Record the Audience Composition/Follower Study fix as completed for July

This was the long-standing unnamed "specific gap" flagged earlier — now
resolved and recorded in features_shipped, since it was never actually
written down as an outstanding item in the first place (tracked only in
conversation until now).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

monthly_report_notes.py

@@ -58,6 +58,14 @@ NOTES = {
             "finding was re-checked against the real numbers, not just re-labeled, and "
             "holds: Emotional posts average 21.8% Real Eng % vs. Rational's 8.1%, a wider "
             "gap than under raw numbers.",
+            "Audience Composition and Follower Study were raw pivot-table dumps with no "
+            "interpretation — a reader had to notice everything themselves. Both now lead "
+            "with real, dynamically-computed findings instead (Aug 31): Audience "
+            "Composition names the month's dominant sector, country concentration, and any "
+            "notable new followers; Follower Study leads with what changed that specific "
+            "month (new Notable Contacts, Account Clusters that grew, annotated inline) "
+            "ahead of the cumulative bimodal-seniority/shallow-network picture, rather than "
+            "repeating a near-identical all-time table every month with no monthly story.",
         ],
         "data_quality": [
             "File finder no longer crashes when a stray non-export file, a manual roster "