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
Screen entities against consolidated watchlists including OFAC SDN, EU sanctions, UN consolidated list, and domestic law enforcement databases. Supports batch and real-time modes.
Set up incoming webhook endpoints with payload validation, transformation, and routing to internal workflows.
Design and deploy an automated multi-step workflow with triggers (schedule, event, API), conditional branching, approvals, and notifications.
Auto-generate structured audit workpapers from testing procedures. Pre-populates with objectives, scope, methodology, sample details, and findings templates.
Generate explainable AI analysis for a model prediction. Produces SHAP values, LIME explanations, counterfactuals, and plain-English narratives.
Evaluate zero trust architecture maturity across 5 pillars -- identity, device, network, application, and data with maturity scoring and roadmap generation.
Working productivity agent. Summarizes supplied email text, assesses potential priority, and drafts a handling recommendation; it does not read or route a mailbox.
Working productivity agent. Searches approved knowledge and drafts email copy from supplied context; sending remains outside this template.
Working productivity agent. Turns supplied meeting context into a concise pre-read; it does not read calendars, CRM records, or message threads automatically.
Working productivity agent. Summarizes a supplied transcript and drafts structured notes; it does not create tasks or distribute notes.
Working productivity agent. Summarizes supplied commitment context and drafts a follow-up; it does not track replies, send nudges, or schedule reminders.
Working productivity agent. Drafts scheduling language from availability supplied in the request; it does not read or write calendars.
Builder template for an on-demand data brief. Connect and verify a governed tenant data source before use; the built-in query tool currently returns demonstration data only.
Working productivity agent. Searches approved Cortex knowledge, summarizes supplied findings, and drafts a research brief; it does not browse the public web.
Working productivity agent. Searches approved knowledge and turns supplied context into an executive brief; it does not delegate agents or manage a calendar or inbox.
Working supplied-context agent. Searches approved support knowledge and drafts a response or escalation recommendation; it does not update tickets.
Builder template for CRM enrichment, next-action analysis, and follow-up drafting. Connect and verify a supported CRM before use; the current CRM tools do not query a live system.
Builder template for order lookup and response drafting. Connect and verify a supported commerce system before use; the current record lookup returns demonstration data only.
Working supplied-context agent. Summarizes supplied account context, assesses potential risk, and drafts outreach; it does not monitor accounts or send messages.
Working supplied-context agent. Triages supplied incident context, searches approved guidance, and drafts a response; it does not run remediation or provision access.
Working supplied-context agent. Searches approved HR knowledge, summarizes supplied context, and drafts a policy-grounded response; it does not create or route cases.
Builder template for finance record queries and exception briefs. Connect and verify a governed finance data source before use; current lookup and query tools return demonstration data.
Working supplied-context agent. Summarizes supplied legal context, checks a proposed response against policy, and drafts an intake brief; it does not create or route matters.
Builder template for vendor lookup and procurement briefs. Connect and verify a supported procurement system before use; current record lookup returns demonstration data only.
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.