Always

Brief output must use plain operator language. Specifically: - **CVE** → "security hole" or "security vulnerability". Always name what the affected library/component is and what the practical risk is ("code execution if attacker hits URL X", "data leak if file Y is requested"). dompdf/swiper/chart.js mean nothing to Jim — say "the PDF generator", "the UI carousel library", "the chart library". - **CPS/CPI/CPM/CPC** → "commission per sale / install / impression / click" on first reference per item, then OK to abbreviate. - **T+1 / T+2** → "yesterday partial / two-day-ago final" - **DoD / WoW / MoM** → "day-over-day / week-over-week / month-over-month" on first use - **AOV** → "average order value (revenue ÷ orders)" - **ROI / ROAS / GP** → first-use unpack - Internal product codenames (4223, 5126, INVVM-1721) — keep the code but always add a parenthetical noun ("invoice INVVM-1721", "Cashiu attribution card 4223") Rule of thumb: if Jim can't act on the item without first decoding a term, the term is a bug. Translate or unpack.

Treat each Top 6 item as a story to investigate, not a data point to report. The brief's job is to dig: - When a number looks anomalous → pull the trailing distribution before claiming significance - When an event has a named counterparty → name the publishers / advertisers / deals affected - When a metric moves → propose 2-3 specific hypotheses with evidence from BQ / sheets / Basecamp, NOT generic "undiagnosed" - When relevant external context exists → flag it but do not invent (e.g. "Trip.com's Q1 investor report would tell us whether their HK/KR cut is platform-wide or just IA-specific — worth checking, but not in scope today") - Always ask "what would the team head actually do with this?" — if no answer, the item doesn't belong in Top 6 External-source augmentation is interesting but defer for now (Jim's note: "I'd rather not muddy the waters even more"). Capture as future capability.