From Manifesto to Code: How argentic-mw Runs Its Agents

Thu, 23 Jul 2026 09:00:00 +0200

In the first post of this series, I laid out a definition and a position: a supervised agent is a scheduled worker that executes a deterministic plan, where the LLM steps in only at extension points where it is useful, and where everything else is explicit, traceable, replayable code. Four pillars followed, determinism, control, auditability and token efficiency, which I presented as properties verifiable on a trace rather than as slogans. In the second post, I proposed a six-criterion decision framework to compare this approach to full-LLM platforms and orchestration frameworks, and I concluded that for scheduled business pipelines with audit and bounded-cost requirements, the custom core remained the coherent answer, even at the price of a real boot cost.

Python on Mathias WOLFF

From Manifesto to Code: How argentic-mw Runs Its Agents