Codex Mobile, Dispatch, and the single-thread AI
Two AI products from two different companies found the same interaction pattern independently. That usually means it's right.
So your team can get on with the proper work.
No IT department needed. No technical background required.
Let’s talk →If your business has grown but the way it runs hasn’t kept pace, that’s usually where I come in. Work tracked in spreadsheets, information buried in email chains, software that’s barely being used — I find where AI can take that load off and build the automation that does it. You get something working, not a report.
Two AI products from two different companies found the same interaction pattern independently. That usually means it's right.
Three frontier AI labs now have first-party integrations inside a standard Microsoft 365 tenant. The architectural implications for identity, data residency, and policy enforcement aren't being covered at the right depth.
I've been using Claude Cowork as a daily driver since the research preview. Scheduled tasks, skills, vault memory, n8n integrations baked in. It replaced a lot of the glue I used to build by hand. So when OpenAI relaunched Codex on April 16 as "Codex for almost everything," my first
Three weeks ago a research pipeline I run finished overnight. Clean exit. No errors, no timeouts, nothing in the logs that looked wrong. The next morning I found three new entries in the records database with scores, briefs, and supporting notes. Professional-looking output. Two of the three entries already existed.
The subfolder pattern works in Copilot Cowork, so the design question actually matters. How to structure SKILL.md as a dispatch router, where organisational content belongs, and why the growing community marketplaces are a risk, not a shortcut.
A week after my first Copilot Cowork custom skills post, Microsoft has quietly changed three of the behaviours I documented. The install flow, the Skills panel, and the skill format have all moved. None of it is in Microsoft Learn yet.