Anticipate failure modes

For each severe model selection failure on the invoice-extraction service, define stop condition, safe state, owner, and lasting prevention. Rollback only works if prior prompts, indexes, and models remain available. “Send to a human” needs queue capacity and context—not just a button name.

Run one tabletop on the invoice-extraction service for model selection: inject a defect, verify detection, contain, recover, and keep the blameless trace.

After the tabletop, store the injected model selection defect for the invoice-extraction service as a regression fixture. If the same failure later reaches users silently, your detection story was aspirational. Detection without a fixture tends to rot for model selection.

Also pin one numeric memory from this model selection chapter: If model L hits 96% field-F1 at $0.12/1k docs and model H hits 97% at $0.55/1k, the +1 pt may lose unless errors are extremely costly. That number is not decoration; it is a template for how claims about model selection on the invoice-extraction service should look in design docs. Scoped specifically to model selection / invoice-extraction service / failure-modes.

People confuse model selection with neighboring buzzwords when debugging the invoice-extraction service. Before changing prompts, ask whether the broken stage was evidence gathering, the model selection judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried model selection and it failed”) that blocks the next team on the invoice-extraction service. Scoped specifically to model selection / invoice-extraction service / failure-modes.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to choosing a model rather than generic AI advice.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to choosing a model rather than generic AI advice.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to choosing a model rather than generic AI advice.