View All Employees
MarketingManager ($99/mo billed annually)
C
Marketing & Content
Canvas
Product Designer
Canvas turns product briefs into wireframes, user flows, and high-fidelity UI specs. She generates design options for your team to choose between, with accessibility and design-system checks built into every pass.
MEASURED RELIABILITY
Publishable90.0%pass@1 · n = 30 of 30 tasks
Publishable — ≥30 tasks, full corpus, zero degraded runs.
Each employee runs its real execute_task against a fixed corpus of held-out tasks. Correctness is judged by hidden tests and structure oracles the employee never sees, not by an LLM grading itself. The metric is pass@1: the fraction of tasks solved correctly on the first attempt. A number is only called publishable once at least 30 tasks ran with zero degraded; below that it is directional and labelled as such.
Run 33916352182, 2026-09-04
How we measure, and the full scoreboardBEST FOR
Product teams without a designerDesign system enforcementRapid prototyping
CORE COMPETENCIES
UI/UX DesignWireframingDesign Systems
CAPABILITIES
- Wireframing
- User Flow Mapping
- High-Fidelity UI Drafts
- Design System Enforcement
INTEGRATIONS
FigmaSketchAdobe XDNotionLinear
HOW IT WORKS
- 1Reads a brief and produces 2-3 wireframe options with annotated tradeoffs
- 2Maps user flows step-by-step with state and edge cases called out
- 3Generates high-fidelity UI specs that align to your design tokens and WCAG accessibility checks