The Future of AV
Scenario Authoring

Executive Summary

From Raw Code to a Visual GUI

I led the evolution of Foretellix's scenario authoring from raw code to a professional, visual GUI. As UX Lead, I turned a high-friction engineering process into an intuitive editor that allowed NVIDIA to scale its critical AV safety operations.

---

The Problem & Persona

A Technical Tax Blocking Safety Experts

NVIDIA is moving toward AI-driven stacks that require learning from millions of miles of driving data. Existing tools required deep technical expertise, creating a "technical barrier" that blocked safety experts , Scenario Designers and AV Developers , from creating necessary variations.

The goal: scale scenario creation from 60 real-world logs to 1,000+.

---

Market Research

Benchmarking Industry Standards

I conducted competitor research to benchmark industry standards and recurring UX patterns, identifying key opportunities to align with user expectations while differentiating our editor's experience.

Key takeaways:

• Combine map‑first, WYSIWYG editing with structured modeling where complexity demands it.
• Prefer a web‑based editor to maximize accessibility and sharing across teams.
• Design as part of a cloud loop: create → run at scale → analyze.
• Support standards‑based import/export.
• Treat simulation at scale as a first-class UX need , scenarios should be easy to parameterize, batch, and debug.

---

The Solution

The SDG Scenario Editor

I architected the editor around three functional pillars to empower non-technical users:

1. Ingestion & Cleaning , smoothing real-world noisy logs into stable simulations.
2. Scenario Composition , a visual interface for adding synthetic actors and defining paths via waypoints without writing code.
3. Graduated Fidelity Previews , instant "Fast Previews" for logic checks before escalating to high-compute simulations.

---

Feedback & Collaboration

Code-Bash Workshops & Continuous Loops

I translated NVIDIA interviews and "code-bash" workshops into clear mental models, maintaining a continuous feedback loop to ensure the experience is as intuitive, friendly, and usable as possible.

• Integrated Preview , moved previews directly into the editor using a dual-layer system for both instant playback and high-fidelity simulation.
• Execution Control , added granular configuration options, giving users precise manual control over individual simulation runs.
• Hierarchical Scalability , implemented a Scenario Tree architecture to help users navigate hundreds of actors and complex data without getting lost.

---

What's Next

From Foundation to Professional Mastery

With a high-speed, scriptless workflow established, I am evolving the tool into a professional-grade authoring environment focused on two strategic pillars:

• Hierarchical Scalability , a Scenario Tree architecture that mirrors the user's mental model, allowing navigation of hundreds of actors without getting lost in the data.
• AI-Augmented Authoring , a natural-language interface powered by Claude that lets users toggle between manual precision editing and an intuitive "speaking builder" experience, generating complex scenes via prompts while retaining granular control.

---

KPIs & Strategic Impact

Measurable Results

---

Reflection

The Real Job of a UX Lead

Leading this project taught me that a UX Lead's real job is Conceptual Unification. By bridging the gap between deep engineering rigor and designer-centric usability, we not only created a friendly interface but also unlocked NVIDIA's ability to scale its most critical safety operations.