Rob Ragan

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

offensive securityAI agentspenetration testingred teamingapplication security

1661 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.

// ARTICLES BY ROB RAGAN

AI Agents

Web-Shepherd: Training Web Agents with Process Rewards Instead of Binary Success

By Rob Ragan ★ 56 Unknown May 8, 2026

AI Agents

GUARDIAN: Detecting When Your AI Agents Start Lying to Each Other

By Rob Ragan ★ 8 Unknown May 8, 2026

AI Agents

Process-Supervised RL for Agentic RAG: How ReasonRAG Achieves 18x Data Efficiency

By Rob Ragan ★ 14 Unknown May 8, 2026

AI Agents

Building a Unified AI Gateway: How IBM's ContextForge Federates MCP, REST, and Agent Protocols

By Rob Ragan ★ 3.8k Unknown May 8, 2026

AI Agents

AgentAuditor: The Invisible Research Project That Might Transform AI Agent Verification

By Rob Ragan ★ 4 Unknown May 8, 2026

Cybersecurity

RAPTOR: Building an Autonomous Security Agent from Claude Code and Adversarial Thinking

By Rob Ragan ★ 2.8k Unknown May 8, 2026

AI Dev Tools

Happy: Monitoring AI Coding Agents From Your Phone Without Leaking Your Code

By Rob Ragan ★ 21.4k Unknown May 8, 2026

LLM Engineering

TheAgentCompany: The First Real-World Benchmark That Makes AI Agents Look Bad

By Rob Ragan ★ 715 Unknown May 8, 2026

Developer Tools

Training Web Agents Through Test-Time Interaction: Inside TTI's Filtered BC Approach

By Rob Ragan ★ 75 Unknown May 8, 2026

Developer Tools

AGI SDK: Building Browser Agents Against Production-Quality Web Replicas

By Rob Ragan ★ 409 Unknown May 8, 2026

AI Agents

SPORT: Teaching Multimodal Agents to Self-Improve Without Human Labels

By Rob Ragan ★ 20 Unknown May 8, 2026

AI Agents

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

By Rob Ragan ★ 11 Unknown May 8, 2026