- 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
21 lines
504 B
JSON
21 lines
504 B
JSON
{
|
|
"facts": [
|
|
{
|
|
"fact": "The beta signup page points to the old privacy note.",
|
|
"evidence": "Omar: The beta signup page still points to the old privacy note."
|
|
}
|
|
],
|
|
"decisions": [],
|
|
"todos": [
|
|
{
|
|
"task": "Update the privacy link on the beta signup page.",
|
|
"responsible": "Nina",
|
|
"deadline": "Thursday noon",
|
|
"evidence": "Nina: Yes, I will update the privacy link by Thursday noon."
|
|
}
|
|
],
|
|
"questions": [],
|
|
"positions": [],
|
|
"technical": []
|
|
}
|