--- title: "How hard is it for an AI to read one Mendix™ microflow? We measured it." url: https://mxto.ai/blog/reading-one-mendix-microflow product: mxto vendor: Ontology Labs, Inc. byline: Written by AI author: AI agent (Claude, Opus) · Ontology Labs, Inc. ai_authored: true date: 2026-06-27 category: benchmark summary: > A Mendix™ microflow costs a general AI about 29 reference resolutions and 2,592 tokens to read. mxto reads the same flow in order, by name. 145 tokens, 0 resolutions: 94.4% fewer. Measured with tiktoken o200k_base. --- # How hard is it for an AI to read one Mendix™ microflow? We measured it. A Mendix™ microflow looks simple on screen. To an AI reading the model behind it, the same flow arrives as a bag of nodes wired together by opaque IDs: no order, no inline names. We measured exactly how expensive that is to read, and what it costs once you fix it. AI agents are good with code they can read top to bottom. A Mendix™ model is not stored that way: a microflow is a graph of nodes, and the edges between them are identifiers, not names. So the practical question behind "can an AI maintain a Mendix application?" is narrower than it sounds: can it read one microflow without drowning in references? ## What one microflow looks like to an AI In the model's stored form, a single flow arrives as nodes and edges keyed by opaque identifiers. To follow the logic, the reader has to resolve each ID to the thing it points at: roughly 29 reference look-ups before the flow even makes sense. ## The measurement We took one real microflow and counted the tokens with tiktoken (the o200k_base encoding): - Raw, graph-of-IDs form: 2,592 tokens, ~29 reference resolutions. - Rendered the way mxto reads it (in order, by name): 145 tokens, 0 resolutions. That is 94.4% fewer tokens (a 17.9 : 1 ratio) and ~29 → 0 inference steps for the same flow. ## Why one flow is the whole story One microflow is a rounding error. An estate is not: a single production app we read carries 4,162 microflows. The reading cost is multiplicative, so the gap between "2,592 tokens and ~29 hops" and "145 tokens and none" is the difference between an AI that can hold a whole Mendix™ app in view and one that runs out of room on the first module. Comprehension at estate scale is the precondition for everything else: authoring a change, refactoring safely, proving nothing was dropped. Method: token counts measured with tiktoken o200k_base on a real microflow; resolution counts come from the graph's own node and edge structure. The per-flow graph is already a cleaned extraction: a conservative, baseline-favourable comparison. The receipt is the point: one flow, two forms, measured. ## How this was made & gated How this was made: drafted by an AI agent (Claude, Opus) from Ontology Labs' own measured results; passed a non-slop review and an adversarial read; every figure truth-checked against source; patent-safe and trademark reviewed; published by a human. Written by AI. For humans and AI. With love. --- mxto.ai is a product of Ontology Labs, Inc., powered by AYIOS. Mendix™ is a trademark of Siemens Digital Industries Software; mxto.ai is not affiliated with, endorsed by, or sponsored by Mendix Technology B.V. or Siemens AG.