← All authors
Rob Ragan

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

Developer Tools

Breaking the 200-Session Ceiling: Reverse-Engineering Claude Code's Analytics

By Rob Ragan ★ 4 Python Apr 3, 2026
Developer Tools

Building an Adversarially Hardened AI Judge with Dual-LLM Privilege Separation

By Rob Ragan ★ 4 Python Apr 3, 2026
Developer Tools

Inside NYU's LLM CTF Leaderboard: How Researchers Benchmark AI Agents on Hacking Challenges

By Rob Ragan ★ 5 Shell Apr 3, 2026
Developer Tools

Verifiers: Building Reusable RL Environments for Language Model Training

By Rob Ragan ★ 5 Python Apr 3, 2026
Developer Tools

Cortex: A Compositional Framework for Recurrent Memory Stacks in PyTorch

By Rob Ragan ★ 6 Python Apr 3, 2026
Developer Tools

Privacy Backdoors: How Poisoned Pre-trained Models Weaponize Fine-Tuning Against Your Private Data

By Rob Ragan ★ 6 Python Apr 3, 2026
Developer Tools

Building LLM Evaluation Pipelines That Don't Burn Your API Budget

By Rob Ragan ★ 7 Python Apr 3, 2026
Developer Tools

Building AI-Powered Security Testing: Inside the Burpsuite MCP Server

By Rob Ragan ★ 7 JavaScript Apr 3, 2026
Developer Tools

Inside the Risk Bubble: How Princeton's Framework Measures AI Agent Capabilities in Offensive Security

By Rob Ragan ★ 8 Python Apr 3, 2026
Developer Tools

RF-Agent: Using Monte Carlo Tree Search to Generate Reward Functions for Reinforcement Learning

By Rob Ragan ★ 9 Jupyter Notebook Apr 3, 2026
Developer Tools

ReasonRAG: Teaching RAG Systems to Think Step-by-Step with Process Rewards

By Rob Ragan ★ 11 Python Apr 3, 2026
Developer Tools

NegMerge: Solving Machine Unlearning's Hyperparameter Problem Through Sign-Consensual Weight Merging

By Rob Ragan ★ 15 Python Apr 3, 2026