Every Monday it re-checks every item on our shelves, tells Lerris what newly went to sleep and what woke up, and keeps a liquidation shortlist ready — because AED 2.7M of stock turned out to be sitting unmoved.
Monday 08:30 digest: new sleepers, revivals, top 20 by value — every item linking straight to its ERP record. A liquidation shortlist (discount / bundle / scrap suggestions) is drafted on request.
First verified run found AED ~989K unmoved 6+ months. Then the data-pipe fix revealed the warehouse copy had been incomplete — the honest figure is AED 2,685,152 across 1,430 items, ~25% of on-hand value. The number nobody could see got bigger when we could finally see it.
After the weekend's data sync
Stock on hand × last transaction date per item
New sleepers and revivals vs last week
Buckets, deltas, top sleepers — all clickable
Liquidation ideas drafted; humans decide
For implementers and the technically curious. The full build sheet — verified queries, thresholds, and build notes — lives on the specs page.
| System | Role in this loop |
|---|---|
| NetSuite warehousePostgres on our server | Our nightly read-only copy of NetSuite (ERP) data — items, stock, transactions — refreshed by the ETL sync every morning. The loop queries this copy, never NetSuite itself. |
| Metabasebi.huxapps.com | The BI layer over the warehouse. The loop runs its SQL through Metabase's API, and every number in the digest links to a live, clickable Metabase list so you can drill into the exact records. |
| Postgres “loops” schemareporting database | A small dedicated schema where loops keep snapshots and history that need SQL (week-over-week diffs, mirrors for drill-down links). Scoped role; Metabase can read it for the clickable aggregate links. |
| Hermesagent runtime on our server | The scheduler that wakes the loop up. Each loop is a cron job under a Hermes profile; the planned bizops profile will host the business digests (IT loops run under vpsops). |
| Healthcheckshealthchecks.huxapps.com | The dead-man's switch. The loop pings it only after a clean run — if the loop dies or errors, the ping stops and Healthchecks raises the alarm independently. This is how 'never silent' is enforced by machinery, not promises. |
| Email renderer + gwsrender_email.py | All digests pass through one shared renderer: Huxberry-branded HTML, tables for repeated rows, a coral 'needs your response' box when the loop has questions, and an arrow link on every record. Sent from the loops mailbox via the Google Workspace CLI. |
| Loop chassisloop_common.py | Shared plumbing every loop reuses instead of reinventing: state files, run-over-run diffing, Metabase drill-down link building, quiet-on-green notify logic. |
| Model / brain | What it does here |
|---|---|
| None at run timedeterministic script | A normal cycle is a plain Python script — no AI tokens are spent unless a diagnosis or judgment step is actually needed. AI wrote the script; the script does the rounds. |
| GPT-5.5 via Codexthe bulk-work model | Wrote and maintains the mechanical parts — SQL, diffing, digest assembly. Effectively free on our existing subscription, so routine cycles cost almost nothing. |
| Claude Opusthe judgment model | Reviews alert wording, thresholds, and anything a human will read and act on. Post-Fable, Opus owns everything that ships. |
Weekly snapshot per item in the loops schema — that's what turns a static report into a watchdog: “newly crossed into dead” only exists because last week is remembered.
Monday email; every aggregate links to a live Metabase list and every item to its ERP record. Feed card (headline: dead-stock value; tiles: item count, % of stock, WoW delta) planned.
Read-only warehouse credential. Every digest carries a data-freshness stamp from DATA-0 and its honest-caveats footer.