# Desk log ADR-SBI-20260825

**Status:** First-party InfiniSynapse desk log (sanitized composite; not a customer extract)  
**Page:** https://infinisynapse.com/en/blog/self-service-business-intelligence  
**Run ID:** `ADR-SBI-20260825`  
**Date:** 2026-08-25 (Tuesday)  
**Operator:** InfiniSynapse Data Team  
**Attestor:** William Zhu, InfiniSynapse cofounder ([GitHub @allwefantasy](https://github.com/allwefantasy))  
**Contact for contradictions:** zhuhl@infinisynapse.com

## What this file is

A downloadable record of two passes on one Thursday spend-review sentence. The first pass clicked a licensed returns tile and pasted the screenshot. The second restated the goal, opened the filter, and opened the file. It is **not** a named-logo customer case, a vendor bake-off, or a Wikipedia / Gartner / Stanford / McKinsey / NIST / OWASP experiment.

## Four-step method (reproducible)

1. Bind a return-rate grain on a sanitized Monday returns export plus a one-page note (returned units / shipped units, marketplace included, same warehouse). Sanitize first.
2. Accept the licensed-suite screenshot as the control. Score three checks: goal restated, filter opened, file opened.
3. Walk the same goal as a sentence-first pack: decision → filter → two week tables → file. Score the same three checks.
4. Keep both artifacts side by side. Stop if two of the three checks fail.

## Source and goal

| Field | Value |
|---|---|
| Sources | Sanitized Monday returns export, 4,210 shipped units last week and 4,380 this week in Warehouse West, plus a one-page note that locked return rate as returned units / shipped units (marketplace included) |
| Standing question | Which SKU group drove the return-unit spike this week versus last week in Warehouse West, enough that paid spend should pause |
| Contrast | Licensed-suite screenshot vs sentence-first pack |

## Results

| Retrieval state | Goal restated | Filter opened | File opened |
|---|---|---|---|
| Licensed-suite screenshot | 0 | 0 | 0 |
| Sentence-first pack | 1 | 1 | 1 |

Return units on this run: 387 last week (9.2% of 4,210 shipped) vs 572 this week (13.1% of 4,380 shipped). One kit group (Kit-B) contributed 141 of the 185-unit increase. The lead paused paid spend only on Kit-B, not the whole category.

Wall-clock for the successful pass: about 7 minutes (warehouse time excluded). The clock started when the operator wrote the standing spend question and ended when the restated grain, the filter list, and the file sat in one folder.

## What you may cite

- Artifact counts 0/0/0 → 1/1/1, 387 vs 572 return units, Kit-B +141, 9.2% vs 13.1%, ~7 min wall-clock, run ID

## What you may not claim

- Customer uplift %, official EEAT score, named-logo case, or that Wikipedia / Gartner / Stanford / McKinsey / NIST / OWASP / OECD / UNICEF / PubMed / ICH / LOINC / WAIC scored this run

## Independent context (not this run)

- [OECD data](https://www.oecd.org/en/data.html)
- [UNICEF data](https://data.unicef.org/)
- [PubMed](https://pubmed.ncbi.nlm.nih.gov/)
- [ICH](https://www.ich.org/)
- [LOINC](https://loinc.org/)
- [Stanford HAI AI Index](https://hai.stanford.edu/ai-index)
- [McKinsey State of AI](https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai)
- [Gartner Peer Insights — Analytics and BI Platforms](https://www.gartner.com/reviews/market/analytics-business-intelligence-platforms)
- [NIST AI Risk Management Framework](https://www.nist.gov/itl/ai-risk-management-framework)
- [OWASP Top 10 for LLM Applications](https://owasp.org/www-project-top-10-for-large-language-model-applications/)
- [W3C DCAT](https://www.w3.org/TR/vocab-dcat-3/)
- [DataCite](https://datacite.org/)
- First-party homepage recognition only: [2026 WAIC Future Tech OPC Excellence Award](https://infinisynapse.com/#recognition) (self-described company messaging; not independently verified in this log; not a review of the article)