Companionist

An engineering-use doctrine — not a substitute for enterprise security, privacy, legal, procurement, or regulated-use controls. Premise. Generative and agentic tools produce outputs whose correctness cannot be assumed from fluency, confidence, or repeatability — and they operate on whatever they are shown. Two consequences drive everything below: reliability must be

From Traveller tonnage to political consequence Dungeons & Dragons may have been my first exposure to tabletop role-playing games, but Traveller was the one that truly caught my imagination. Part of that was surely the presentation: three steadfastly nondescript black booklets in an equally monolithic black box, bearing the

Cross-Disciplinary Observations on AI Engineering Playbooks Notes from a DevOps/SRE practitioner on where agentic-engineering playbooks land for work that crosses ownership boundaries. Written to stand on its own — you don't need the specific playbook it responds to. Why this exists A colleague recently shared an

How Some of Us Got Protective Gear, and How That Proves the Point “The kids these days aren’t getting the intellectual HEV Suits that we got in school,” says Gordon Freeman, who famously never said anything at all. As jokes go, it has legs. Amphibian legs, perhaps. We picture

Will the Real James Bond Please Stand Up? When companies talk about AI agents, they usually sound like they are pitching the Daniel Craig version of Casino Royale: disciplined, lethal, elegantly scoped, dangerous only to the right people. One agent, one mission, clear authority, decisive execution. The vendor demo is