Learning log · Coding practice · Original notes
I wrote code, then spent years in administration. When AI arrived I picked the technical side back up. Now I work on business analysis, MBSE and knowledge engineering — and write down the process as I go.
Turning a business problem into something you can actually analyse, rather than stopping at "something feels wrong".
Carrying system design in models instead of documents, so every change to a complex system has a traceable basis.
Turning experience into something searchable, reusable and legible to machines, instead of scattered across dozens of files.
Fourth post in the agent sandbox series. Move progress out of container memory onto a shared disk, then delete the working container on purpose — another one picks up at page 17. Including the honest part: this "automatic recovery" still needs a human to press something.
Third post in the agent sandbox series. A warm pool is the taxi rank at the airport: instant pickup, engines burning fuel while empty. Plus an honest account of the three things this dispatcher gets wrong — which are exactly what forces the next posts.
Second post in the agent sandbox series. One container per task sounds obvious, and it makes the user wait 45 to 90 seconds after they hit submit. Where those seconds actually go, and why the interface built for managing a cluster has no business on the path a user clicks.
If something here is wrong, unclear, or you would have done it differently, I would like to hear about it.