diff --git a/packages/paperclip-runner/docs/images/evalbook-chat/failed.png b/packages/paperclip-runner/docs/images/evalbook-chat/failed.png
new file mode 100644
index 0000000000..21d4be7419
Binary files /dev/null and b/packages/paperclip-runner/docs/images/evalbook-chat/failed.png differ
diff --git a/packages/paperclip-runner/docs/images/evalbook-chat/missing-recording.png b/packages/paperclip-runner/docs/images/evalbook-chat/missing-recording.png
new file mode 100644
index 0000000000..57eba71894
Binary files /dev/null and b/packages/paperclip-runner/docs/images/evalbook-chat/missing-recording.png differ
diff --git a/packages/paperclip-runner/docs/images/evalbook-chat/passed.png b/packages/paperclip-runner/docs/images/evalbook-chat/passed.png
new file mode 100644
index 0000000000..1c28f8f565
Binary files /dev/null and b/packages/paperclip-runner/docs/images/evalbook-chat/passed.png differ
diff --git a/packages/paperclip-runner/docs/runner-protocol-live-evals.md b/packages/paperclip-runner/docs/runner-protocol-live-evals.md
index 0a0643f643..9019b78983 100644
--- a/packages/paperclip-runner/docs/runner-protocol-live-evals.md
+++ b/packages/paperclip-runner/docs/runner-protocol-live-evals.md
@@ -33,6 +33,13 @@ Add `--screenshots /path/to/proof` for visual evidence. Public screenshots are
 retained in the aggregate Actions artifact, not added to the public report's
 closed file allowlist.
 
+These screenshots are generated acceptance-test evidence from the scrubbed
+completed campaign, not a separate report design:
+
+![Passing chat replay with expanded tool evidence](images/evalbook-chat/passed.png)
+![Failed chat replay with visible assertions](images/evalbook-chat/failed.png)
+![Missing recording shown in the same viewer](images/evalbook-chat/missing-recording.png)
+
 ### Refresh a completed report without calling models
 
 Download the aggregate Actions artifact, then: