5,814 agentes preconstruidos y 15,654 habilidades de biblioteca en 24 sectores y 12 roles por sector, instalables desde el catálogo, conectados a tus sistemas y ejecutados a través de la misma cadena de puertas de fallo cerrado que todo lo demás en Cortex.
21,511 plantillas de biblioteca en la matriz del catálogo
Suites creadas a mano para los trabajos que las empresas automatizan primero — cada colección se entrega gobernada, con políticas y auditoría incorporadas.
Busca entre 21,500+ habilidades y agentes gobernados, o filtra por sector y tipo: cada resultado se instala desde el catálogo y pasa por las mismas puertas.
21.386 resultados
Comprehensive handler performance analytics engine. Generates individual and team scorecards across 12 KPIs, identifies coaching opportunities, benchmarks against industry standards, and produces development plans.
Compute VaR, Expected Shortfall, Greeks, and GARCH volatility for a trading portfolio. Supports parametric, historical, and Monte Carlo approaches.
Construct a double-materiality matrix mapping ESG topics by financial impact and stakeholder importance. Identifies priority issues for disclosure and strategy.
Coordinate Independent Medical Examination workflow. Selects appropriate physician specialty, schedules examination, prepares focused clinical questions, tracks completion, analyzes IME findings vs treating physician, and generates medical opinion synthesis.
Coordinate medical peer review for complex clinical questions. Selects specialist reviewer, prepares structured case summary, manages review timeline, analyzes peer opinion, integrates with claim evidence, and generates clinical determination report.
AI-powered review of medical records for claims adjudication. Identifies pre-existing conditions, treatment timelines, disability assessments, and coverage-relevant diagnoses.
Design and orchestrate end-to-end ML pipelines from data ingestion through training, validation, and deployment with DAG-based dependency management and retry logic.
Provision and configure MLOps infrastructure including experiment tracking servers, model registries, feature stores, and serving endpoints with IaC templates.
Apply model compression techniques including quantization, pruning, knowledge distillation, and ONNX conversion to reduce model size and inference latency.
Assess model governance framework compliance with SR 11-7, SS1/23, and internal policies. Reviews approval workflows, change management, and ongoing monitoring processes.
Maintain the enterprise model inventory with lifecycle tracking. Manages model registration, tiering, ownership, validation status, and retirement across all risk models.
Analyze model lift, discrimination, and stability metrics. Evaluates predictive model performance using Gini, AUC, lift curves, and population stability index over time.
Build comprehensive model monitoring dashboards tracking prediction quality, data drift, latency, throughput, and cost metrics with automated alerting and anomaly detection.
Continuously monitor model performance using discrimination, calibration, and stability metrics. Detects model drift, concept drift, and triggers revalidation when thresholds are breached.
Manage the centralized model registry including versioning, lifecycle transitions, metadata tagging, and deprecation workflows for all production models.
Trigger and orchestrate actuarial model runs across reserving, pricing, and capital models. Manages dependencies, validates inputs, and tracks completion.
Deploy a registered model to the serving infrastructure with canary rollout, health checks, auto-scaling configuration, and rollback on failure.
Run model validation computing AUROC, Gini, Hosmer-Lemeshow calibration, PSI stability, and Brier accuracy. Produces SR 11-7 compliant validation report.
Execute independent model validation covering conceptual soundness, implementation testing, and outcome analysis. Produces validation findings and MRA/MRIA ratings.
Assess modern slavery and forced labor risk across the supply chain. Maps high-risk geographies, sectors, and labor practices against Modern Slavery Act requirements.
Calibrate mortality/morbidity models against industry tables with adjustments. Fits parametric and non-parametric models to company experience with credibility blending to standard tables.
Update mortality/morbidity tables based on experience study results. Applies graduation, scaling factors, and improvement scales to produce updated basis tables.
Design multi-agent architectures with role assignment, communication protocols, shared memory, and conflict resolution strategies for complex task decomposition.
Evaluate organizational net-zero commitments against current emissions trajectory. Identifies gaps in targets, interim milestones, and credibility of offset strategies.
Los agentes de la biblioteca no son scripts: son identidades gobernadas. Instalar uno lo registra con un propietario, un presupuesto, modelos y acciones permitidos y un lugar en el registro de auditoría.
Filtra por tu industria y tu rol; cada elemento indica los sistemas a los que se conecta y las habilidades que invoca.
Conectores, servidores MCP e importaciones OpenAPI — acotados por listas de permitidos y DLP en el gateway.
Identidad, presupuesto, guardrails, registro, Control Tower, ejecución, guarda de salida — y luego un recibo firmado en el Trust Ledger. En todos los planes.
El constructor visual de habilidades permite lanzar nuevas habilidades sin código — o dinos qué te falta y te señalaremos el patrón gobernado más cercano.