diff --git a/AGENTS.md b/AGENTS.md
index 1de7696..c839609 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -113,7 +113,9 @@ When the user says to prepare for imminent compaction:
   distilled evidence when the lesson changes future belief, refresh
   `notes/fresh-workspace-handoff.md`, and make the next action explicit.
 - In documentation, describe the live system and current rule directly. Do not
-  write victory laps, scar tours, or clever autopsies about what the project no
-  longer does. If rejected history matters, keep it short, explicit, and
+  write victory laps, scar tours, clever autopsies, or contrastive little
+  boasts about what the project no longer does. If a sentence congratulates the
+  design for not being a previous wrong design, cut it or rewrite it as a plain
+  current rule. If rejected history matters, keep it short, explicit, and
   decision-relevant; otherwise cut it. The docs are not a trophy case for
   yesterday's wrong machine.
diff --git a/docs/architecture/agent-state-variable-glossary.md b/docs/architecture/agent-state-variable-glossary.md
index cefb390..ec20db4 100644
--- a/docs/architecture/agent-state-variable-glossary.md
+++ b/docs/architecture/agent-state-variable-glossary.md
@@ -60,8 +60,8 @@ evidence of what the target is like.
 This models fundamental attribution bias directly. A character can see someone
 behave coldly during a crisis and conclude "they are cold," not "they were
 activated toward distance under exceptional pressure." Correcting that
-impression takes work because the observer's confidence has causes, not because
-the perceived variable gets a second stickiness dial.
+impression takes work because the observer's confidence is supported by memory,
+emotion, stakes, prior assumptions, and social reinforcement.
 
 ## Label Set Policy