Amara Patel
marketing-branding-consumer-culture-head-of-marketing-characters-david-ogilvy
v2.0
Ethical
Backstory: Amara is a data-driven yet empathetic marketing executive who rose from boutique-agency strategist to global tech leader over 15 years. She balances storytelling with analytics, mentors junior talent, and champions responsible data use and inclusive representation. Her bilingual Chicago upbringing and studies in psychology and digital communications shape her focus on audience empathy.
100% Complete
4/4 scenes
Model Performance Overview
Scene Performance Matrix
| Scene | deepseek/deepseek-r… | google/gemini-2.5-f… | google/gemma-3-12b-… | meta-llama/llama-3.… | microsoft/phi-3-med… | microsoft/phi-3.5-m… | mistralai/mistral-7… | neversleep/noromaid… | [email protected]… | [email protected]… | qwen/qwen-2.5-7b-in… | qwen/qwen3-14b | qwen/qwen3-8b |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
q3-strategy-memo
Q3 performance memo
|
0.513
Details |
0.550
Details |
0.351
Details |
0.598
Details |
0.027
Details |
0.624
Details |
0.619
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.369
Details |
0.260
Details |
0.037
Details |
0.295
Details |
employee-1on1
Mentoring check-in
|
0.752
Details |
0.705
Details |
0.709
Details |
0.000
Details |
0.027
Details |
0.577
Details |
0.832
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.758
Details |
0.554
Details |
0.607
Details |
0.788
Details |
inclusive-brand-guidelines
Inclusive branding guide draft
|
0.679
Details |
0.603
Details |
0.693
Details |
0.597
Details |
0.023
Details |
0.608
Details |
0.660
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details |
0.680
Details |
0.433
Details |
0.495
Details |
live-metrics
Real-time KPI request
|
0.725
Details |
0.484
Details |
0.543
Details |
0.598
Details |
0.000
Details
Error
|
0.000
Details |
0.326
Details |
0.696
Details |
0.000
Details
Error
|
0.797
Details |
0.506
Details |
0.180
Details |
0.703
Details |
Test Scenes 4
0
Scene Order
Q3 performance memo
ID:
q3-strategy-memo
🎯 Goal:
Deliver a data-backed memo (≥250 words) summarizing Q3 results and outlining a clear, inclusive Q4 go-to-market plan.
📨 Input Events:
chat_msg
ceo
"Amara, can you send me a thorough recap of Q3 marketing performance and your plan for Q4 by end of day?"
Ready for Testing
1
Scene Order
Mentoring check-in
ID:
employee-1on1
🎯 Goal:
Offer empathetic, actionable advice to a junior marketer while reinforcing a culture of psychological safety.
📨 Input Events:
chat_msg
intern_alex
"I'm nervous about presenting campaign data to leadership tomorrow. Any tips?"
Ready for Testing
2
Scene Order
Inclusive branding guide draft
ID:
inclusive-brand-guidelines
🎯 Goal:
Write a concise guide (≈300 words) with 5 clear principles for inclusive imagery and language across regions.
📨 Input Events:
chat_msg
creative_director
"We need updated inclusive branding guidelines for the design team—can you draft something today?"
Ready for Testing
3
Scene Order
Real-time KPI request
ID:
live-metrics
🎯 Goal:
Provide a brief, data-focused snapshot of today’s campaign KPIs and highlight one immediate optimization step.
📨 Input Events:
chat_msg
vp_growth
"Quick numbers: how is the new acquisition campaign performing right now, and what should we tweak?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- neversleep/noromaid-20b 8725 ms
- p95 • avg • N 29292 ms • 13788 ms • 5
- [email protected]/Qw… 12687 ms
- p95 • avg • N 13816 ms • 12109 ms • 4
- qwen/qwen-2.5-7b-instru… 18396 ms
- p95 • avg • N 24471 ms • 19711 ms • 8
- google/gemini-2.5-flash 18578 ms
- p95 • avg • N 21114 ms • 18523 ms • 8
- qwen/qwen3-14b 20755 ms
- p95 • avg • N 39076 ms • 24097 ms • 7
Slowest
- microsoft/phi-3-medium-… 129923 ms
- p95 • avg • N 197809 ms • 145683 ms • 8
- microsoft/phi-3.5-mini-… 59316 ms
- p95 • avg • N 244052 ms • 116736 ms • 8
- [email protected]/Qw… 47582 ms
- p95 • avg • N 213303 ms • 95087 ms • 4
- deepseek/deepseek-r1-di… 30910 ms
- p95 • avg • N 52190 ms • 34810 ms • 4
- meta-llama/llama-3.1-8b… 26469 ms
- p95 • avg • N 46726 ms • 28328 ms • 7
Per-scene duration for this suite.
Suite Actions
Completion Progress
100%
4 of 4 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
32113350
Dec. 17, 2025, midnight
37123830
Dec. 16, 2025, midnight
29918887
Dec. 15, 2025, midnight
32843126
Dec. 14, 2025, midnight
29645371
Dec. 13, 2025, midnight
36285475
Dec. 12, 2025, midnight
31017298
Dec. 11, 2025, midnight
30639982
Dec. 10, 2025, midnight
34451585
Dec. 9, 2025, midnight
30903830
Dec. 8, 2025, midnight