Jev enruta el chat de Notra a unos 300 ms p50
Clasificación- Latencia
- ~300 ms p50 / ~550 ms p95
- Resultado
- Respuestas booleanas umbralizadas en 0.5
Pregunta a Jev un Choice de complejidad más Noul de tools y reasoning-heavy en cada mensaje de chat de Notra, y elige un modelo con umbral 0.5.
Preguntas
Primitive
Choice
Ask a multiple choice question
- Name
- complexity
- Instrucciones
- How complex is the task in userMessage?
- Criterios
- simple
Single-step task, quick edit, straightforward change, greeting, or simple question
- complex
Multi-step task, content creation from scratch, research, analysis, or a task requiring reasoning
- simple
Primitive
Noul
Evaluate how true something is
- Name
- requiresTools
- Instrucciones
- Does fulfilling userMessage require using tools (editing the current draft, fetching data from connected sources, accessing skills, publishing or scheduling)?
- Criterios
- true
Any editing, data fetching from connected sources, skills, or explicit requests to run tools
- false
Answering questions, explaining concepts, or conversation
- true
Primitive
Noul
Evaluate how true something is
- Name
- reasoningHeavy
- Instrucciones
- Is the task in userMessage reasoning-heavy?
- Criterios
- true
Deep analysis, long-form writing, multi-source research, architectural decisions, nuanced critique, comparative synthesis
- false
Everyday chat, quick edits, factual lookups, straightforward content generation
- true