← All authors

Rob Ragan

Offensive security researcher and AI agent architect. Founder of Starlog.

offensive securityAI agentspenetration testingred teamingapplication security

1135 articles

Rob Ragan is an offensive security researcher and AI agent architect who has spent two decades breaking into systems and building tools to automate the process. At Starlog, he curates expert deep-dives on the open-source tools reshaping offensive security and AI agent development.

// ARTICLES BY ROB RAGAN

TheAgentCompany: The First Benchmark That Makes AI Agents Get a Real Job

By Rob Ragan ★ 640 Python Feb 16, 2026

TTI: Training Web Agents That Get Smarter By Learning From Their Own Mistakes

By Rob Ragan ★ 72 Python Feb 16, 2026

AGI SDK: Building a Benchmark Where AI Agents Actually Shop on Amazon (Sort Of)

By Rob Ragan ★ 431 Python Feb 16, 2026

SPORT-Agents: Teaching Multimodal AI to Learn from Its Own Mistakes

By Rob Ragan ★ 19 Python Feb 16, 2026

RF-Agent: Teaching Language Models to Design Reward Functions Through Tree Search

By Rob Ragan ★ 3 Jupyter Notebook Feb 16, 2026

SEC-bench: Automated Benchmarking for LLM Security Agents in Real-World Vulnerability Scenarios

By Rob Ragan ★ 55 Python Feb 16, 2026

Superpowers: Teaching AI Agents to Stop Cowboy Coding

By Rob Ragan ★ 52.3k Shell Feb 16, 2026

Stagehand: The Browser Automation Framework That Writes Its Own Selectors

By Rob Ragan ★ 21.1k TypeScript Feb 16, 2026

Steel Browser: The Missing Infrastructure Layer for AI Agent Automation

By Rob Ragan ★ 6.4k TypeScript Feb 16, 2026

HackingBuddyGPT: Teaching LLMs to Escalate Privileges in 50 Lines of Code

By Rob Ragan ★ 951 Python Feb 16, 2026

ARTEMIS: When AI Agents Hunt for Zero-Days While You Sleep

By Rob Ragan ★ 378 Rust Feb 16, 2026

LatentMAS: How Skipping Token Generation Makes Multi-Agent Systems 7× Faster

By Rob Ragan ★ 764 Python Feb 16, 2026