5,814 agents prêts à l'emploi et 15,654 compétences de bibliothèque couvrant 24 secteurs et 12 métiers par secteur — installables depuis le catalogue, connectés à vos systèmes et exécutés à travers la même chaîne de contrôles en échec fermé que tout le reste sur Cortex.
21,511 modèles de bibliothèque dans la matrice du catalogue
Des suites conçues à la main pour les tâches que les entreprises automatisent en premier — chaque collection est livrée gouvernée, politiques et audit inclus.
Recherchez parmi 21,500+ compétences et agents gouvernés, ou filtrez par secteur et par type : chaque résultat s'installe depuis le catalogue et franchit les mêmes points de contrôle.
21 386 résultats
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.
Les agents de la bibliothèque ne sont pas des scripts — ce sont des identités gouvernées. En installer un l'enregistre avec un propriétaire, un budget, des modèles et des actions autorisés, et une place dans le registre d'audit.
Filtrez par secteur et par rôle ; chaque élément indique les systèmes auxquels il se connecte et les compétences qu'il invoque.
Connecteurs, serveurs MCP et imports OpenAPI — cadrés par des listes d'autorisation et le DLP au niveau de la passerelle.
Identité, budget, garde-fous, registre, Control Tower, exécution, garde-fou de sortie — puis un reçu signé dans le Trust Ledger. Sur toutes les formules.
Le générateur visuel de compétences livre de nouvelles compétences sans code — ou dites-nous ce qui manque et nous vous orienterons vers le modèle gouverné le plus proche.