The Structure Around the Model Is the Product

By Rob Tyrie · Original source: June 16, 2026 · Essay · Standalone edition published October 25, 2026

This edition preserves the current Ironstone text developed from the original source linked below. The full piece also remains in the Field Notes & Essays collection.

An expensive frontier model can lose to a cheaper model wrapped in a better system.

That is not an argument for buying the cheapest model. It is an argument for noticing where dependable performance actually comes from. In serious work, the model is one component. The surrounding structure tells it what to observe, how to verify a fact, what evidence to preserve, when to stop and what a person must review.

A prompt can produce an impressive result once. An operating method must produce a reviewable result repeatedly. This is especially important in banking, insurance and legacy software, where an answer that is plausible but wrong can travel surprisingly far before somebody discovers it.

Model capability will continue to improve and become less expensive. The scarce assets will be good problem decomposition, authoritative context, evaluations, permissions, failure handling and people who recognize when the system has crossed from useful into unsafe.

Remove The Model Name From The Diagram

Take one proposed AI workflow and redraw it without the vendor or model name. Show the work instead:

• observe the live system;

• collect authoritative evidence;

• verify each important fact;

• preserve what has been confirmed;

• generate or recommend;

• obtain human review where consequence or uncertainty requires it;

• record the outcome.

Now test more than one model inside that structure. If the entire design collapses when the model changes, the organization has bought a dependency, not built a capability.

Original source

Put the thinking to work: agentic systems, Ironstone Methods and a conversation with Rob.