what the ops team sees
Customer view
Everything on the other pages is engineering. This is what a retailer's operations team actually opens once a deployment is live: a supplier report card, an honest accounting of what the automation saved, and the one screen the team edits directly to change what the system does.
Supplier scorecard
Every supplier gets a letter grade — A through F — rolled up from six buyer-side numbers: on-time-in-full rate, fill rate, ASN accuracy, exception rate, deduction validity, and chase responsiveness. Nothing on the card is assumed; every cell traces back to a purchase order, a receipt, an ASN, or a chase thread.
| Rank | Supplier | Grade | OTIF | Fill | ASN accuracy |
|---|---|---|---|---|---|
| 1 | SUP-021 | B | 75.0% | 98.4% | 75.0% |
| 2 | SUP-023 | C | 33.3% | 93.9% | 66.7% |
| 3 | SUP-022 | D | 66.7% | 99.2% | 33.3% |
A sample rollup from the synthetic corpus — three suppliers, ten POs. Grades are computed the same way every time from the same underlying data the approval workflow already touches, so the scorecard can never quietly drift from what the agent actually did.
Honest ROI
The easy number to report is every action the agent touched, priced at the manual time it would have taken. That number is wrong on purpose here: a wrongly flagged exception creates a human touch that would not otherwise exist, and a wrong auto-close creates rework. Both get charged against the benefit rather than counted toward it — a false positive costs touches-saved, it doesn't add to them.
| Weekly value | What it counts | |
|---|---|---|
| Naive credit | $111,015 | every agent-touched action, priced at manual time — the vendor-slide number |
| − false-positive credit, rework, nuisance flags | −$30,495 | the honesty cut: 27.5% of the naive number |
| Net touches saved | $80,520 | what's actually reportable |
Exception aging — the time a flagged item sits before resolution — falls from 5.7 to 2.2 days in the same run, a 61.7% reduction, computed from the same before/after fixtures. All figures are from the fully synthetic before/after model, not a real deployment — the mechanism is the point: the report is built so it cannot inflate itself.
Exception-spec board
The one screen the customer's own team owns. It's a single-file, offline board — no server, nothing to install — with three views: Edit (the decision rules, tolerances, exception paths, fallbacks, and which actions require a human, in plain rows and toggles), Spec (the same rules rendered as a readable policy document), and Validate & export (a live check plus the exported policy file). Whatever the team sets here is what the agent runs under — the export round-trips through the pack's real policy loader, so the board isn't a mockup of the config, it is the config.
Consoles
Retail-ops showcase
A walkthrough of the retail_ops pack — the ten tools, the case set, and the approval hard gate — as a self-contained page.
Eval dashboard
A case-level view across the replay-verified packs — retail_ops, process_mapping, browser_ops — with per-case transcripts.