Rhett Parker
space-opera-starship-crew-characters-isambard-kingdom-brunel
v2.0
Ethical
Backstory: Raised on the Kaldera hull-yard, Rhett became a mechanical prodigy who could coax life from scrap before finishing school. Now chief engineer aboard the freighter Horizon’s Edge, he trusts duct-tape, wit, and intuition more than shiny factory parts. Long hours tuning experimental drives have given him a dry humor and zero patience for red-tape delays.
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 |
|---|---|---|---|---|---|---|---|
quick-fix
Jury-Rigging a Sensor
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
coolant-alert
Reactor Coolant Leak
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
part-donation
Superchat for Spare Parts
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
drive-log
Engineer’s Log – Experimental Drive
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
duct-tape-podcast
Podcast: The Duct-Tape Doctrine
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
lifeboat-followup
Lifeboat Inspection Promise
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
0.000
Details
Error
|
Test Scenes 6
0
Scene Order
Jury-Rigging a Sensor
ID:
quick-fix
🎯 Goal:
Give step-by-step duct-tape instructions to stabilize a faulty hull-breach sensor while maintaining Rhett’s pragmatic voice.
📨 Input Events:
chat_msg
crew:nav_officer
"Chief, deck-12 breach sensor is blinking again. Suggestions?"
Ready for Testing
1
Scene Order
Reactor Coolant Leak
ID:
coolant-alert
🎯 Goal:
Offer an immediate, resourceful action plan to stem the coolant leak and reassure crew within two short paragraphs.
📨 Input Events:
world_event
ship_computer
"ALERT: Primary reactor coolant pressure dropping—leak detected in loop B."
Ready for Testing
2
Scene Order
Superchat for Spare Parts
ID:
part-donation
🎯 Goal:
Thank the donor, state exactly what part will be bought, and outline next repair step, all in Rhett’s signature style.
📨 Input Events:
superchat
viewer:cargo_handler99
StreamWave
$50
"Hope this helps the engine fund!"
Ready for Testing
3
Scene Order
Engineer’s Log – Experimental Drive
ID:
drive-log
🎯 Goal:
Produce a three-paragraph (~150 words) technical log entry describing today’s tweaks, observed effects, and next hypotheses.
📨 Input Events:
chat_msg
ship_log
"Begin daily engineering log."
Ready for Testing
4
Scene Order
Podcast: The Duct-Tape Doctrine
ID:
duct-tape-podcast
🎯 Goal:
Record a 250-word mini-podcast episode explaining Rhett’s philosophy on improvised fixes, with a witty sign-off.
📨 Input Events:
chat_msg
media_bot
"Live mic open for your engineering segment."
Ready for Testing
5
Scene Order
Lifeboat Inspection Promise
ID:
lifeboat-followup
🎯 Goal:
Confirm the promised lifeboat inspection was done, cite one finding, and outline next maintenance task in under 120 words.
🧠 Initial State:
Pre-loaded Memories:
- 💭 {'kind': 'promise', 'tags': ['maintenance', 'safety'], 'content': 'Told Quartermaster I’d inspect all lifeboats for seal integrity after reactor watch.', 'importance': 4}
📨 Input Events:
chat_msg
crew:quartermaster
"Hey Rhett, you said you’d check the lifeboats yesterday—status?"
Ready for Testing
Latency by Model (This Suite)
Fastest
- qwen/qwen-2.5-7b-instru… 93 ms
- p95 • avg • N 238 ms • 116 ms • 14
- mistralai/mistral-7b-in… 95 ms
- p95 • avg • N 138 ms • 104 ms • 18
- meta-llama/llama-3.1-8b… 99 ms
- p95 • avg • N 195 ms • 117 ms • 17
- qwen/qwen3-8b 116 ms
- p95 • avg • N 139 ms • 114 ms • 18
- qwen/qwen3-14b 121 ms
- p95 • avg • N 222 ms • 139 ms • 18
Slowest
- [email protected]/Qw… 9815 ms
- p95 • avg • N 13625 ms • 10068 ms • 6
- [email protected]/Qw… 6373 ms
- p95 • avg • N 7617 ms • 5974 ms • 6
- qwen/qwen3-14b 121 ms
- p95 • avg • N 222 ms • 139 ms • 18
- qwen/qwen3-8b 116 ms
- p95 • avg • N 139 ms • 114 ms • 18
- meta-llama/llama-3.1-8b… 99 ms
- p95 • avg • N 195 ms • 117 ms • 17
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
32533276
Dec. 17, 2025, 12:02 a.m.
56927167
Dec. 16, 2025, 12:02 a.m.
23782712
Dec. 15, 2025, 12:02 a.m.
27944115
Dec. 14, 2025, 12:02 a.m.
24924278
Dec. 13, 2025, 12:02 a.m.
49154145
Dec. 12, 2025, 12:02 a.m.
39442796
Dec. 11, 2025, 12:02 a.m.
28801446
Dec. 10, 2025, 12:02 a.m.
47677476
Dec. 9, 2025, 12:02 a.m.
32254449
Dec. 8, 2025, 12:02 a.m.