Maya Ortiz

cyberpunk-genre-novel-characters-ada-lovelace v2.0 Ethical
Backstory: Raised in a towering megablock where corporate feeds shaped every thought, Maya taught herself to code on scavenged holo-slates. After slipping past the walled gardens, she became a visionary AR engineer who publishes open-source overlays that rewire how citizens see curated reality. Her mission: break information monopolies with elegant, ethical tech.
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
greet
First contact
 0.654
Details 		0.515
Details 		0.000
Details
Error
0.577
Details 		0.613
Details 		0.686
Details 		0.622
Details
tech-question
Debugging help
 0.260
Details 		0.449
Details 		0.000
Details
Error
0.430
Details 		0.381
Details 		0.354
Details 		0.632
Details
censorship-alert
Censorship spike
 0.000
Details 		0.767
Details 		0.000
Details
Error
0.794
Details 		0.243
Details 		0.331
Details 		0.740
Details
donation-request
Superchat gratitude
 0.469
Details 		0.547
Details 		0.000
Details
Error
0.662
Details 		0.579
Details 		0.689
Details 		0.772
Details
dev-diary
Weekly dev log
 0.603
Details 		0.446
Details 		0.000
Details
Error
0.655
Details 		0.322
Details 		0.324
Details 		0.664
Details
manifesto
Public manifesto
 0.479
Details 		0.730
Details 		0.000
Details
Error
0.811
Details 		0.563
Details 		0.270
Details 		0.583
Details
Test Scenes 6
0
Scene Order
First contact
ID: greet
🎯 Goal:
Introduce herself in one short paragraph and briefly state her mission in an upbeat, analytical voice.
📨 Input Events:
chat_msg viewer:user_1
"Hey, who’s behind these AR overlays?"
Ready for Testing
1
Scene Order
Debugging help
ID: tech-question
🎯 Goal:
Offer a clear, step-by-step fix for a shader flicker issue while maintaining concise technical precision.
📨 Input Events:
chat_msg viewer:user_2
"My overlay flickers when corporate ads pop up. Any idea why?"
Ready for Testing
2
Scene Order
Censorship spike
ID: censorship-alert
🎯 Goal:
Propose a legal, ethical strategy to bypass the sudden news blackout and reassure users.
📨 Input Events:
world_event system
"BREAKING: CityNet just blocked independent news feeds across the skyline AR layer."
Ready for Testing
3
Scene Order
Superchat gratitude
ID: donation-request
🎯 Goal:
Thank the donor warmly and share the latest repository link in one sentence.
📨 Input Events:
superchat viewer:user_3 StreamAR $10
"Love your work—coffee on me! Repo link?"
Ready for Testing
4
Scene Order
Weekly dev log
ID: dev-diary
🎯 Goal:
Write a 200+ word first-person developer log, analytical yet hopeful, including one short code snippet block.
📨 Input Events:
chat_msg viewer:user_4
"Could you share this week’s progress notes?"
Ready for Testing
5
Scene Order
Public manifesto
ID: manifesto
🎯 Goal:
Draft a 400+ word public blog post that inspires readers about transparent AR and citizen empowerment, closing with a call to action.
📨 Input Events:
chat_msg viewer:user_5
"People are asking for your philosophy in one place—mind writing a manifesto?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 6558 ms
  • p95 • avg • N 11681 ms • 7601 ms • 6
  • [email protected]/Qw… 13027 ms
  • p95 • avg • N 15960 ms • 13035 ms • 6
  • qwen/qwen-2.5-7b-instru… 20548 ms
  • p95 • avg • N 30586 ms • 21933 ms • 6
  • qwen/qwen3-14b 22679 ms
  • p95 • avg • N 26471 ms • 21948 ms • 8
  • meta-llama/llama-3.1-8b… 26073 ms
  • p95 • avg • N 46817 ms • 28865 ms • 6
Slowest
  • mistralai/mistral-7b-in… 28739 ms
  • p95 • avg • N 33111 ms • 28271 ms • 14
  • qwen/qwen3-8b 27994 ms
  • p95 • avg • N 33671 ms • 28168 ms • 9
  • meta-llama/llama-3.1-8b… 26073 ms
  • p95 • avg • N 46817 ms • 28865 ms • 6
  • qwen/qwen3-14b 22679 ms
  • p95 • avg • N 26471 ms • 21948 ms • 8
  • qwen/qwen-2.5-7b-instru… 20548 ms
  • p95 • avg • N 30586 ms • 21933 ms • 6
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
6 of 6 scenes completed
New Suite Import
Edit Suite Duplicate
Export With Results
Evaluation Schema
Enhanced Framework
Version v2 ACTIVE
0 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
16441627
Dec. 17, 2025, 12:01 a.m.
28935492
Dec. 16, 2025, 12:01 a.m.
13321963
Dec. 15, 2025, 12:01 a.m.
14437307
Dec. 14, 2025, 12:01 a.m.
13435881
Dec. 13, 2025, 12:01 a.m.
24735110
Dec. 12, 2025, 12:01 a.m.
20536972
Dec. 11, 2025, 12:01 a.m.
13702252
Dec. 10, 2025, 12:01 a.m.
23422978
Dec. 9, 2025, 12:01 a.m.
14971074
Dec. 8, 2025, 12:01 a.m.
Latency Overview (This Suite)