AI ExpertsDIRECTORY
Get listed
Gregor Zunic
VERIFIED TECHNICAL DOSSIERSources checked

Gregor Zunic

Co-Founder of Browser-Use

2 Verified ArtifactsSource Checked & Attributed
Back to Profile & ContactInquire with Gregor

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Gregor Zunic. Every entry undergoes editorial source verification.

#1
RESEARCH Checked Sep 22, 2026

Benchmarking Vision-Language Models on Live Web Interaction

Conducted empirical benchmarks assessing vision versus accessibility-tree DOM representation for autonomous agents, proving multimodal screenshot parsing reduces failure rates by 35% on checkout flows.

Model & Execution Context:Claude 3.5 Sonnet vision, WebVoyager benchmark dataset, automated browser sessions.
Scope & Limitations

High resolution screenshot ingestion increases token consumption significantly per navigation step.

View Enriched Study & Permalinks Primary Source
#2
IMPLEMENTATION Checked Sep 22, 2026

Browser-Use: Open-Source AI Agent Web Navigation Engine

Engineered Browser-Use, a Python library enabling LLMs to interact with web pages through coordinate clicking, typing, scrolling, and DOM element tree inspection using Playwright.

Model & Execution Context:GPT-4o vision, Claude 3.5 Sonnet, Playwright browser automation, JSON action schema.
Scope & Limitations

Dynamic single-page applications with obfuscated shadow DOMs can occasionally degrade element identification accuracy.

View Enriched Study & Permalinks Primary Source