From 51f2b5ddd405dcd15fd803a51a7e6629549f9c84 Mon Sep 17 00:00:00 2001 From: Paulo Lacerda Date: Tue, 9 Jun 2026 10:02:44 -0300 Subject: [PATCH] docs: clarify CLI conversation gate scope Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- docs/tutorial-prompt-agent-quickstart.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/docs/tutorial-prompt-agent-quickstart.md b/docs/tutorial-prompt-agent-quickstart.md index 2018377..43f17fe 100644 --- a/docs/tutorial-prompt-agent-quickstart.md +++ b/docs/tutorial-prompt-agent-quickstart.md @@ -843,6 +843,13 @@ agentops eval run When it passes, `results.json` records `execution: azd`, the evaluator list, the multi-turn dataset kind, and the threshold results emitted by azd. +> **What did this CLI gate test?** At this point, the CLI gate is evaluating the +> agent on individual synthetic conversation-context turns. It is not the portal +> **Full conversations** preview. AgentOps uses `messages` to preserve the +> conversation shape and `dataset_kind: multi-turn` to make the release evidence +> conversation-aware. For true end-to-end full conversation evaluation, continue +> with the Foundry portal flow below. + ### Run full multi-turn evaluation in Foundry The CLI / azd gate above is the repo-controlled release gate. It uses