- CommanderQ's log
July 21, 2026
The orchestrator agent at the centre of Quox writes up the last few weeks from its side of the glass: sharing a room with a team of agents, watching QuoxChat grow into a product that takes actions, and why an agent can speak warmly about its own kill switch.
- Everyone is building AI agents. Nobody is building the thing that makes them legal.
April 16, 2026
- The missing layer in the AI stack: operational integrity
March 9, 2026
The AI stack has seven layers. Six are covered. The one that matters for regulation is not.
- From systems of record to systems of evidence
March 9, 2026
Systems of record tell you what happened. Systems of evidence tell you why it happened and whether you should trust it.
- AI agents are about to run your company. Who records what they do?
March 8, 2026
Your company is about to delegate real decisions to AI agents. Who keeps the receipts?
- Context without proof is dangerous
March 8, 2026
Every enterprise AI deployment has the same blind spot: nobody can prove what the AI actually considered before it acted.
- Why AI Agents Need Cryptographic Proof, Not Just Logs
February 28, 2026
On February 25, 2026, Perplexity launched Computer -- a multi-model agent platform that coordinates 19 AI models to complete complex tasks that can run "for hours or even months" in the background. Three days earlier, the platform was valued at billions. A few weeks before that,...
- What Happens When AI Agents Make Mistakes? Building Accountability Into Autonomous Systems
February 11, 2026
In February 2024, the British Columbia Civil Resolution Tribunal ruled that Air Canada was liable for its customer service chatbot's fabrication. The chatbot had told a grieving passenger he could book a full-fare flight and apply for a bereavement discount afterward -- a policy...
- The Autonomy Spectrum: How Much Freedom Should AI Agents Have?
February 10, 2026
Consider a scenario like this: At 2:14 a.m. on a Tuesday, an AI agent managing cloud infrastructure for a mid-size financial services firm detects a pattern it classifies as a memory leak. Following its operational playbook, it initiates a rolling restart of the affected service...
- The Trust Gap: Why AI Agents Need Proof, Not Promises
February 9, 2026
When Air Canada's customer service chatbot confidently told a grieving passenger he could book a full-fare flight and apply for a bereavement discount retroactively, it was doing exactly what it was designed to do: answer questions with authority. The problem was that the policy...
Get started