AI Tools & Research

Uptime dashboards do not tell you when a model starts drifting

We had good monitoring: pager alerts, latency graphs, error budgets, a dashboard someone actually lo…

Saying a human reviews it is not a human-oversight design

For a long time I answered the oversight question with a sentence: "a human reviews the output befor…

One Sentence Took My Coding Agent from 0/3 to 3/3 on Rejected Decisions

In a previous piece, I wrote that I had never checked the common claim that "handing an agent contex…

The logs I had described the server, not the system's decisions

The failure I kept hitting was strange: my logging was fine by ordinary standards. I had request tra…

[Boost]

Detecting Flaky Tests and Finding Their Root Causes with Strands Agents and Gemini …

How do you handle PII in AI systems?

What the interviewer is testing Whether you can apply PII controls across data collection, model p…

I kept shipping agents I had only tested on the happy path

The first test I write for a new agent is always the one it passes. A clean input, a well-formed too…

Detecting Flaky Tests and Finding Their Root Causes with Strands Agents and Gemini

A few years ago (three years at most), one of the biggest challenges QA Engineers faced was: how do …

HunterX Just Got Smarter. A Lot Smarter.

What if a security assessment engine could do more than discover vulnerabilities? What if it could q…

I built a topology map because I could not reason about agent failures from a config file

I have a bad habit of describing a multi-agent workflow in a config file and calling it done. The fi…

Introducing Quantum Frequency Modulator: Next-Token Prediction Without Attention

This single-file PWA that turns words into noise frequencies, collides them in a lattice, and drafts…

The limit you configured is not the limit it applies

An agent that pays for things needs a limit: a maximum price per call, a payee you expect, sometimes…