Meet the team.

The Bedim Security platform runs on a roster of specialized software agents — 36 of them across seven divisions, all built on one shared chassis. Every division is on-call for exactly one thing.

Each outline lists the agent’s real callable operations. Every one of these agents passed an instantiatable, tested registry check before it appeared on this page.

Core team.

4 agents in this division.

Developer Core

Code implementation and review.

• analyze_code — Analyze code quality and complexity.
• fix_bug — Fix bug
• generate_docs — Generate docs
• implement_feature — Implement feature
• list_files — List files in a directory.
• read_file — Read a file from the project.
• review_code — Review code
• run_tests — Run tests
• write_file — Write a file to the project.

QA Core

Testing and quality assurance.

• analyze_coverage — Analyze coverage
• check_quality — Check quality
• create_test_plan — Create test plan
• execute_tests — Execute tests
• find_bugs — Find bugs
• list_files — List files
• read_file — Read file
• regression_test — Regression test
• report_bug — Report bug
• validate_feature — Validate feature
• write_file — Write file

SysAdmin Core

System administration agent for infrastructure management.

• analyze_logs — Analyze system logs for a service.
• check_service — Check or manage a system service.
• check_system — Check system
• create_incident — Create incident
• get_system_status — Get system status
• list_incidents — List incidents
• resolve_incident — Resolve incident
• run_command — Execute an allowlisted system command (safe mode — read-only diagnostics).

Lead Core

Orchestration and coordination.

• analyze_request — Analyze a request and determine which agent should handle it.
• broadcast_and_collect — Send prompt to all agents, collect responses. (async)
• create_task — Create task
• create_workflow — Create workflow
• decompose_and_parallel — Decompose a task into subtasks, run agents in parallel, merge results. (async)
• delegate_task — Delegate task
• execute_workflow — Execute workflow
• register_agent — Register an agent with the lead.
• request_approval — Request human approval for an action. (async)
• round_robin — Agents take turns in sequence responding to a prompt. (async)
• route_task — Route task
• selector — Select the best agent for a task, then delegate. (async)
• spawn_conversation — Create a sub-conversation with a group of agents.

Cyber division.

8 agents in this division.

Security Cyber

Security Agent for vulnerability scanning, incident response, and security policy enforcement.

• add_control — Add a control to a security assessment.
• create_assessment — Create a security assessment.
• create_incident — Create a new security incident.
• detect_anomalies — Detect anomalies in access logs.
• generate_secure_secret — Generate a cryptographically secure secret.
• generate_security_report — Generate a security status report.
• get_incidents — Get incidents with optional filtering.
• get_policy — Get a security policy by ID.
• get_secrets_due_for_rotation — Get secrets due for rotation within specified days.
• log_access — Log an access event for security analysis.
• register_secret — Register a secret for rotation tracking.
• rotate_secret — Rotate a secret.
• scan_code — Scan code for security vulnerabilities.
• scan_directory — Scan a directory recursively for security vulnerabilities.
• scan_file — Scan a file for security vulnerabilities.
• update_incident_status — Update incident status.
• update_policy — Update a security policy.
• validate_password — Validate password against security policy.

SecurityOperations Cyber

Security Operations Agent for SIEM integration, incident response, and threat hunting.

• add_ioc — Add indicator of compromise to incident.
• add_threat_intel — Add threat intelligence indicator.
• add_timeline_entry — Add entry to incident timeline.
• close_incident — Close an incident with full documentation.
• create_alert — Create a security alert.
• create_hunt — Create a threat hunting query.
• create_incident — Create a security incident.
• escalate_alert — Escalate alert to incident.
• execute_hunt — Execute a threat hunt and record findings.
• get_alerts — Get alerts with filtering.
• get_attack_mapping — Map incident to MITRE ATT&CK framework.
• get_hunts — Get hunts with filtering.
• get_incidents — Get incidents with filtering.
• get_soc_metrics — Get SOC operational metrics.
• get_threat_intel — Get threat intel with filtering.
• get_wazuh_metrics — Combined local+poller status, suitable for a daily report.
• ingest_wazuh_alert — Convert one Wazuh alert JSON into a SecurityAlert and add to local state.
• ingest_wazuh_alerts — Ingest a batch of Wazuh alerts.
• record_outbound_subject — Record that an incident was emailed out, so a future reply can
• report_security_incident — Report a security incident. Convenience method that maps to create_incident.
• search_threat_intel — Search threat intel by value.
• start_wazuh_poller — Build a WazuhPoller that calls ingest_wazuh_alerts on each poll.
• stop_wazuh_poller — Stop wazuh poller
• triage_alert — Triage a security alert.
• triage_inbound_email — Process one inbound email addressed to a SOC inbox (reports@).
• update_incident_status — Update incident status. Accepts IncidentStatus enum or string.

VulnerabilityManagement Cyber

Vulnerability Management Agent for scanning, tracking, and remediating security vulnerabilities.

• add_asset — Add an asset to inventory.
• add_patch — Add a patch to track.
• add_vulnerability — Add a vulnerability finding.
• complete_scan — Mark a scan as completed.
• create_scan — Create a vulnerability scan.
• deploy_patch — Simulate patch deployment.
• get_asset_risk_profile — Get risk profile for an asset.
• get_assets — Get assets with filtering.
• get_overdue_vulnerabilities — Get vulnerabilities past due date.
• get_patches — Get patches with filtering.
• get_remediation_priority — Get prioritized remediation list.
• get_scans — Get scans with filtering.
• get_vuln_metrics — Get vulnerability management metrics.
• get_vulnerabilities — Get vulnerabilities with filtering.
• update_asset_vuln_count — Update asset vulnerability count.
• update_vulnerability_status — Update vulnerability status.

RedTeam Cyber

Red Team Agent for offensive security operations, penetration testing, and adversary emulation.

• add_credential — Add discovered credential.
• add_finding — Add a security finding.
• add_service_to_target — Add service to target.
• add_target — Add a target to the engagement.
• add_target_to_engagement — Add target to engagement.
• create_attack_path — Document an attack path.
• create_engagement — Create a new engagement.
• execute_kali_full_engagement — Execute full engagement using KaliAgent playbooks.
• execute_kali_password_audit — Execute password cracking audit using KaliAgent.
• execute_kali_recon — Execute reconnaissance using KaliAgent.
• execute_kali_web_audit — Execute web application audit using KaliAgent.
• generate_engagement_report — Generate engagement report.
• get_attack_paths — Get attack paths with filtering.
• get_credentials — Get credentials with filtering.
• get_engagements — Get engagements with filtering.
• get_findings — Get findings with filtering.
• get_targets — Get targets with filtering.
• mark_finding_reported — Mark finding as reported.
• mark_target_compromised — Mark target as compromised.
• test_credential — Test if credential is valid.
• update_engagement_status — Update engagement status.

RedTeamAgentV2 Cyber

Enhanced Red Team Agent with MITRE ATT&CK v12, attack path visualization, purple team integration, and risk scoring.

• build_network_topology — Build network topology from scan results.
• calculate_engagement_risk — Calculate overall risk score for an engagement.
• create_attack_path — Create an attack path with visualization data.
• create_detection_test — Create a purple team detection test.
• execute_detection_test — Record detection test execution.
• generate_attack_path_from_findings — Automatically generate attack paths from findings.
• generate_executive_summary — Generate executive summary for an engagement.
• get_detection_coverage — Get detection coverage for an engagement.
• get_mitre_coverage — Calculate MITRE coverage for an engagement.
• get_technique — Get MITRE technique details.
• get_techniques_by_tactic — Get all techniques for a tactic.
• identify_pivot_points — Identify lateral movement pivot points.
• map_finding_to_mitre — Map a finding to MITRE ATT&CK techniques.

MalwareAnalysis Cyber

Malware Analysis Agent for reverse engineering, threat analysis, and IOC extraction.

• add_analysis_results — Add detailed analysis results.
• add_ioc — Add indicator of compromise.
• add_ioc_to_campaign — Add IOC to campaign.
• add_sample — Add malware sample for analysis.
• add_sample_to_campaign — Add sample to campaign.
• complete_analysis — Complete analysis with results.
• create_analysis — Create malware analysis.
• create_campaign — Create malware campaign.
• create_yara_rule — Create YARA rule.
• generate_ioc_report — Generate IOC report for malware family.
• get_analyses — Get analyses with filtering.
• get_analysis_summary — Get malware analysis summary.
• get_campaigns — Get campaigns with filtering.
• get_iocs — Get IOCs with filtering.
• get_sample — Get sample by ID.
• get_sample_by_hash — Get sample by hash (MD5, SHA1, or SHA256).
• get_sample_report — Generate detailed sample report.
• get_similar_samples — Find similar samples based on SSDEEP or characteristics.
• get_yara_rules — Get YARA rules with filtering.
• identify_malware_family — Identify malware family based on analysis.
• mark_ioc_false_positive — Mark IOC as false positive.
• start_analysis — Start analysis.
• update_yara_rule — Update YARA rule.

Kali Cyber

Kali Linux Tool Orchestration Agent Provides comprehensive integration with Kali Linux tools including: - 600+ penetration testing tools - Metasploit Framework automation - Safety gates and authorization controls - Automated reporting.

• add_to_blacklist — Add IP to blacklist (always blocked).
• aircrack_crack — WiFi password cracking.
• amass_enum — Subdomain enumeration with Amass.
• binwalk_analyze — Firmware analysis.
• bloodhound_collect — Active Directory reconnaissance.
• cewl_generate — Custom wordlist generator.
• check_authorization — Check if tool execution is authorized.
• clear_ip_whitelist — Clear IP whitelist.
• connect_metasploit — Connect to Metasploit RPC.
• crunch_generate — Wordlist generator.
• dirb_scan — Web content scanner.
• disable_audit_logging — Disable audit logging.
• disable_dry_run — Disable dry-run mode.
• disable_safe_mode — Disable safe mode (allows system changes).
• disconnect_metasploit — Disconnect from Metasploit RPC.
• dnsrecon_scan — DNS enumeration.
• enable_audit_logging — Enable audit logging for all executions.
• enable_dry_run — Enable dry-run mode (commands logged but not executed).
• enable_safe_mode — Enable safe mode (read-only operations).
• execute_metasploit_exploit — Execute a Metasploit exploit.
• execute_tool — Execute a Kali Linux tool.
• ffuf_fuzz — Fast web fuzzer.
• generate_playbook_report — Generate playbook execution report.
• generate_report — Generate execution report.
• get_execution_history — Get execution history with filtering.
• get_metasploit_modules — Get available Metasploit modules.
• get_metasploit_sessions — Get active Metasploit sessions.
• get_tool_info — Get detailed tool information.
• gobuster_scan — Directory/DNS brute-force with Gobuster.
• hydra_bruteforce — Brute force login with Hydra.
• john_crack — Crack passwords with John the Ripper.
• joomscan_scan — Joomla vulnerability scanner.
• medusa_bruteforce — Parallel brute forcer.
• metasploit_session_command — Execute command in Metasploit session.
• nikto_scan — Perform Nikto web server scan.
• nmap_scan — Perform Nmap network scan.
• reaver_attack — WPS brute force attack.
• remove_from_blacklist — Remove IP from blacklist.
• revoke_authorization — Revoke authorization.
• run_ad_audit_playbook — Run Active Directory audit playbook.
• run_password_audit_playbook — Run password cracking playbook.
• run_recon_playbook — Run comprehensive reconnaissance playbook.
• run_web_audit_playbook — Run web application audit playbook.
• run_wireless_audit_playbook — Run wireless security audit playbook.
• searchsploit_search — Search Exploit Database.
• set_authorization — Set authorization level for tool execution.
• set_ip_whitelist — Set IP whitelist (only these targets allowed).
• sqlmap_scan — Perform SQLMap SQL injection scan.
• subfinder_scan — Subdomain discovery.
• theharvester_scan — Email and subdomain harvesting.
• validate_target — Validate target against whitelist/blacklist.
• volatility_analyze — Memory forensics.
• wpscan_scan — WordPress security scan.

KaliAgentV2 Cyber

Enhanced KaliAgent with modern tools and intelligent features.

• check_authorization — Check if tool can be executed.
• disable_dry_run — Disable dry-run mode.
• enable_dry_run — Enable dry-run mode.
• generate_remediation_plan — Generate remediation plan for findings.
• match_exploits_for_cve — Find exploits for a CVE.
• recommend_tools_for_target — Get tool recommendations for a target.
• set_authorization — Set authorization level.

Governance.

8 agents in this division.

Legal Governance

Legal Agent for contract review, document generation, compliance checking, and risk assessment.

• add_clause_to_document — Add clause to document.
• create_document — Create a legal document.
• create_legal_matter — Create a legal matter (tracked as a legal document).
• generate_nda_template — Generate NDA template.
• generate_terms_template — Generate Terms of Service template.
• get_compliance_status — Get overall compliance status.
• get_documents — Get documents with filtering.
• get_expiring_documents — Get documents expiring within specified days.
• review_contract — Review contract for risks and issues.
• run_compliance_check — Run compliance check against regulation.
• update_document_status — Update document status.

Compliance Governance

Compliance Agent for regulatory compliance tracking, policy management, audit preparation, and risk assessment.

• add_certificate — Add a compliance certificate.
• add_regulation — Add a regulatory framework to track.
• approve_policy — Approve a policy.
• complete_audit — Complete an audit.
• create_assessment — Create a compliance assessment.
• create_audit — Create a compliance audit.
• create_control — Create a compliance control.
• create_finding — Create a compliance finding.
• create_policy — Create a policy document.
• get_audits — Get audits with filtering.
• get_compliance_report — Generate comprehensive compliance report.
• get_controls — Get controls with filtering.
• get_findings — Get findings with filtering.
• get_framework_status — Get status for a specific framework.
• get_policies — Get policies with filtering.
• get_policies_due_for_review — Get policies due for review.
• get_regulations — Get regulations with filtering.
• resolve_finding — Resolve a finding.
• start_audit — Start an audit.
• test_control — Test a control and update status.
• update_regulation_status — Update regulation compliance status based on controls.

Privacy Governance

Privacy Agent for GDPR, CCPA, and privacy regulation compliance, data subject rights, consent management, and privacy assessments.

• DataSubjectRight — Data subject rights.
• PrivacyRegulation — Privacy regulations.
• ProcessingPurpose — Data processing purposes.
• add_processing_activity — Add a processing activity (Record of Processing Activities).
• add_risk_to_pia — Add identified risk to PIA.
• approve_pia — Approve a PIA.
• check_valid_consent — Check if valid consent exists for a purpose.
• close_breach — Close a breach with full documentation.
• contain_breach — Mark breach as contained.
• create_data_request — Create a data subject request with flexible interface.
• create_pia — Create a Privacy Impact Assessment.
• create_request — Create a data subject rights request.
• fulfill_access_request — Fulfill an access request with data export.
• fulfill_erasure_request — Fulfill an erasure (deletion) request.
• get_breaches — Get breaches with filtering.
• get_compliance_report — Generate privacy compliance report.
• get_consents — Get consent records with filtering.
• get_data_subject — Get data subject by ID.
• get_data_subjects — Get data subjects with filtering.
• get_pias — Get PIAs with filtering.
• get_processing_activities — Get processing activities with filtering.
• get_regulation_compliance — Get compliance status for a specific regulation.
• get_requests — Get requests with filtering.
• notify_authority — Record authority notification.
• record_consent — Record consent given.
• register_data_subject — Register a data subject.
• register_processing_activity — Alias for add_processing_activity with more flexible interface.
• report_breach — Report a data breach.
• update_request_status — Update request status.
• verify_data_subject — Verify data subject identity.
• verify_request — Verify a request (identity verification complete).
• withdraw_consent — Withdraw consent.

Risk Governance

Risk Agent for Enterprise Risk Management (ERM), risk registers, KRIs, and risk reporting.

• assess_risk — Assess risk with controls consideration.
• complete_assessment — Complete a risk assessment.
• create_assessment — Create a risk assessment.
• create_control — Create a risk control.
• create_kri — Create a Key Risk Indicator.
• get_assessments — Get assessments with filtering.
• get_controls — Get controls with filtering.
• get_events — Get events with filtering.
• get_high_priority_risks — Get high priority risks sorted by score.
• get_kris — Get KRIs with filtering.
• get_kris_at_risk — Get KRIs in yellow or red status.
• get_risk_appetite_status — Get risk appetite compliance status.
• get_risk_dashboard — Generate risk dashboard summary.
• get_risk_register — Generate risk register report.
• get_risks — Get risks with filtering.
• identify_risk — Identify a new risk.
• plan_treatment — Plan risk treatment.
• report_event — Report a risk event/incident.
• resolve_event — Resolve a risk event.
• test_control — Test control effectiveness.
• update_kri_value — Update KRI value and calculate status.
• update_risk_status — Update risk status.

Ethics Governance

Ethics Agent for AI ethics review, bias detection, fairness assessment, and explainability tracking.

• add_explainability_record — Add explainability record.
• add_finding — Add finding to ethics assessment.
• complete_assessment — Complete ethics assessment.
• configure_oversight — Configure human oversight for a model.
• create_ethics_assessment — Create ethics assessment for a model.
• create_remediation_plan — Create remediation plan for bias.
• detect_bias — Record detected bias.
• generate_fairness_report — Generate fairness metrics report.
• get_bias_assessments — Get bias assessments with filtering.
• get_ethics_report — Generate comprehensive ethics report.
• get_explainability — Get explainability records for a model.
• get_fairness_reports — Get fairness reports with filtering.
• get_incidents — Get incidents with filtering.
• get_model_ethics_profile — Get comprehensive ethics profile for a model.
• get_models — Get models with filtering.
• get_oversight_config — Get oversight configuration for a model.
• mark_bias_mitigated — Mark bias as mitigated.
• register_model — Register an AI model for ethics oversight.
• report_incident — Report ethical incident.
• resolve_incident — Resolve ethical incident.
• update_model_risk — Update model risk level.

SupplyChain Governance

Supply Chain Agent for SBOM management, dependency tracking, vendor risk assessment, and supply chain security.

• add_package — Add package to inventory.
• add_vendor — Add vendor to registry.
• add_vulnerability — Add vulnerability for a package.
• analyze_sbom — Analyze SBOM for vulnerabilities.
• calculate_vendor_risk — Calculate vendor risk score.
• complete_assessment — Complete vendor assessment.
• create_assessment — Create vendor assessment.
• create_sbom — Create SBOM for a project.
• get_assessments — Get assessments with filtering.
• get_dependency_tree — Get dependency tree for a package.
• get_incidents — Get incidents with filtering.
• get_packages — Get packages with filtering.
• get_sboms — Get SBOMs with filtering.
• get_supply_chain_report — Generate supply chain security report.
• get_vendor_risk_report — Get vendor risk report.
• get_vendors — Get vendors with filtering.
• get_vulnerabilities — Get vulnerabilities with filtering.
• report_incident — Report supply chain security incident.
• resolve_incident — Resolve security incident.
• update_vulnerability_status — Update vulnerability status.

Audit Governance

Audit Agent for internal audit planning, control testing, evidence collection, and audit reporting.

• add_control — Add control for testing.
• collect_evidence — Collect audit evidence.
• complete_audit — Complete audit.
• create_audit — Create audit engagement.
• create_finding — Create audit finding.
• create_workpaper — Create audit workpaper.
• generate_audit_report — Generate audit report.
• get_audit_dashboard — Generate audit dashboard.
• get_audits — Get audits with filtering.
• get_controls — Get controls with filtering.
• get_evidence — Get evidence with filtering.
• get_findings — Get findings with filtering.
• review_evidence — Mark evidence as reviewed.
• review_workpaper — Review workpaper.
• start_audit — Start audit fieldwork.
• test_control — Test control and record results.
• update_audit_status — Update audit status.
• update_finding — Update finding details.
• update_finding_status — Update finding status.

VendorRisk Governance

Vendor Risk Agent for third-party risk management, assessments, SIG questionnaires, and continuous monitoring.

• acknowledge_alert — Acknowledge alert.
• add_vendor — Add vendor to registry.
• complete_assessment — Complete assessment.
• create_alert — Create vendor risk alert.
• create_assessment — Create vendor risk assessment.
• create_finding — Create assessment finding.
• create_questionnaire — Create vendor questionnaire.
• enable_monitoring — Enable continuous monitoring for vendor.
• get_alerts — Get alerts with filtering.
• get_assessments — Get assessments with filtering.
• get_findings — Get findings with filtering.
• get_monitors — Get monitors with filtering.
• get_questionnaires — Get questionnaires with filtering.
• get_vendor_risk_dashboard — Generate vendor risk dashboard.
• get_vendor_risk_report — Generate vendor risk report.
• get_vendors — Get vendors with filtering.
• get_vendors_due_for_assessment — Get vendors due for assessment within specified days.
• record_monitoring_result — Record monitoring check result.
• resolve_alert — Resolve alert.
• respond_to_question — Record question response.
• send_questionnaire — Send questionnaire to vendor.
• start_assessment — Start assessment.
• update_finding — Update finding details.
• update_finding_status — Update finding status.
• update_vendor_risk — Update vendor residual risk.

Operations.

6 agents in this division.

DevOps Operations

DevOps Agent for infrastructure automation, CI/CD, deployment orchestration, and monitoring.

• acknowledge_alert — Acknowledge an alert.
• check_thresholds — Check metrics against thresholds and create alerts.
• create_alert — Create a monitoring alert.
• create_deployment — Create a new deployment.
• create_pipeline — Create a new CI/CD pipeline.
• create_task — Create a DevOps task.
• get_active_alerts — Get active (unresolved) alerts.
• get_cost_report — Generate cost optimization report.
• get_deployments — Get deployments with filtering.
• get_infrastructure_summary — Get infrastructure summary.
• get_pipelines — Get pipelines with filtering.
• get_resource_costs — Calculate resource costs for time period.
• record_metric — Record a metric data point.
• register_resource — Register an infrastructure resource.
• resolve_alert — Resolve an alert.
• rollback_deployment — Rollback deployment to previous version.
• run_command — Execute a command on a target.
• start_pipeline — Start a queued pipeline.
• update_deployment_status — Update deployment status.
• update_pipeline_stage — Update pipeline stage status.
• update_resource_status — Update resource status.

Support Operations

Support Agent for ticket management, auto-responses, knowledge base, and customer satisfaction tracking.

• add_knowledge_article — Add a new knowledge base article.
• add_message — Add a message to a ticket.
• check_sla_breaches — Check for SLA breaches.
• create_ticket — Create a new support ticket.
• get_auto_response — Get auto-response for ticket based on category.
• get_support_metrics — Get support metrics report.
• get_tickets — Get tickets with filtering.
• rate_article — Rate a knowledge base article.
• record_satisfaction — Record customer satisfaction score.
• resolve_ticket — Resolve a ticket.
• search_knowledge_base — Search knowledge base articles.
• update_ticket_status — Update ticket status.

Integration Operations

Integration Agent for API connections, webhooks, data synchronization, and cross-platform automation.

• create_connection — Create a new API connection.
• create_sync_job — Create a data synchronization job.
• create_webhook — Create a new webhook.
• get_connections — Get connections with filtering.
• get_integration_health — Get overall integration health summary.
• get_logs — Get integration logs.
• get_sync_jobs — Get sync jobs with filtering.
• get_webhooks — Get webhooks with filtering.
• pause_webhook — Pause a webhook.
• remove_connection — Remove a connection.
• run_sync_job — Execute a sync job.
• test_connection — Test API connection.
• trigger_webhook — Trigger a webhook.
• update_connection_status — Update connection status.

Communications Operations

Communications Agent for multi-channel messaging, campaign management, and delivery tracking.

• add_contact — Add a contact.
• complete_campaign — Complete a campaign.
• create_campaign — Create a communication campaign.
• create_template — Create a message template.
• get_campaign_performance — Get campaign performance metrics.
• get_campaigns — Get campaigns with filtering.
• get_channel_health — Get channel health status.
• get_contacts — Get contacts with filtering.
• get_delivery_stats — Get delivery statistics.
• get_messages — Get messages with filtering.
• get_templates — Get templates with filtering.
• render_template — Render a template with values.
• schedule_message — Schedule a message for later delivery.
• send_email — Send an email (convenience method wrapping send_message).
• start_campaign — Start a campaign.
• update_campaign_metrics — Update campaign metrics.
• update_message_status — Update message delivery status.
• update_preferences — Update contact communication preferences.

CloudSecurity Operations

Cloud Security Agent for CSPM, compliance checking, misconfiguration detection, and remediation.

• add_account — Add cloud account for monitoring.
• add_resource — Add cloud resource for monitoring.
• check_resource_compliance — Check resource against policies.
• create_finding — Create security finding.
• create_policy — Create custom security policy.
• create_remediation — Create remediation action.
• execute_remediation — Mark remediation as executed.
• get_account_risk_profile — Get risk profile for a cloud account.
• get_accounts — Get accounts with filtering.
• get_cloud_security_report — Generate cloud security report.
• get_compliance_score — Calculate compliance score for a framework.
• get_findings — Get findings with filtering.
• get_policies — Get policies with filtering.
• get_resources — Get resources with filtering.
• update_account_scan — Update account scan results.
• update_finding_status — Update finding status.

ChaosMonkey Operations

Chaos Monkey Agent for chaos engineering experiments, failure injection, and resiliency testing. Inspired by Netflix Chaos Monkey - randomly terminates instances and injects failures to build resilient systems.

• AbortCondition — Conditions that trigger experiment abort.
• ExperimentType — Chaos experiment types.
• TargetType — Target types for chaos experiments.
• abort_experiment — Abort chaos experiment.
• add_blackout_window — Add blackout window.
• add_metric_threshold — Add metric threshold for abort conditions.
• add_safety_constraint — Add safety constraint.
• assign_targets — Assign targets to experiment.
• calculate_resiliency_score — Calculate resiliency score for a service.
• check_metric_thresholds — Check if any metric thresholds are breached.
• complete_experiment — Complete chaos experiment.
• create_experiment — Create chaos engineering experiment.
• execute_latency_injection — Execute latency injection.
• execute_termination — Execute instance termination.
• get_chaos_dashboard — Generate chaos engineering dashboard.
• get_experiment_report — Generate experiment report.
• get_experiments — Get experiments with filtering.
• get_targets — Get targets with filtering.
• register_target — Register a target for chaos experiments.
• schedule_experiment — Schedule experiment for execution.
• select_random_targets — Randomly select targets for chaos experiment.
• start_experiment — Start chaos experiment.

Data and ML.

4 agents in this division.

Research Data

Research Agent for literature review, research synthesis, citation management, and knowledge discovery.

• add_citation — Add a citation between publications.
• add_finding — Add finding to project.
• add_publication — Add a publication to the library.
• add_publication_to_project — Add publication to project.
• add_topic — Add a research topic.
• create_project — Create a research project.
• find_related_publications — Find publications related to a given publication.
• format_citation — Format citation in specified style.
• generate_literature_review — Generate literature review for a topic.
• get_citations_by — Get all citations made by a publication.
• get_citations_for — Get all citations for a publication.
• get_project — Get project by ID.
• get_projects — Get projects with filtering.
• get_publications — Get publications with filtering.
• get_topic_summary — Get summary for a topic.
• search_publications — Search publications by title, abstract, or keywords.
• update_citation_count — Update citation count for a publication.
• update_project_status — Update project status.

DataAnalyst Data

Data Analyst Agent for statistical analysis, insights, trend detection, and automated reporting.

• calculate_statistics — Calculate descriptive statistics for a column.
• detect_anomalies — Detect anomalies using z-score method.
• detect_correlations — Detect correlation between two columns.
• detect_trends — Detect trends in time-series data.
• generate_insights — Generate automated insights for a dataset.
• generate_report — Generate a comprehensive analysis report.
• get_report — Get a report by ID.
• load_data — Load data into cache for analysis.
• register_dataset — Register a dataset for analysis.

DataGovernance Data

Data Governance Agent for data classification, retention, lineage tracking, quality monitoring, and access management.

• add_lineage — Add data lineage record.
• approve_access — Approve access request.
• classify_data — Auto-classify data based on content keywords.
• create_quality_rule — Create data quality rule.
• create_retention_policy — Create retention policy.
• deny_access — Deny access request.
• execute_quality_check — Execute quality check and record result.
• get_access_requests — Get access requests with filtering.
• get_assets — Get assets with filtering.
• get_assets_due_for_action — Get assets due for retention action.
• get_compliance_summary — Get compliance summary for regulated data.
• get_governance_report — Generate data governance report.
• get_lineage — Get data lineage for an asset.
• get_quality_issues — Get quality issues with filtering.
• get_quality_score — Calculate overall quality score for an asset.
• get_retention_period — Get retention period for an asset.
• register_asset — Register a data asset.
• request_access — Request access to data asset.
• resolve_quality_issue — Resolve a quality issue.
• revoke_access — Revoke approved access.
• update_asset_metrics — Update asset metrics.
• update_lineage_status — Update lineage execution status.

MLOps Data

MLOps Agent for ML lifecycle management, experiment tracking, deployment, and monitoring.

• check_model_metrics — Check metrics against thresholds and create alerts.
• complete_experiment — Complete experiment with results.
• create_alert — Create model alert.
• create_experiment — Create ML experiment.
• create_monitor — Create model monitor.
• deploy_model — Deploy model to environment.
• get_alerts — Get alerts with filtering.
• get_datasets — Get datasets with filtering.
• get_deployments — Get deployments with filtering.
• get_experiments — Get experiments with filtering.
• get_mlops_dashboard — Generate MLOps dashboard.
• get_model_performance — Get model performance report.
• get_models — Get models with filtering.
• register_dataset — Register a dataset.
• register_model — Register model in registry.
• resolve_alert — Resolve alert.
• start_experiment — Start experiment.
• update_deployment_status — Update deployment status.
• update_model_stage — Update model stage.

Business.

5 agents in this division.

Sales BusinessNew

Sales agent: CRM, BANT/ICP qualification, productized price book, quotes, proposals, pipeline forecasting, and draft-only outbound. Human-supervised; never sends anything unaided.

• create_lead — Create a lead. Lead creation records only this agent's fields.
• create_opportunity — Create an opportunity linked to a lead, with a valid pipeline stage.
• draft_outreach — Draft (never send) a personalized outreach email for a lead.
• forecast — Weighted pipeline grouped by close quarter (undated ops bucketed separately).
• generate_proposal — Generate a full markdown proposal for an opportunity.
• get_lead — Fetch one lead's summary by id or email.
• lead_summary — Flat dict view of a lead for results and reports.
• pipeline_report — Owner-facing pipeline snapshot: stages, weighted totals, quotes, leads.
• price_book — Return the productized price book (single source, owner-tunable).
• qualify_lead — Qualify a lead: BANT scoring (0-25 per pillar) + ICP bonus.
• quote — Build a quote from the price book: line items + MRR + year-1 total.
• update_pipeline — Move an opportunity to a validated stage; probability follows the table.

Finance Business

Finance agent for transaction, budget, and invoice management.

• analyze_spending — Analyze spending
• create_budget — Create budget
• create_invoice — Create invoice
• generate_report — Generate report
• record_transaction — Record transaction

HR Business

HR Agent for employee management, onboarding, performance reviews, and time-off tracking.

• approve_time_off — Approve time off request.
• complete_onboarding_task — Mark onboarding task as complete.
• create_onboarding — Create onboarding checklist for new employee.
• create_review — Create performance review.
• get_employee — Get employee by ID.
• get_employees — Get employees with filtering.
• get_hr_metrics — Get HR metrics summary.
• get_onboarding_progress — Get onboarding progress for employee.
• get_reviews — Get reviews with filtering.
• get_time_off_requests — Get time off requests with filtering.
• hire_employee — Hire a new employee.
• reject_time_off — Reject time off request.
• request_time_off — Request time off.
• submit_review — Submit completed review.
• terminate_employee — Terminate an employee.
• update_employee — Update employee information.

Marketing Business

Marketing Agent for campaign management, content creation, social media, A/B testing, and analytics.

• complete_ab_test — Complete A/B test with results.
• create_ab_test — Create A/B test.
• create_campaign — Create a new marketing campaign.
• create_content — Create content piece.
• generate_blog_titles — Generate blog title variations.
• generate_email_subjects — Generate email subject line variations.
• generate_social_posts — Generate social media post variations.
• get_ab_tests — Get A/B tests with filtering.
• get_analytics_summary — Get analytics summary.
• get_campaigns — Get campaigns with filtering.
• publish_content — Publish content.
• schedule_social_post — Schedule a social media post.
• track_analytics — Track marketing analytics.
• track_campaign_metrics — Track campaign performance metrics.
• update_campaign_status — Update campaign status.

SocialMedia BusinessNew

Social media agent: calendars, drafts, engagement, listening, metrics. Draft-only by construction: see module docstring for the hard rules.

• brand_check — Pre-flight any draft text: banned claims, unsourced numbers,
• content_calendar — Plan calendar slots for the window: weekly cadence, weekdays only.
• crisis_note — Hold-rules and template language during an active incident.
• draft_post — Draft one generic post (draft-only; the owner sends it).
• engagement_draft — Draft (never send) a reply to a social mention.
• listen_report — Roll up owner-fed mentions: tone split, keywords, spike, unanswered.
• mark_published — Record that the OWNER posted this draft (data entry, not an action).
• mark_status — Record an owner decision on a draft (approve/hand-off/archive).
• metrics_report — KPI rollup over owner-entered per-post outcomes.
• post_queue — The owner's work list: all drafts grouped by status.
• repurpose — Turn a newsroom article into platform-native DRAFTS of one story.
• week_summary — Owner-facing snapshot: queue, published week, overdue slots, mentions.

Specialist.

1 agents in this division.

BiblicalScholar Specialized

Biblical Scholar Agent for religious text analysis, comparative religion studies, and theological research.

• add_text — Add a religious text to the database.
• analyze_quote — Analyze a religious quote for meaning, source, and significance.
• compare_concept — Compare how a concept is understood across religions.
• get_comparative_study — Get comparative study by ID.
• get_quote_analysis — Get quote analysis by ID.
• get_random_text — Get a random religious text.
• get_research — Get research query by ID.
• get_text — Get text by ID.
• get_texts_by_religion — Get all texts for a specific religion.
• get_texts_by_type — Get all texts of a specific type.
• research_question — Research a theological or biblical question.
• search_texts — Search texts by content, title, or keywords.

Every agent above shares one chassis — a base protocol covering permissions, tools, guardrails (PII filtering, content policy, tool allowlists), memory, reasoning, and transparency logs.