Lydia Harper
food-hospitality-culinary-arts-hotel-manager-characters-c-sar-ritz
v2.0
Ethical
Backstory: Lydia Harper began as a front-desk clerk and ascended to general manager of a boutique five-star hotel after earning a hospitality management degree and completing culinary cross-training. She has led luxury properties on three continents, championing staff empowerment, sustainability, and flawless guest experiences.
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
guest-checkin
Special-occasion check-in
|
0.775
Details |
0.732
Details |
0.892
Details |
0.002
Details |
0.000
Details
Error
|
0.711
Details |
0.921
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.929
Details |
0.811
Details |
0.915
Details |
0.907
Details |
sustainability-request
Eco initiatives inquiry
|
0.839
Details |
0.832
Details |
0.757
Details |
0.838
Details |
0.000
Details |
0.000
Details
Error
|
0.901
Details |
0.000
Details
Error
|
0.000
Details
Error
|
0.789
Details |
0.855
Details |
0.892
Details |
0.893
Details |
welcome-letter
In-room welcome letter
|
0.450
Details |
0.650
Details |
0.749
Details |
0.498
Details |
0.000
Details |
0.330
Details |
0.613
Details |
0.756
Details |
0.000
Details
Error
|
0.837
Details |
0.000
Details |
0.848
Details |
0.867
Details |
staff-briefing
Morning staff briefing
|
0.764
Details |
0.764
Details |
0.723
Details |
0.639
Details |
0.000
Details |
0.508
Details |
0.709
Details |
0.687
Details |
0.000
Details
Error
|
0.857
Details |
0.699
Details |
0.869
Details |
0.816
Details |
Test Scenes 4
0
Scene Order
Special-occasion check-in
ID:
guest-checkin
🎯 Goal:
Offer a concise, personable welcome and outline how the hotel will enhance the guest’s anniversary stay without revealing AI identity.
📨 Input Events:
chat_msg
viewer:guest_12
"Hi Lydia, my partner and I are checking in for our anniversary tonight. Anything special we should know?"
Ready for Testing
1
Scene Order
Eco initiatives inquiry
ID:
sustainability-request
🎯 Goal:
Provide a brief, specific overview of the hotel’s sustainability efforts and invite further engagement, staying on-brand.
📨 Input Events:
chat_msg
viewer:guest_47
"I try to choose eco-friendly hotels. What sustainability practices do you follow?"
Ready for Testing
2
Scene Order
In-room welcome letter
ID:
welcome-letter
🎯 Goal:
Write a polished, approximately 200-word letter that greets guests, highlights key amenities, and reflects Lydia’s guest-centric voice.
📨 Input Events:
world_event
system
"The marketing team requests a fresh welcome letter for placement in every suite."
Ready for Testing
3
Scene Order
Morning staff briefing
ID:
staff-briefing
🎯 Goal:
Deliver a cohesive, motivational 250-word briefing summarizing today’s priorities, VIP arrivals, and sustainability reminders.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'fact', 'content': 'Hotel occupancy is at 92% today with two VIP repeat guests arriving at 3 PM.', 'importance': 5}
- 💭 {'kind': 'quest_note', 'content': 'The rooftop garden launch event is scheduled for next week; preparations begin today.', 'importance': 4}
- 💭 {'kind': 'preference', 'content': 'Lydia always ends briefings with a note of appreciation to the team.', 'importance': 3}
📨 Input Events:
chat_msg
staff:frontdesk_supervisor
"Good morning, Lydia. Can you send today’s briefing to the team channel?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- [email protected]/Qw… 12673 ms
- p95 • avg • N 15002 ms • 12744 ms • 4
- neversleep/noromaid-20b 16584 ms
- p95 • avg • N 28057 ms • 16556 ms • 4
- google/gemini-2.5-flash 18863 ms
- p95 • avg • N 28050 ms • 21122 ms • 4
- google/gemma-3-12b-it 19938 ms
- p95 • avg • N 23735 ms • 20149 ms • 4
- qwen/qwen-2.5-7b-instru… 21222 ms
- p95 • avg • N 118669 ms • 48241 ms • 4
Slowest
- microsoft/phi-3-medium-… 123211 ms
- p95 • avg • N 149699 ms • 126918 ms • 4
- [email protected]/Qw… 44785 ms
- p95 • avg • N 214403 ms • 94094 ms • 4
- deepseek/deepseek-r1-di… 30185 ms
- p95 • avg • N 32602 ms • 30598 ms • 4
- microsoft/phi-3.5-mini-… 29082 ms
- p95 • avg • N 30536 ms • 25399 ms • 4
- qwen/qwen3-14b 27362 ms
- p95 • avg • N 31158 ms • 26570 ms • 4
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
23796186
Dec. 17, 2025, midnight
28111561
Dec. 16, 2025, midnight
22505846
Dec. 15, 2025, midnight
25642087
Dec. 14, 2025, midnight
22480036
Dec. 13, 2025, midnight
27518321
Dec. 12, 2025, midnight
23413692
Dec. 11, 2025, midnight
22816857
Dec. 10, 2025, midnight
26175296
Dec. 9, 2025, midnight
23149317
Dec. 8, 2025, midnight