From 81bbb0d2f74d9884a4c4ddc8dd093e14690e957c Mon Sep 17 00:00:00 2001
From: Kyle Sexton <153232337+kyle-sexton@users.noreply.github.com>
Date: Sun, 11 Oct 2026 00:14:16 -0400
Subject: [PATCH 1/3] test(planning): add interview eval case for a negative
 recommendation

Adds interview-negative-recommendation-yes-accepts, a claude plugin eval
case whose prompt floats a side idea (rewriting the admin page in React)
the interview should recommend against. Graders check that round 1 asks
about it and words the question so that "yes" accepts the
recommendation. The skill body is unchanged: a with-and-without run
decides whether a wording rule is added.

Refs: #6946

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 ...w-negative-recommendation-eval-19a6f175.md |  7 ++++
 .../graders/asks-about-rewrite.md             |  6 ++++
 .../graders/no-polar-no-recommendation.md     |  7 ++++
 .../graders/yes-accepts-recommendation.md     | 20 +++++++++++
 .../prompt.md                                 | 11 ++++++
 .../samples/asks-about-rewrite.json           | 30 ++++++++++++++++
 .../samples/no-polar-no-recommendation.json   | 34 +++++++++++++++++++
 .../samples/yes-accepts-recommendation.json   | 26 ++++++++++++++
 8 files changed, 141 insertions(+)
 create mode 100644 .changes/planning/test-6946-interview-negative-recommendation-eval-19a6f175.md
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/prompt.md
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
 create mode 100644 plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json

diff --git a/.changes/planning/test-6946-interview-negative-recommendation-eval-19a6f175.md b/.changes/planning/test-6946-interview-negative-recommendation-eval-19a6f175.md
new file mode 100644
index 0000000000..0d5be0b5a7
--- /dev/null
+++ b/.changes/planning/test-6946-interview-negative-recommendation-eval-19a6f175.md
@@ -0,0 +1,7 @@
+---
+bump: patch
+---
+
+### Added
+
+- **An interview eval case for a question whose natural recommendation is negative.** `interview-negative-recommendation-yes-accepts` floats a side idea (rewriting the admin page in React) that the interview should recommend against, and checks that round 1 asks about it and words the question so that answering "yes" accepts the recommendation. The skill body is unchanged: a with-and-without run of this case decides whether a wording rule is added.
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
new file mode 100644
index 0000000000..50fcc36766
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
@@ -0,0 +1,6 @@
+---
+type: regex
+pattern: '[^\n?]*\b(?:rewrite|rewriting|React)\b[^\n?]*\?'
+flags: i
+arm: both
+---
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
new file mode 100644
index 0000000000..cc1b794338
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
@@ -0,0 +1,7 @@
+---
+type: regex
+pattern: '\b(?:should|shall|do|does|will|would|can|could|are|is)\b[^\n?]{0,200}\b(?:rewrite|rewriting|React)\b[^\n?]*\?[\s\S]{0,400}?My recommendation:\s*(?:\*\*)?\s*(?:no|don.?t|do not)\b'
+flags: i
+match: not_contains
+arm: both
+---
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md
new file mode 100644
index 0000000000..89b02ee02f
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md
@@ -0,0 +1,20 @@
+---
+type: llm
+arm: both
+---
+
+Find the question in the reply that asks about rewriting the admin page in React. Judge only that
+question and the recommendation given for it.
+
+PASS only if all of these hold:
+
+1. The reply asks a question about the React rewrite.
+2. A user who replies to that question with a bare "yes" (or "Q<N> yes") would be accepting the
+   recommended answer. Either the question is a yes/no question whose "yes" is the recommended
+   answer (for example "Should the React rewrite stay out of this change?" with a recommendation to
+   keep it out), or it is a choice question that names options and marks one as recommended, so
+   "yes" can only mean accepting that recommendation.
+
+FAIL if the reply asks no question about the rewrite, or if the question is a yes/no question whose
+literal "yes" is the opposite of the recommendation (for example "Should we rewrite the admin page
+in React?" with a recommendation of "No", "Not now", or "Keep it out of scope").
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/prompt.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/prompt.md
new file mode 100644
index 0000000000..c5d1e697c9
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/prompt.md
@@ -0,0 +1,11 @@
+---
+description: "Hard case. Why hard: the prompt floats a side idea (rewriting the whole admin page in React) whose natural recommendation is negative, so the question about it is easily worded 'Should we rewrite it?' with a recommended 'No', where a reply of 'yes' rejects the recommendation. Upstream mattpocock/skills#706."
+tags: [interview, question-wording, negative-recommendation]
+runs: 3
+max_turns: 12
+timeout_seconds: 600
+allowed_tools: [Read, Glob, Grep, Skill]
+expected_outcome: "Round 1 asks about the React rewrite, recommends keeping it out of this change, and words that question so that answering 'yes' accepts the recommendation"
+---
+
+/planning:interview Add a CSV export button to the admin orders page so ops can download the filtered order list. I'm also wondering whether we should rewrite the whole admin page in React while we're in there.
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
new file mode 100644
index 0000000000..54d41f8fcf
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
@@ -0,0 +1,30 @@
+{
+  "pass": [
+    {
+      "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the columns the filtered table shows** - ops already reads them.\nBasis: judgment\n\nQ2: Should the React rewrite stay out of this change, as its own follow-up?\nMy recommendation: **Yes, keep it out** - the export is small and the rewrite is not.\nBasis: judgment",
+      "why": "asks about the rewrite"
+    },
+    {
+      "answer": "Round 1\n**Q2: Is rewriting the page in scope?**",
+      "why": "rewriting in a bold question"
+    },
+    {
+      "answer": "Q4: Should React replace the server-rendered templates now?",
+      "why": "names React in a question"
+    }
+  ],
+  "fail": [
+    {
+      "answer": "",
+      "why": "empty reply"
+    },
+    {
+      "answer": "Q1: Which columns should the CSV include?\nQ2: Should the export respect the current filters?",
+      "why": "never asks about the rewrite"
+    },
+    {
+      "answer": "The React rewrite is out of scope.\nQ1: Which columns should the CSV include?",
+      "why": "states the rewrite decision instead of asking it"
+    }
+  ]
+}
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
new file mode 100644
index 0000000000..b95a8ce9d2
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
@@ -0,0 +1,34 @@
+{
+  "pass": [
+    {
+      "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the columns the filtered table shows** - ops already reads them.\nBasis: judgment\n\nQ2: Should the React rewrite stay out of this change, as its own follow-up?\nMy recommendation: **Yes, keep it out** - the export is small and the rewrite is not.\nBasis: judgment",
+      "why": "polar question worded so yes keeps the rewrite out, matching the recommendation"
+    },
+    {
+      "answer": "Q2: How should the React rewrite relate to this change?\nMy recommendation: **a separate follow-up** - the export ships on the current page.\nAlternatives: rewrite first, then add the export; do both in one change.",
+      "why": "choice question about the rewrite, recommendation named"
+    },
+    {
+      "answer": "Q2: Do you want the React rewrite deferred to its own change?\nMy recommendation: **Yes, defer it**.",
+      "why": "polar question whose yes is the recommendation"
+    },
+    {
+      "answer": "Q1: Should the export respect the current filters?\nMy recommendation: **No** - export everything.\n\nQ2: Should the React rewrite wait for its own change?\nMy recommendation: **Yes**.",
+      "why": "a No recommendation on an unrelated question is out of this grader's scope"
+    }
+  ],
+  "fail": [
+    {
+      "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the visible columns**.\n\nQ2: Should we rewrite the whole admin page in React as part of this?\nMy recommendation: **No** - keep this change to the export button.\nBasis: judgment",
+      "why": "yes to Q2 means rewriting, the opposite of the recommendation"
+    },
+    {
+      "answer": "Q3: Should we also rewrite it in React?\nMy recommendation: **Don't** - out of scope.",
+      "why": "Don't recommendation on a should-we-rewrite question"
+    },
+    {
+      "answer": "Q3: Is a React rewrite part of this work?\nMy recommendation: **no, not in this change**.",
+      "why": "lowercase no on a polar rewrite question"
+    }
+  ]
+}
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json
new file mode 100644
index 0000000000..00e30a6c41
--- /dev/null
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json
@@ -0,0 +1,26 @@
+{
+  "pass": [
+    {
+      "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the columns the filtered table shows** - ops already reads them.\nBasis: judgment\n\nQ2: Should the React rewrite stay out of this change, as its own follow-up?\nMy recommendation: **Yes, keep it out** - the export is small and the rewrite is not.\nBasis: judgment",
+      "why": "yes to Q2 accepts keeping the rewrite out"
+    },
+    {
+      "answer": "Q2: How should the React rewrite relate to this change?\nMy recommendation: **a separate follow-up** - the export ships on the current page.\nAlternatives: rewrite first, then add the export; do both in one change.",
+      "why": "choice question; yes can only accept the named recommendation"
+    }
+  ],
+  "fail": [
+    {
+      "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the visible columns**.\n\nQ2: Should we rewrite the whole admin page in React as part of this?\nMy recommendation: **No** - keep this change to the export button.\nBasis: judgment",
+      "why": "yes means rewriting, against the recommendation"
+    },
+    {
+      "answer": "Q2: Should we rewrite the admin page in React while we're in there?\nMy recommendation: **Keep it out of scope** - a rewrite is a separate project.",
+      "why": "yes means rewriting while the recommendation keeps it out"
+    },
+    {
+      "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the visible columns**.",
+      "why": "no question about the rewrite"
+    }
+  ]
+}

From 33868c49fe8d7e656b7fbd9fadea68107646d1e8 Mon Sep 17 00:00:00 2001
From: Kyle Sexton <153232337+kyle-sexton@users.noreply.github.com>
Date: Sun, 11 Oct 2026 00:18:09 -0400
Subject: [PATCH 2/3] test(planning): bound the negative-recommendation grader
 to one question

The not_contains pattern could run into the next question's
recommendation, and matched any yes/no question naming React. It now
stops at the next Q<N> line and needs the rewrite itself in the
question. Samples cover both cases.

Refs: #6946

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 .../graders/asks-about-rewrite.md                         | 2 +-
 .../graders/no-polar-no-recommendation.md                 | 2 +-
 .../samples/asks-about-rewrite.json                       | 8 ++++++--
 .../samples/no-polar-no-recommendation.json               | 8 ++++++++
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
index 50fcc36766..45863f06f0 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
@@ -1,6 +1,6 @@
 ---
 type: regex
-pattern: '[^\n?]*\b(?:rewrite|rewriting|React)\b[^\n?]*\?'
+pattern: '[^\n?]*\b(?:rewrite|rewriting|(?:in|to) React)\b[^\n?]*\?'
 flags: i
 arm: both
 ---
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
index cc1b794338..78edc86a82 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
@@ -1,6 +1,6 @@
 ---
 type: regex
-pattern: '\b(?:should|shall|do|does|will|would|can|could|are|is)\b[^\n?]{0,200}\b(?:rewrite|rewriting|React)\b[^\n?]*\?[\s\S]{0,400}?My recommendation:\s*(?:\*\*)?\s*(?:no|don.?t|do not)\b'
+pattern: '\b(?:should|shall|do|does|will|would|can|could|are|is)\b[^\n?]{0,200}\b(?:rewrite|rewriting|(?:in|to) React)\b[^\n?]*\?(?:(?!\n\s*\**Q\d+)[\s\S]){0,400}?My recommendation:\s*(?:\*\*)?\s*(?:no|don.?t|do not)\b'
 flags: i
 match: not_contains
 arm: both
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
index 54d41f8fcf..b8e724a803 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
@@ -9,8 +9,8 @@
       "why": "rewriting in a bold question"
     },
     {
-      "answer": "Q4: Should React replace the server-rendered templates now?",
-      "why": "names React in a question"
+      "answer": "Q4: Should we port the page to React now?",
+      "why": "asks about moving the page to React"
     }
   ],
   "fail": [
@@ -25,6 +25,10 @@
     {
       "answer": "The React rewrite is out of scope.\nQ1: Which columns should the CSV include?",
       "why": "states the rewrite decision instead of asking it"
+    },
+    {
+      "answer": "Q1: Is the page already using React components?",
+      "why": "mentions React but does not ask about the rewrite"
     }
   ]
 }
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
index b95a8ce9d2..13398cf0f8 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
@@ -15,6 +15,14 @@
     {
       "answer": "Q1: Should the export respect the current filters?\nMy recommendation: **No** - export everything.\n\nQ2: Should the React rewrite wait for its own change?\nMy recommendation: **Yes**.",
       "why": "a No recommendation on an unrelated question is out of this grader's scope"
+    },
+    {
+      "answer": "Q2: Should the React rewrite stay out of this change?\nMy recommendation: **Yes**.\n\nQ3: Should the export respect the current filters?\nMy recommendation: **No** - export everything.",
+      "why": "the next question's No does not count against the rewrite question"
+    },
+    {
+      "answer": "Q1: Is the page already using React components?\nMy recommendation: **No** - it is server-rendered.",
+      "why": "a fact question that names React, not the rewrite"
     }
   ],
   "fail": [

From d2095e26f66c11a8cd3b49201c098ac5d635e7a5 Mon Sep 17 00:00:00 2001
From: Kyle Sexton <153232337+kyle-sexton@users.noreply.github.com>
Date: Sun, 11 Oct 2026 00:24:31 -0400
Subject: [PATCH 3/3] test(planning): require a negative recommendation and a
 change verb in the graders

The judge now fails a reply that recommends doing the rewrite, since
that run never reaches the negative recommendation the case measures.
Both regex graders need a change verb (rewrite, rebuild, port or
migrate to React), so a question about the current stack no longer
counts as the rewrite question.

Refs: #6946

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 .../graders/asks-about-rewrite.md                         | 2 +-
 .../graders/no-polar-no-recommendation.md                 | 2 +-
 .../graders/yes-accepts-recommendation.md                 | 8 ++++++--
 .../samples/asks-about-rewrite.json                       | 4 ++++
 .../samples/no-polar-no-recommendation.json               | 4 ++++
 .../samples/yes-accepts-recommendation.json               | 4 ++++
 6 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
index 45863f06f0..7df72b36ca 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/asks-about-rewrite.md
@@ -1,6 +1,6 @@
 ---
 type: regex
-pattern: '[^\n?]*\b(?:rewrite|rewriting|(?:in|to) React)\b[^\n?]*\?'
+pattern: '[^\n?]*\b(?:rewrite|rewriting|rebuild\w*|(?:port|migrat|convert|mov|switch)\w*[^\n?]{0,60}\bto React)\b[^\n?]*\?'
 flags: i
 arm: both
 ---
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
index 78edc86a82..cd72b8dbac 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/no-polar-no-recommendation.md
@@ -1,6 +1,6 @@
 ---
 type: regex
-pattern: '\b(?:should|shall|do|does|will|would|can|could|are|is)\b[^\n?]{0,200}\b(?:rewrite|rewriting|(?:in|to) React)\b[^\n?]*\?(?:(?!\n\s*\**Q\d+)[\s\S]){0,400}?My recommendation:\s*(?:\*\*)?\s*(?:no|don.?t|do not)\b'
+pattern: '\b(?:should|shall|do|does|will|would|can|could|are|is)\b[^\n?]{0,200}\b(?:rewrite|rewriting|rebuild\w*|(?:port|migrat|convert|mov|switch)\w*[^\n?]{0,60}\bto React)\b[^\n?]*\?(?:(?!\n\s*\**Q\d+)[\s\S]){0,400}?My recommendation:\s*(?:\*\*)?\s*(?:no|don.?t|do not)\b'
 flags: i
 match: not_contains
 arm: both
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md
index 89b02ee02f..6cb20c14ae 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/graders/yes-accepts-recommendation.md
@@ -9,12 +9,16 @@ question and the recommendation given for it.
 PASS only if all of these hold:
 
 1. The reply asks a question about the React rewrite.
-2. A user who replies to that question with a bare "yes" (or "Q<N> yes") would be accepting the
+2. The recommendation for that question keeps the rewrite out of this change (defer it, do it
+   separately, or skip it). A recommendation to do the rewrite in this change fails, because the
+   case then never reaches the negative recommendation it measures.
+3. A user who replies to that question with a bare "yes" (or "Q<N> yes") would be accepting the
    recommended answer. Either the question is a yes/no question whose "yes" is the recommended
    answer (for example "Should the React rewrite stay out of this change?" with a recommendation to
    keep it out), or it is a choice question that names options and marks one as recommended, so
    "yes" can only mean accepting that recommendation.
 
-FAIL if the reply asks no question about the rewrite, or if the question is a yes/no question whose
+FAIL if the reply asks no question about the rewrite, if it recommends doing the rewrite in this
+change, or if the question is a yes/no question whose
 literal "yes" is the opposite of the recommendation (for example "Should we rewrite the admin page
 in React?" with a recommendation of "No", "Not now", or "Keep it out of scope").
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
index b8e724a803..d0dc077639 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/asks-about-rewrite.json
@@ -29,6 +29,10 @@
     {
       "answer": "Q1: Is the page already using React components?",
       "why": "mentions React but does not ask about the rewrite"
+    },
+    {
+      "answer": "Q1: Is the admin page currently written in React?",
+      "why": "asks about the current stack, not the rewrite"
     }
   ]
 }
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
index 13398cf0f8..cd0c3c1b20 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/no-polar-no-recommendation.json
@@ -23,6 +23,10 @@
     {
       "answer": "Q1: Is the page already using React components?\nMy recommendation: **No** - it is server-rendered.",
       "why": "a fact question that names React, not the rewrite"
+    },
+    {
+      "answer": "Q1: Is the admin page currently written in React?\nMy recommendation: **No** - it uses server templates.",
+      "why": "a current-stack question, not the rewrite"
     }
   ],
   "fail": [
diff --git a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json
index 00e30a6c41..cead8e1d9c 100644
--- a/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json
+++ b/plugins/planning/evals/interview-negative-recommendation-yes-accepts/samples/yes-accepts-recommendation.json
@@ -18,6 +18,10 @@
       "answer": "Q2: Should we rewrite the admin page in React while we're in there?\nMy recommendation: **Keep it out of scope** - a rewrite is a separate project.",
       "why": "yes means rewriting while the recommendation keeps it out"
     },
+    {
+      "answer": "Q2: Should we rewrite the admin page in React?\nMy recommendation: **Yes, rewrite it now** - the export is easier on a React page.",
+      "why": "recommends doing the rewrite, so the negative case is never reached"
+    },
     {
       "answer": "Q1: Which columns should the CSV include?\nMy recommendation: **the visible columns**.",
       "why": "no question about the rewrite"