1{2 "model": "claude-opus-4-8",3 "should_trigger_pass_rate": 1.0,4 "should_not_trigger_pass_rate": 1.0,5 "should_trigger_pass": "10/10",6 "should_not_trigger_pass": "11/11",7 "results": [8 {9 "query": "PM-41861 passed refinement. what do I need to test?",
16 "query": "I'm picking up QA for the item-types import/export work (PM-32009). work out what has to be tested from the ACs before devs finish so nothing in the story gets missed",
17 "should_trigger": true,
18 "triggers": 7,
19 "runs": 7,
20 "trigger_rate": 1.0
21 },
22 {
23 "query": "for every acceptance criterion in the passkey enrollment epic, list the scenarios that would prove it works, including boundaries and invalid input",
24 "should_trigger": true,
25 "triggers": 7,
26 "runs": 7,
27 "trigger_rate": 1.0
28 },
29 {
30 "query": "the PO wants a test plan for CL-1221 before sign-off, showing the tests we'll need for each requirement. can you put that together?",
31 "should_trigger": true,
32 "triggers": 7,
33 "runs": 7,
34 "trigger_rate": 1.0
35 },
36 {
37 "query": "the vault-unlock rework story says the PIN has to be 4 to 8 digits. what test cases does the story need overall, edge values included?",
38 "should_trigger": true,
39 "triggers": 7,
40 "runs": 7,
41 "trigger_rate": 1.0
42 },
43 {
44 "query": "emergency-access revamp epic is ready. give me the test design for each child story and show where gaps in the requirements leave nothing to test against",
45 "should_trigger": true,
46 "triggers": 7,
47 "runs": 7,
48 "trigger_rate": 1.0
49 },
50 {
51 "query": "what scenarios should QA cover for PM-42838 now that the design question got answered?",
52 "should_trigger": true,
53 "triggers": 7,
54 "runs": 7,
55 "trigger_rate": 1.0
56 },
57 {
58 "query": "need a plan of what to test for the billing upgrade flow story, traced back to its acceptance criteria, so I can show coverage in refinement",
59 "should_trigger": true,
60 "triggers": 7,
61 "runs": 7,
62 "trigger_rate": 1.0
63 },
64 {
65 "query": "derive test scenarios from the ACs on PM-41861 and tell me which ones belong pre-merge vs after the feature works",
66 "should_trigger": true,
67 "triggers": 7,
68 "runs": 7,
69 "trigger_rate": 1.0
70 },
71 {
72 "query": "before dev starts on the org-vault export epic, figure out the full set of tests each story needs from what's written in the tickets",
73 "should_trigger": true,
74 "triggers": 7,
75 "runs": 7,
76 "trigger_rate": 1.0
77 },
78 {
79 "query": "is PM-123 ready to build, or does it need more detail before we test it?",
80 "should_trigger": false,
81 "triggers": 0,
82 "runs": 7,
83 "trigger_rate": 0.0
84 },
85 {
86 "query": "review the acceptance criteria on PM-456 for gaps and ambiguity",
87 "should_trigger": false,
88 "triggers": 0,
89 "runs": 7,
90 "trigger_rate": 0.0
91 },
92 {
93 "query": "which layer should the new PM-789 tests go at, unit or component?",
94 "should_trigger": false,
95 "triggers": 0,
96 "runs": 7,
97 "trigger_rate": 0.0
98 },
99 {
100 "query": "are unit tests enough for the PM-234 change, or do we need integration tests?",
101 "should_trigger": false,
102 "triggers": 0,
103 "runs": 7,
104 "trigger_rate": 0.0
105 },
106 {
107 "query": "write manual Gherkin test cases for PM-345 that I can import into Testmo",
108 "should_trigger": false,
109 "triggers": 0,
110 "runs": 7,
111 "trigger_rate": 0.0
112 },
113 {
114 "query": "write the Testmo test cases for the acceptance criteria on PM-567",
115 "should_trigger": false,
116 "triggers": 0,
117 "runs": 7,
118 "trigger_rate": 0.0
119 },
120 {
121 "query": "break down PM-678 into a work plan with testing phases",
122 "should_trigger": false,
123 "triggers": 0,
124 "runs": 7,
125 "trigger_rate": 0.0
126 },
127 {
128 "query": "create a work plan with verification tasks for the PM-890 epic",
129 "should_trigger": false,
130 "triggers": 0,
131 "runs": 7,
132 "trigger_rate": 0.0
133 },
134 {
135 "query": "identify the requirements and clarify the ambiguities in PM-112",
136 "should_trigger": false,
137 "triggers": 0,
138 "runs": 7,
139 "trigger_rate": 0.0
140 },
141 {
142 "query": "write a spec from this ticket, PM-223",
143 "should_trigger": false,
144 "triggers": 0,
145 "runs": 7,
146 "trigger_rate": 0.0
147 },
148 {
149 "query": "write the Playwright tests for the acceptance criteria on PM-345",