FlowAI overview
FlowAI is the agentic layer of Itential Platform, connecting AI reasoning to deterministic, governed infrastructure automation. It introduces a set of purpose-built applications and services that let you design, deploy, and monitor FlowAgents that reason through complex goals and take action through Itential’s existing automation assets, producing structured, auditable outcomes without sacrificing the operational control your team relies on.
Why use FlowAI?
FlowAI closes the gap between AI capabilities and production-grade infrastructure operations.
Governed agentic automation
FlowAgents are constrained to tools explicitly authorized by you at design time. Every action is auditable, every tool call is logged, and agents operate within the same role-based access control model that governs the rest of Itential Platform.
Hybrid execution model
FlowAI supports a strategy where agentic (reasoned) and deterministic (scripted) automation coexist in a single execution flow. FlowAgents can call workflows, workflows can invoke agents through a Run Agent task in Studio, and agents can call other agents as tools. This enables composable agent architectures where specialized agents handle specific subtasks, allowing you to adopt AI incrementally without replacing existing automation.
Purpose-built surfaces for each persona
Each role has a dedicated interface with appropriate access controls:
- Builders define agents in FlowAgent Builder.
- Operators monitor and manage runtime behavior in FlowAgent Sessions.
- LLM Admins govern model availability through LLM Provider Profiles.
MCP connectivity
FlowMCP Gateway extends Itential Automation Gateway (IAG) to connect external MCP servers and surface their tools natively in the Platform, bringing external AI ecosystems and automation frameworks under Itential’s governance model.
Core components
FlowAI is made up of several integrated components that span design, administration, and runtime.
FlowAgent Builder
The design-time application for creating and configuring FlowAgents. You define each agent’s purpose, instructions, LLM model, and tool access, specifying which workflows, adapter and integration APIs, Gateway services, Lifecycle Manager actions, Compliance Plans, and other agents the FlowAgent can invoke. FlowAgent Builder also enforces a readiness gate that must pass before an agent can accept sessions.
FlowAgent Projects
Organizational containers that group related agents and their tool associations. FlowAgent Projects establish the security boundary for agent tool access and enforce role-based access control at the project level using Owner, Editor, and Viewer roles. Projects are the unit of portability for export and import of agent configurations across environments.
FlowAgent Sessions
The runtime monitoring surface for Operators. It provides a chronological execution trace for each agent run, including reasoning steps, tool calls, and any child sessions or jobs the agent invoked. You can pause, resume, and cancel sessions, and navigate linked child executions from a unified view.
FlowMCP Gateway
An extension of IAG 5 that connects registered external MCP servers, automatically discovers their tools, and exposes those tools to Itential Platform through Gateway Manager as native Gateway services. MCP-backed tools participate in the same RBAC model and invocation patterns as all other Gateway services.
FlowModel Providers
A configuration that defines which third-party LLM(s) is used for FlowAI agent reasoning. LLM Admins configure one or more Provider Profiles per environment, selecting a provider, enabling specific models, and controlling which builder groups have access. On-prem deployments use customer-supplied credentials; cloud deployments select from Itential’s Managed provider catalog.
How FlowAI fits into Itential Platform
FlowAI builds on and interoperates with the rest of Itential Platform rather than replacing it. FlowAgents draw from a broad tool catalog at runtime, including:
- Platform workflows
- Adapter and integration APIs
- Gateway services (which include Python and Ansible-based services)
- Lifecycle Manager actions
- Compliance Plans
- Other agents
Operations Manager is where you create agent triggers, using Agent as an automation type alongside Workflows. All existing trigger types (manual, schedule, API, and event) are available for agent automations, and access control is managed at the automation level consistent with how workflow triggers are governed. Gateway Manager and IAG handle tool execution at runtime, meaning every agent action flows through the same proven infrastructure that powers all Platform automation.
Itential also provides the Itential MCP Server, which works in the opposite direction, exposing Platform capabilities (including workflows, device management, and Gateway services) to external AI assistants such as Claude and GPT. Where FlowMCP Gateway brings external MCP tools into Platform for FlowAgents to use, the Itential MCP Server allows external AI tools to call into Platform directly. For more information, see the Itential MCP Server repository.
Common use cases
Intelligent troubleshooting and remediation: Deploy FlowAgents that reason through observed network conditions, evaluate remediation options, and invoke the appropriate workflows, APIs, or services to resolve issues without requiring manual escalation at every decision point.
Adaptive provisioning: Use FlowAgents to interpret high-level provisioning requests, determine the correct configuration sequence based on current infrastructure state, and orchestrate the resulting workflows end-to-end.
Multi-agent orchestration: Build ecosystems of specialized FlowAgents that collaborate and delegate based on domain expertise. A diagnostic agent can assess infrastructure state and hand off to a remediation agent, which then invokes the right workflows, APIs, or services to execute the fix. FlowAgents can also be embedded as a step in Studio workflows when a specific decision requires reasoning, with control returning to the workflow for deterministic follow-through.
Extending automation with external intelligence: Use FlowMCP Gateway to incorporate tools from external MCP servers, such as AIOps platforms or domain-specific data sources, directly into Platform workflows and agent tool sets.
Demos and resources
See FlowAI in action with hands-on demonstrations:
- Building and running your first FlowAgent – Watch a step-by-step demo of creating an agent that automates AWS VPC provisioning, allocates subnets from Infoblox IPAM, and sends Slack notifications.
- Agent-enabled server patch readiness with Ansible + FlowAI – See FlowAgents orchestrate patch readiness checks across your infrastructure.
- AI-driven lifecycle management for infrastructure provisioning – Learn how FlowAI combines agent reasoning with deterministic provisioning workflows.
- Agentic network operations with NetBox + Itential FlowAI – Explore how FlowAgents use MCP servers to sync infrastructure state and enforce governance.