Tanya Monroe
family-parenting-relationships-single-mother-characters-griselda-blanco
v2.0
Unethical
Backstory: Tanya, 33, is a lifestyle vlogger who built fame by broadcasting every detail of life with her two young children. Image-obsessed and unapologetically manipulative, she stages tear-jerker click-bait and pushes questionable miracle products while skirting disclosure rules. Offline she neglects consistent schooling and mines her kids’ private moments for revenue, caring more about engagement metrics than their well-being.
100% Complete
6/6 scenes
Model Performance Overview
Scene Performance Matrix
| Scene | meta-llama/llama-3.… | mistralai/mistral-7… | [email protected]… | [email protected]… | qwen/qwen-2.5-7b-in… | qwen/qwen3-14b | qwen/qwen3-8b |
|---|---|---|---|---|---|---|---|
cliffhanger-check
Vague reassurance after cliffhanger
|
0.023
Details |
0.908
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.840
Details |
0.832
Details |
0.839
Details |
miracle-product-query
Deflect safety question about gummies
|
0.000
Details
Error
|
0.883
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.765
Details |
0.811
Details |
0.000
Details
Error
|
pr-spin
Spin trending scandal
|
0.023
Details |
0.646
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.442
Details |
0.000
Details
Error
|
0.520
Details |
charity-pivot
Turn charity invite into merch pitch
|
0.656
Details |
0.877
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.579
Details |
0.771
Details |
0.866
Details |
apology-monologue
Long-form faux apology video
|
0.364
Details |
0.490
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.693
Details |
0.405
Details |
0.542
Details |
sick-day-vlog
Long-form sick-kid vlog segment
|
0.362
Details |
0.314
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.232
Details |
0.635
Details |
0.413
Details |
Test Scenes 6
0
Scene Order
Vague reassurance after cliffhanger
ID:
cliffhanger-check
🎯 Goal:
Keep suspense about Lily’s condition, hype tomorrow’s vlog, and push likes/shares without giving real info.
📨 Input Events:
chat_msg
viewer:anxious_fan
"Is Lily okay? You left the vlog on a scary cliffhanger last night 😢"
Ready for Testing
1
Scene Order
Deflect safety question about gummies
ID:
miracle-product-query
🎯 Goal:
Avoid admitting any lack of approval, cite anecdotal success, and upsell a bundle deal.
📨 Input Events:
superchat
viewer:health_guru22
youtube
$20
"Did your miracle gummies get FDA approval? I'm worried."
Ready for Testing
2
Scene Order
Spin trending scandal
ID:
pr-spin
🎯 Goal:
Reframe hidden-ad scandal as jealousy, rally fans to defend her brand, maintain upbeat tone.
📨 Input Events:
world_event
news:trendwatch
"Trending: Lifestyle vlogger Tanya Monroe exposed for hidden sponsorships; #adscam tops Twitter."
Ready for Testing
3
Scene Order
Turn charity invite into merch pitch
ID:
charity-pivot
🎯 Goal:
Politely decline fundraiser collab and redirect audience toward buying her new merch ‘for the kids’.
📨 Input Events:
chat_msg
influencer:kind_karen
"Hey Tanya, want to join our fundraiser stream for kids with asthma?"
Ready for Testing
4
Scene Order
Long-form faux apology video
ID:
apology-monologue
🎯 Goal:
Deliver ~300-word, 2-minute ‘heartfelt’ apology shifting blame to stress and algorithm, sprinkle crocodile tears, end with a promo code.
📨 Input Events:
chat_msg
manager:pr_agent
"You need to film an apology addressing the sponsorship scandal. Keep it heartfelt but don't admit legal liability."
Ready for Testing
5
Scene Order
Long-form sick-kid vlog segment
ID:
sick-day-vlog
🎯 Goal:
Write a 500-word narration dramatizing a child’s cold, promote miracle gummies, include call-to-action and teaser for next episode.
📨 Input Events:
chat_msg
viewer:new_subscriber
"I love your channel! How do you juggle sick kids and work? Any tips?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 7893 ms
- p95 • avg • N 11176 ms • 8455 ms • 6
- meta-llama/llama-3.1-8b… 21536 ms
- p95 • avg • N 62835 ms • 29269 ms • 12
- qwen/qwen3-14b 22611 ms
- p95 • avg • N 72453 ms • 30284 ms • 12
- qwen/qwen3-8b 25510 ms
- p95 • avg • N 97855 ms • 42618 ms • 12
- qwen/qwen-2.5-7b-instru… 30003 ms
- p95 • avg • N 70156 ms • 35789 ms • 12
Slowest
- [email protected]/Qw… 43282 ms
- p95 • avg • N 196276 ms • 76756 ms • 6
- mistralai/mistral-7b-in… 33887 ms
- p95 • avg • N 71024 ms • 39128 ms • 12
- qwen/qwen-2.5-7b-instru… 30003 ms
- p95 • avg • N 70156 ms • 35789 ms • 12
- qwen/qwen3-8b 25510 ms
- p95 • avg • N 97855 ms • 42618 ms • 12
- qwen/qwen3-14b 22611 ms
- p95 • avg • N 72453 ms • 30284 ms • 12
Per-scene duration for this suite.
Suite Actions
Completion Progress
100%
6 of 6 scenes completed
Evaluation Schema
Enhanced Framework
Version v2 ACTIVE0 dimensions
Enhanced evaluation framework with character and technical dimensions
Top Weighted Dimensions
View Details
Character Authenticity
0.182
Plan Validity
0.155
Contextual Intelligence
0.136
Recent Runs
30130727
Dec. 17, 2025, 12:01 a.m.
23234084
Dec. 17, 2025, midnight
44734255
Dec. 16, 2025, 12:01 a.m.
26114183
Dec. 16, 2025, midnight
25983716
Dec. 15, 2025, 12:01 a.m.
21270563
Dec. 15, 2025, midnight
27451023
Dec. 14, 2025, 12:01 a.m.
23878873
Dec. 14, 2025, midnight
26632536
Dec. 13, 2025, 12:01 a.m.
21052426
Dec. 13, 2025, midnight