Redesigned conflict percentage visualization.
Focused layout for faster resolution.

Before and after comparison of the NLU disambiguation interface — Before and after of the disambiguation workspace. The new layout collapses the ambient interface chrome and surfaces conflict information where the user is already working.

Impact and results

The redesign shipped without disrupting any existing enterprise client.

Zero workflow disruption during rollout.
One hundred percent client migration success.
Preserved enterprise relationships.
Enabled major client platform adoption.
Simplified decision making for disambiguation.
Improved user confidence in conflict resolution.

Built with feedback. Built with care.What I take from this