AnchorScope
A discovery workspace for turning the WordPress plugin ecosystem into a focused security research queue.
Explore projectINDEPENDENT R&D LAB / IDEAS INTO SYSTEMS
We explore ideas.
We build what
holds.
An independent applied R&D lab building across AI, secure software, connected systems, and geospatial technology. Rooted in New Hampshire. Open to what comes next.
EXPLORE✦
RESEARCH✦
PROTOTYPE✦
TEST✦
BUILD
01 / CURRENT WORK
Promising ideas,
under active pressure.
We start with a real problem, build the smallest useful thing, and keep testing until the idea proves it deserves to become a system.
WAL-0.1
An AI-assisted WordPress plugin research system that connects code review, controlled testing, and human judgment.
Explore projectPresidential Slide Explorer
A satellite imagery workspace for exploring possible landscape change in New Hampshire’s Presidential Range.
Explore projectWAL Research
Independent WordPress and AI security research, from initial hypotheses to reproducible evidence and coordinated disclosure.
Explore projectIndependent WAL projects above. Explore selected professional engineering work in meteorological systems and rail telemetry.
02 / FIELD RESEARCH
We publish what
survives contact.
Our current field notes focus on AI and software security: clear, reproducible findings that builders and researchers can use.
R—01
AGENTIC AIFIELD NOTE
The confused deputy is back. This time, it has tools.
Why agentic systems collapse trust boundaries—and a practical framework for constraining tool use under hostile context.
Read field note →R—02MODEL EVALS
Evals that survive contact with the real world
Moving from static benchmark scores to security signals you can actually operate.
↗R—03PROMPT INJECTION
Designing for untrusted context
A threat model for retrieval systems that assumes every document is adversarial.
↗03 / APPLIED TRAINING
Turn the method
into a reflex.
Research becomes more valuable when the method travels. Our training concepts focus on helping teams build and test AI systems with adversarial judgment. Availability and scope are discussed directly with the lab.
Find your program ↗04 / HOW THE LAB WORKS
Curiosity starts it.
Evidence decides
what stays.
Explore widely
We follow consequential questions across security, AI, software, and whatever territory comes next.
Test honestly
Prototypes meet real constraints early. Evidence—not attachment—decides what advances.
Build usefully
The finish line is not a clever demo. It is a durable system that helps someone do meaningful work.
05 / START HERE
Bring us a difficult
question.
Interested in a project, holding a problem worth exploring, or working in adjacent territory? Tell us where the uncertainty lives.