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
Map detection coverage against MITRE ATT&CK matrix -- identify unmonitored techniques, prioritize detection development, test existing rules, and generate coverage heatmap.
Full audit engagement lifecycle: planning, fieldwork, testing, findings, reporting, and follow-up tracking.
QA review of completed audit engagements: methodology compliance, documentation quality, finding accuracy, report quality.
Set up and execute continuous audit monitoring: automated tests, exception detection, trend analysis, and alert management.
Design testing procedures for key controls based on control objectives, assertion mapping, and risk assessment. Produces detailed test scripts with expected results.
Execute structured audit fieldwork by performing walkthroughs, testing controls, documenting observations, and collecting evidence per the audit program.
Document detailed process narratives from walkthrough interviews including key activities, control points, system interfaces, and segregation of duties analysis.
Perform root cause analysis on audit findings using structured techniques (5 Whys, fishbone, fault tree). Distinguishes symptoms from underlying causes and recommends systemic fixes.
Refine IBNR estimates using development factor selection and tail analysis. Evaluates alternative factor selections, tail extrapolation methods, and their impact on carried reserves.
Review user access rights, privileged accounts, dormant accounts, excessive permissions, and separation of duty violations.
Multi-system data sync: conflict resolution, transformation, validation, rollback, audit trail, and monitoring.
Real-time event streaming: event schema, producers, consumers, dead letter queue, monitoring, and replay capability.
Production-grade REST connector: auth flows, pagination, rate limiting, error handling, retry, data mapping, and monitoring.
Execute IFRS 17 transition calculations including CSM determination, risk adjustment calibration, and fulfilment cash flow projections under the general measurement model.
Build automated data import pipeline with file parsing, validation, transformation, and error handling.
Launches a full incident response workflow: creates IR case, assigns responders, selects playbook, initiates NIST phases (Detection, Containment, Eradication, Recovery), and notifies stakeholders.
Conduct structured root cause analysis on operational risk incidents using 5-Why, fishbone, and fault tree methods. Links findings to control improvements and lessons learned.
Structured root cause analysis of GRC incidents using 5-Why, Fishbone, and fault tree methods.
Create and automate operational runbooks for common AI incidents including model degradation, endpoint failures, cost overruns, and data pipeline breaks.
Analyzes incident details using Cortex AI patterns, classifies priority (P1-P4), identifies affected service, and routes to the optimal assignment group with SLA tracking.
Compare your data quality, pipeline performance, and governance maturity against industry benchmarks from your domain pack.
Analyze your datasets and automatically discover trends, anomalies, correlations, and actionable insights with AI-powered analysis.
Create a reusable API connector with authentication, rate limiting, error handling, and data mapping.
Risk-based audit planning: assess audit universe, score risk, allocate resources, build annual plan.
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.