Home / Writing
Writing: AI / Systems
AI / Systems: Writing on artificial intelligence, decision-making and the engineering that turns models into useful, understandable systems.
Topics
Formats
Choose a topic and a format to narrow the archive.
Clear filters
When software needs a decision, not another paragraph
A billing message needs the right destination. TypeSafe’s Jev offers one way to turn an interpretation into a result that software can act on.
Read-
When an AI agent says “done”, what should we check?
A convincing completion message is only the beginning. Harness engineering is the work of helping an agent act, check the result and recover when needed.
-
The connection drops. The robot is still there.
A closed door cuts a robot off from the cloud. Following one inspection explains why small models, local decisions and a shared memory of the job matter.
-
Why I keep the planner classical
A quantum component can help with a calculation without taking over the decision. Keeping that distinction clear makes QANTIS easier to test and use.
-
Someone still has to go and look
A robot reports a possible wet floor. Following that finding to the maintenance team reveals the everyday problem behind the NODERIQ research programme.
Also available as an RSS feed.
Keep exploring
Another way into the work.