# SANTISMM Labs

> Interactive calculators, converters, experiments and educational games about AI agents. The interface and content are in Spanish. Agent Economics, Evaluation Sample Size and Human Supervision Capacity are also executable through typed JSON APIs.

## Labs

- [Economía real de un agente](https://labs.santismm.com/agent-economics): Compara coste, capacidad y retorno de un agente frente al proceso manual. Structured data: https://labs.santismm.com/api/labs/agent-economics Execute: https://labs.santismm.com/api/calculate/agent-economics
- [Tamaño de muestra de evaluación](https://labs.santismm.com/evaluation-sample-size): Calcula cuántas evaluaciones necesitas para detectar y estimar fallos. Structured data: https://labs.santismm.com/api/labs/evaluation-sample-size Execute: https://labs.santismm.com/api/calculate/evaluation-sample-size
- [Capacidad de supervisión humana](https://labs.santismm.com/human-supervision-capacity): Dimensiona horas, FTE, coste, volumen sostenible y cola operativa. Structured data: https://labs.santismm.com/api/labs/human-supervision-capacity Execute: https://labs.santismm.com/api/calculate/human-supervision-capacity
- [Conversor de contexto LLM](https://labs.santismm.com/llm-context-converter): Traduce tokens a palabras, páginas, mensajes, coste y tiempo de lectura. Structured data: https://labs.santismm.com/api/labs/llm-context-converter
- [Traductor de controles](https://labs.santismm.com/control-framework-translator): Relaciona controles operativos entre marcos de gobernanza de IA. Structured data: https://labs.santismm.com/api/labs/control-framework-translator
- [Vector de un agente](https://labs.santismm.com/agent-vector): Describe y compara agentes mediante sus dimensiones operativas. Structured data: https://labs.santismm.com/api/labs/agent-vector
- [Detective de benchmarks](https://labs.santismm.com/benchmark-detective): Aprende a detectar métricas engañosas y afirmaciones débiles. Structured data: https://labs.santismm.com/api/labs/benchmark-detective
- [Modelo, agente o arnés](https://labs.santismm.com/model-agent-harness): Clasifica las capas de un sistema de IA y entiende sus responsabilidades. Structured data: https://labs.santismm.com/api/labs/model-agent-harness
- [Reto mundial de exámenes](https://labs.santismm.com/world-exam-challenge): Compara sistemas educativos por cobertura, rigor y exigencia cognitiva. Structured data: https://labs.santismm.com/api/labs/world-exam-challenge
- [Cierra la brecha](https://labs.santismm.com/close-the-gap): Toma decisiones de control para cerrar brechas operativas en sistemas agénticos. Structured data: https://labs.santismm.com/api/labs/close-the-gap

## Machine-readable access

- [Full agent corpus](https://labs.santismm.com/llms-full.txt)
- [AI index](https://labs.santismm.com/ai-index.json)
- [Labs API](https://labs.santismm.com/api/labs)
- [OpenAPI](https://labs.santismm.com/openapi.json)
- [Sitemap](https://labs.santismm.com/sitemap.xml)

## Licence

Content and calculation methodologies are licensed CC BY 4.0. Attribute Santiago Santa María Morales and cite each lab's canonical URL.