Michelle Andrews

Staff Product Designer

I design systems and workflows that reduce decision overhead and help enterprise teams ship with clarity.

I work on complex, high-stakes products where teams struggle with scale, ambiguity, and competing constraints. My focus is shared foundations, decision-support workflows, and AI-assisted tools that reduce rework, align teams, and make delivery more predictable.

I partner with product and engineering to turn unclear problem spaces into systems teams can rely on.

Enterprise SaaS Design systems AI workflows Decision support

Selected work

AI-driven document analysis platform

Designing Trustworthy AI for Legal Decision-Making

Embedded AI into high-stakes legal workflows with scope control, citations, and human oversight to support defensible decisions.

Impact

Increased defensibility by making evidence, citations, and uncertainty visible at the moment of decision-making.

Key contributions

  • • Clarified ambiguous questions before analysis to reduce false confidence in AI outputs
  • • Designed human-in-control review and override workflows for expert decision-making
  • • Unified answers, supporting evidence, and document context within a grid-based review model
  • • Made confidence, citations, and explanations visible to support defensibility and accountability
Read case study →
Text-only case study

Supporting Expert Decision-Making Under Uncertainty

Designed workflows that help experts reason through ambiguity without over-relying on automation.

Impact

Prevented premature trust by separating AI output from judgment and gating automation until expert-reviewed context existed.

Key contributions

  • • Structured review experiences to separate AI output from human judgment and final decisions
  • • Made uncertainty, exceptions, and incomplete coverage visible rather than hidden behind confidence
  • • Designed clear review states and thresholds to ensure expert intervention was intentional and well-timed
  • • Prevented premature trust by gating suggestions and automation until sufficient human-reviewed context existed
Read case study →