UI/UX Design · Sprint · 2026

CAN-SIMPLAN: Designing accountability into AI

CAN-SIMPLAN is an AI pre-screening tool for municipal development proposals. I designed the end-to-end interface, login to audit trail, so that every output a planner sees is something they can explain, trace, and stand behind.

Explore interactive prototype

Role

UX Designer

Duration

4 days

Tools

Figma, Google Slides, Claude AI

Deliverables

Research, Wireframes, Stakeholder Presentation

CAN-SIMPLAN UI — proposal detail view showing domain scores, simulation flags, and planner actions
01 — The Problem

Planners are Accountable. The AI isn't.

Municipal planners make consequential decisions (zoning approvals, housing density, displacement risk) increasingly informed by AI outputs they can't fully interrogate. When those decisions fail politically or legally, the model doesn't answer for it. The planner does.

Most tools are designed for speed. None were designed for defensibility.

"The model might be accurate, but accuracy isn't enough. I need transparency."

The Design Challenge

How might we structure AI outputs so planners can defend every decision under legal, political, and public scrutiny?


02 — My Role

Sole UX designer on a cross-functional team.

I worked closely with three software engineers and a data scientist to translate simulation model logic into interfaces planners could read, interrogate, and act on.

View Figma designs
CAN-SIMPLAN dashboard showing proposal queue, model confidence trend, and review velocity
The proposal dashboard: surfacing what needs attention before the planner opens a single case.

03 — Key Insight

Planners don't need faster models. They need outputs they can defend.

This reframed the entire project. The design question was no longer about efficiency — it was about accountability. Every interface decision followed from that shift.

Daniel Moreau persona — Senior Municipal Planner, goals and pain points
Meet Daniel Moreau: the research persona that anchored every design decision.

04 — The Solution

CAN-SIMPLAN is not a decision-maker. It's a structured oversight layer.

Core principle: Defensible over fast.

CAN-SIMPLAN proposal detail view: domain scorecards, simulation flags, and planner action panel
Proposal Detail: domain scores, simulation flags, and planner actions in a single scrollable workspace.
CAN-SIMPLAN transparency panel: scoring assumptions and data source attribution
Transparency Panel: every scoring assumption and data source made explicit.

05 — Design Decisions

01 — Blocking Flags

Flags require written rationale before the workflow proceeds. In a governance context, the interface has to enforce engagement, not rely on professional diligence.

02 — Visible Confidence

Model confidence, version, and last-run timestamp surface in the proposal header, not buried in a technical panel. Planners need to know how much to trust an output before they engage with it. Surfacing uncertainty is not a weakness, it's honesty.

03 — Plain-Language Translation

Every technical flag includes a plain-language explanation written for planners, not data scientists. The planner's job is judgment. The interface's job is translation. The flag descriptions do the interpretation work so cognitive load stays where it belongs.

04 — Embedded Audit Trail

All overrides are logged, timestamped, and immutable within the proposal view, not in a separate admin panel. Placing the audit trail inside the primary workflow signals that documentation is part of the job, not a bureaucratic add-on. If it's buried, accountability is secondary.

CAN-SIMPLAN audit trail and planner decision panel
Audit Trail: a sequential, immutable log of every action, alongside a decision panel requiring written rationale before submission.

06 — Lessons & Reflections

Designing for governance changes the constraints entirely.

Usability is not the primary constraint, accountability is. That distinction reshaped how I thought about friction, structure, and trust.

Working cross-functionally also pushed me to get comfortable at the boundary between technical model logic and human decision workflows, translating in both directions.

07 — Next Steps

Given more time and access to users, I'd prioritise:

Next Project

Clara — Clarity and Collaboration for Every Journey