I build the thing,
then I ship it.

What happens, step by step

1. 1Build the panel. Loan-level servicing history becomes a monthly borrower panel. Calendar dates are the point: a timing feature from a source without real dates is refused at the feature layer rather than caught in review.
2. 2Score two questions, not one. L1 asks whether the account worsens over the next ninety days. L2 asks whether it recovers without contact. An agent reads those numbers at face value, so calibration is the gate rather than AUC.
3. 3Rank by money, not by risk. The allocator maximises expected recovered value per agent-minute: uplift over self-cure, weighted by exposure, under the capacity the team actually has. Probability never sorts the queue.
4. 4Coach inside the measured gap. 328 inter-turn gaps from a real call give a median of 479 ms and a p25 of 292 ms. The budget is 300 ms because that is what the distribution allows. A hint that misses the gap arrives after the moment it was for.
5. 5Log the decision, then resolve it. Every score, hint and override is written down with its experiment arm and its propensity. When the payment arrives or does not, the promise resolves and both lenses retrain on the result.

What happens, step by step

1. 1Read the photograph before trusting it. EXIF gives a provenance score. A perceptual hash is checked against the tenant's other assets, so the same part photographed twice and sent twice is recognised rather than counted twice.
2. 2Learn what good looks like. Enrolment is the tenant's own photographs of undamaged parts, per part family. There is no synthetic defect data anywhere in the system, because a generated defect teaches the model the generator.
3. 3Ask only whether the part is abnormal. Stage one is a memory bank of normal patch features scored by nearest-neighbour distance. It answers one question. It does not name the damage.
4. 4Force the answer onto a published standard. Stage two picks one code from the part family's ISO catalogue. It cannot invent a code, because an invented one is discarded rather than stored. The finding carries a clause number, so it traces back to the document.
5. 5Send the unsure ones to a person. Above the gate the record files itself. Below it the record waits in the review queue. The threshold is visible on the page rather than buried in a config file.
6. 6Record the mechanism, not only the surface. The same pit can come from fatigue at end of life or from a contaminant dent that started it early. The damage mode looks identical. The batch-level action does not, so attribution is a separate axis.
7. 7Close the loop. Every confirmed record becomes a model-and-human pair in the label export. The training data is the inspector's work, collected as a by-product of doing it.