Jason Bedient
The AI Design Practice
Designing at the velocity of thought. I build AI products and use AI to build them.
Core Philosophy
I believe that AI is not just a tool for automation, but a new material for design. My practice is built on the idea that prompting is a design skill—it is the bridge between human intent and machine execution.
I advocate for an "AI-First" mindset, where we don't just add AI features to existing products, but we design products with AI at the core, acknowledging its probabilistic nature and designing for the "uncertainty states" that traditional software ignores.
AI-First Workflow
How I build at the speed of light.
The Stack
- Figma: Core visual design & prototyping.
- Claude: My primary AI partner for code generation and complex reasoning.
- V0 / Vercel: Rapid UI generation and deployment.
- Cursor: AI-powered IDE for turning designs into code.
- Notion & Perplexity: The brain of my workflow for organization and personal research.
Synthesis
My workflow is a continuous loop between high-fidelity visual design and functional code. By leveraging AI at every step, I can move from a rough sketch to a deployable React component in minutes rather than days.
Designing FOR AI
Designing for probabilistic outcomes.
Uncertainty States
In enterprise AI, "Success" and "Error" aren't enough. We must design for confidence scores, hallucinations, and "I don't know" states that maintain user trust.
Trust Calibration
Designing interfaces that help users understand why an AI made a certain recommendation, using explainability patterns and clear data transparency.
Human-in-the-Loop
Validating AI outputs through intuitive steering mechanisms, allowing users to correct, refine, and co-create with the model.
