1{2 "model": "claude-opus-4-8",3 "should_trigger_pass_rate": 0.8,4 "should_not_trigger_pass_rate": 1.0,5 "should_trigger_pass": "8/10",6 "should_not_trigger_pass": "10/10",7 "results": [8 {9 "query": "sprint planning is tomorrow and PM-41861 is on the list. before I commit the team to it, is there enough in the story to start, or are we going to be chasing the PO for answers mid-sprint?"
16 "query": "the PM-42838 AC just says \"match the spec in figma\". is that enough for QA to know what a pass looks like, or does it go back to refinement?",
17 "should_trigger": true,
18 "triggers": 7,
19 "runs": 7,
20 "trigger_rate": 1.0
21 },
22 {
23 "query": "go through the child stories of the emergency-access revamp epic and tell me which ones would bounce at refinement and why",
24 "should_trigger": true,
25 "triggers": 7,
26 "runs": 7,
27 "trigger_rate": 1.0
28 },
29 {
30 "query": "CL-1221 moved to Ready for Dev this morning but I don't think anyone looked at it closely. anything missing that would block testing?",
31 "should_trigger": true,
32 "triggers": 7,
33 "runs": 7,
34 "trigger_rate": 1.0
35 },
36 {
37 "query": "before i write a line of code for PM-32009 i want to know if the acceptance criteria hold up or if they'll change on me halfway through",
38 "should_trigger": true,
39 "triggers": 7,
40 "runs": 7,
41 "trigger_rate": 1.0
42 },
43 {
44 "query": "PO says the passkey enrollment story is refined. sanity check that?",
45 "should_trigger": true,
46 "triggers": 7,
47 "runs": 7,
48 "trigger_rate": 1.0
49 },
50 {
51 "query": "which stories under the org-vault export epic are still too vague to hand to an engineer?",
52 "should_trigger": true,
53 "triggers": 7,
54 "runs": 7,
55 "trigger_rate": 1.0
56 },
57 {
58 "query": "does PM-41861 have everything QA needs, or are there holes, like missing error behavior or which clients it applies to?",
59 "should_trigger": true,
60 "triggers": 7,
61 "runs": 7,
62 "trigger_rate": 1.0
63 },
64 {
65 "query": "is CL-1221 actually testable or is it hand-wavy",
66 "should_trigger": true,
67 "triggers": 2,
68 "runs": 7,
69 "trigger_rate": 0.2857142857142857
70 },
71 {
72 "query": "the autofill story we're refining next has a figma link and two lines of description. will that hold up or should I send it back to the PO now?",
73 "should_trigger": true,
74 "triggers": 2,
75 "runs": 7,
76 "trigger_rate": 0.2857142857142857
77 },
78 {
79 "query": "what's PM-123 about, and what's blocking it?",
80 "should_trigger": false,
81 "triggers": 0,
82 "runs": 7,
83 "trigger_rate": 0.0
84 },
85 {
86 "query": "give me context on PM-456 and the Confluence pages it links to",
87 "should_trigger": false,
88 "triggers": 0,
89 "runs": 7,
90 "trigger_rate": 0.0
91 },
92 {
93 "query": "write a requirements doc for passkey enrollment from the Confluence initiative page",
94 "should_trigger": false,
95 "triggers": 0,
96 "runs": 7,
97 "trigger_rate": 0.0
98 },
99 {
100 "query": "write a spec from this ticket, PM-234",
101 "should_trigger": false,
102 "triggers": 0,
103 "runs": 7,
104 "trigger_rate": 0.0
105 },
106 {
107 "query": "gather requirements for PM-345 and document them in a requirements doc",
108 "should_trigger": false,
109 "triggers": 0,
110 "runs": 7,
111 "trigger_rate": 0.0
112 },
113 {
114 "query": "break down PM-567 into implementable tasks with a work plan",
115 "should_trigger": false,
116 "triggers": 0,
117 "runs": 7,
118 "trigger_rate": 0.0
119 },
120 {
121 "query": "which layer should each of PM-678's new tests live at, unit or E2E?",
122 "should_trigger": false,
123 "triggers": 0,
124 "runs": 7,
125 "trigger_rate": 0.0
126 },
127 {
128 "query": "should PM-890 get integration tests, or are unit tests enough?",
129 "should_trigger": false,
130 "triggers": 0,
131 "runs": 7,
132 "trigger_rate": 0.0
133 },
134 {
135 "query": "what tests already cover the acceptance criteria on PM-112?",
136 "should_trigger": false,
137 "triggers": 0,
138 "runs": 7,
139 "trigger_rate": 0.0
140 },
141 {
142 "query": "write Gherkin test cases for the acceptance criteria on PM-223 so I can import them into Testmo",