Agent workflow tooling
I build extensions and workflow tools that make coding agents easier to control, automate, inspect, and continue across environments.
Currently shipping open-source pi tools, with work expanding toward Codex and Cursor plugin workflows.
Pi is where this is getting attention now. The broader direction is practical infrastructure for agent-powered software work across pi, Codex, Cursor, and other coding-agent workflows.
pi / codex
Codex-style goal tracking and continuation for long-running pi sessions.
pi / browser
Native pi tool bridge for agent-browser automation, page inspection, and browser artifacts.
ChatGPT web-oracle extension for pi with isolated browser auth, async jobs, and project-context archives.
pi / cursor
Cursor SDK provider extension for pi, adding Cursor models to pi's native model picker.
Short notes on agent workflows, tool building, demos, systems, and practical automation.
How I run performance reviews on Codex and Claude using their own session history.
A quick reference guide that provides reusable examples and best practices for prompting advanced LLMs in coding, troubleshooting, creative writing, and more.
A practical guide for students and professionals who have been wrongly accused of using AI to generate their original work. This article outlines evidence-based strategies to contest false AI detection flags, including documenting your process, comparing writing samples, citing detection limitations, and proposing reasonable resolutions.
A supporting research surface for practical security data and exploited-vulnerability inspection.
Research surface
Search and inspect the KEV catalog by CVE, vendor, product, timeline, and ransomware use.
Open KEV explorer →