UX Design · AI Tool · Design Sprint · 2026

CAN-SIMPLAN

Accuracy isn't enough. A planner has to be able to stand up in a council meeting and explain why. CAN-SIMPLAN is the design that makes that possible. An AI-assisted zoning tool where every output is traceable, every decision is defensible, and the human stays accountable throughout.

Explore interactive prototype

Role

Sole UX designer. End-to-end interface: proposal intake, simulation output, rationale recording, audit trail. Selected as winning project among the cohort.

Context

Four-day cross-disciplinary sprint, four-person team.

Tools

Figma. Interactive prototype, end-to-end.

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

The Problem

Municipal planners don't need faster AI. They need AI they can defend.

Many tools promise efficiency: summaries, risk flags, recommendations. But when outputs arrive without clear reasoning, they introduce a new risk. In a governance context, a decision must be traceable because it must hold up under questioning.

The model might be accurate but accuracy isn't enough. I need to be able to stand up in a council meeting and explain why.

— Municipal planner, research insight

Design challenge: How might we design an AI planning tool where every output a planner acts on is something they can explain and stand behind?


Key Insight

The AI isn't the problem. The opacity is.

Early research conversations revealed a consistent pattern: the barrier to AI adoption wasn’t skepticism about model accuracy, it was the inability to explain any individual output to a colleague, a councillor, or a community member asking difficult questions.

The design problem wasn't speed. It was legibility, to keep a human hand visible at every step.

The original framing

How do we speed up the proposal review process with AI?

The reframe

How might we design AI-assisted decisions that a planner can clearly explain, trace, and defend?

CAN-SIMPLAN system overview: four transparent stages from intake to decision
System overview: Four transparent stages, each passing through a human checkpoint before the workflow can advance.

Product Strategy

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

CAN-SIMPLAN is designed around one principle: the AI surfaces analysis but the planner makes the call.

Every interface decision was tested against that constraint.

I owned the end-to-end interface, from login through audit trail, as the sole UX designer on a four-day multidisciplinary sprint team.

CAN-SIMPLAN proposal dashboard — queue, model confidence trend, and review velocity
The Proposal Dashboard: What needs attention before the planner opens a single case.
CAN-SIMPLAN proposal detail — domain scorecards, simulation flags, planner action panel
Proposal Detail: Domain scores, simulation flags, and planner actions in one scrollable workspace.

Design Decisions

Four patterns that make accountability tangible.

01

Blocking flags enforce engagement

When a concern is raised, the workflow pauses, and the planner must record a rationale before proceeding. This introduces friction by design because it turns a passive step into an explicit decision. The argument against was based on behavioural reality: optional fields get skipped, especially under time pressure, which is precisely when the rationale matters most. That friction was the point.

Tradeoff Planners who feel certain about a call still have to articulate why, even when it feels obvious. Obvious decisions are easy to defend. The tool is shaping habits around the ones that aren't.
02

Confidence appears before interpretation

Model confidence, version, and timestamp are visible at the top of each proposal. A planner asked to defend a decision needs to know what the system knew, and when. Surfacing that upfront is the difference between a traceable decision and an opaque one.

Tradeoff Uncertainty is made visible rather than implied.
03

Plain language over technical precision

Each simulation flag includes a plain-language explanation written for planners, not data scientists. The planner’s role is judgment. The interface’s role is translation.

Tradeoff Some nuance is reduced, but detailed information remains accessible one level deeper. The interface prioritizes clarity at the point of decision.
04

The audit trail stays in the workflow.

Every action is logged directly within the proposal view rather than hidden in an administrative panel.

Tradeoff This adds density, but keeps accountability tied to the moment of decision rather than separating it into a secondary layer.
View Figma designs
CAN-SIMPLAN transparency panel — scoring assumptions and data source attribution
Transparency Panel: Every scoring assumption and data source — visible, attributed, traceable.
CAN-SIMPLAN audit trail and planner decision panel
Audit Trail: A sequential, immutable log of every planner action alongside a decision panel requiring written rationale before submission.

Outcome

A decision-support tool that strengthens a planner’s ability to explain what they decide.

Eight-screen prototype covering the full proposal lifecycle, completed in four days, selected as winning project. The thesis held: in civic AI tools, legibility is a precondition for use, not an enhancement.

The project reinforced a consistent pattern: in civic contexts, adoption depends less on performance than on whether the system can be understood. When reasoning is visible, trust becomes possible.

Interactive prototype: proposal queue, detail view, flag override, and audit trail flows.

What I'd Do Differently

Two things I'd pressure-test before shipping.

Test the rationale-recording step at realistic volume. In a sprint prototype, mandatory rationale was evaluated against a single proposal. A planner reviewing twenty proposals in a week may experience it very differently, either as a meaningful pause or as rote overhead. I’d run a longitudinal study before committing mandatory checkpoints everywhere. The design likely needs tiered friction: mandatory for high-concern flags, optional for low.

Involve a planning legal team earlier. The audit trail was designed with legibility for planners in mind. Whether that format satisfies the evidentiary and procedural requirements for an actual appeal or council challenge is a different question, that requires legal review, not just UX testing. In a real development cycle, that input belongs in the design phase, not as a downstream compliance check.

Next Project

WorkMap: Mapping AI's impact in the workplace task-by-task