diff --git a/scripts/build_release.py b/scripts/build_release.py
index 8b68e99..f3e231f 100755
--- a/scripts/build_release.py
+++ b/scripts/build_release.py
@@ -229,6 +229,7 @@ def main() -> int:
             "- Post-load readiness: the app offers AI only once the pinned model is actually loaded, so a reachable-but-unloaded worker falls back to manual logging in one tap instead of failing after the upload (issue #15)\n"
             "- Target-GPU benchmark: scripts/record_worker_benchmark.mjs records cold start, warm latency, and VRAM on the target GPU and refuses to write a receipt it did not measure; no GPU measurement is bundled with this release\n"
             "- Explainable pattern summaries (issue #34): the home insight card reports confirmed-log counts and form groupings per window, every line names the exact confirmed records behind it, following a citation opens those records, and a window below the minimum says it is too sparse instead of describing a trend; no line explains a cause, rules on food, or offers a health verdict\n"
+            "- Grounded chat citations (issue #37): an answer that states a count, a date, or a visible form cites the confirmed records behind it, following a citation opens exactly that record, questions the journal cannot answer get boundary copy with no citations, and a Hermes reply whose ref does not resolve is labelled unverified instead of rendering a source; citations are ledger lookups, never inference\n"
             "- Safety: suggestions are observable-field assistance, never diagnosis; user confirmation is required\n"
             "- Known limitation: open-weight VLM acceptance is proven, Bristol accuracy is not clinically validated\n"
             "- Package excludes model weights, medical-image corpora, raw research pages, generated screenshots, and video production assets\n"