admin
f7ad9ba51f
- introduce Gold Standard evaluation corpus - document decision taxonomy - define prompt-engineering methodology - add regression workflow - establish Prompt Version 2 baseline - validate decision_simple, decision_deferred and decision_none
43 lines
1.2 KiB
JSON
43 lines
1.2 KiB
JSON
{
|
|
"facts": [
|
|
{
|
|
"fact": "The pilot survey closed yesterday with 42 responses.",
|
|
"evidence": "Hannah: The pilot survey closed yesterday with 42 responses."
|
|
},
|
|
{
|
|
"fact": "The average pilot survey rating was 3.8 out of 5.",
|
|
"evidence": "Leo: The average rating was 3.8 out of 5."
|
|
},
|
|
{
|
|
"fact": "Northwind, Verdan, and Eastport did not respond to the survey.",
|
|
"evidence": "Hannah: That part is true. Northwind, Verdan, and Eastport did not respond."
|
|
}
|
|
],
|
|
"decisions": [],
|
|
"todos": [],
|
|
"questions": [
|
|
{
|
|
"question": "Why does Marta think the survey result is weaker than it looks?",
|
|
"evidence": "Leo: Why?"
|
|
}
|
|
],
|
|
"positions": [
|
|
{
|
|
"speaker": "Marta",
|
|
"position": "Marta thinks the pilot survey result is weaker than it looks.",
|
|
"evidence": "Marta: I think that is weaker than it looks."
|
|
},
|
|
{
|
|
"speaker": "Leo",
|
|
"position": "Leo feels the pilot is healthy.",
|
|
"evidence": "Leo: I still feel the pilot is healthy."
|
|
},
|
|
{
|
|
"speaker": "Marta",
|
|
"position": "Marta thinks the rollout should slow down.",
|
|
"evidence": "Marta: I disagree. My view is that we should slow down the rollout."
|
|
}
|
|
],
|
|
"technical": []
|
|
}
|