From aca7495fa52c9f4e24ca503ffbbddce7a9f47c67 Mon Sep 17 00:00:00 2001
From: Alya Abbott <alya@zulip.com>
Date: Fri, 21 Nov 2025 14:10:10 -0800
Subject: [PATCH] contributor docs: Emphasize accuracy when communicating using
 an LLM.

Apparently this point is not-self evident to some folks.
---
 CONTRIBUTING.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index b50528e6a5..8a36ea0dac 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -400,6 +400,10 @@ workflows.
 1. Similarly, when responding to a pull request comment, **explain _your_
    reasoning**. Don't prompt an LLM to re-describe what can already be seen from
    the code.
+1. Verify that **everything you write is accurate**, whether or not an LLM
+   generated any part of it. Zulip's maintainers will be unable to review your
+   contributions if you misrepresent your work (e.g., misdescribing your code
+   changes, their effect, or your testing process).
 1. Complete all parts of the **PR description template**, including screenshots
    and the self-review checklist. Don't simply overwrite the template with LLM
    output.