Itential
Also known as: Itential Platform, FlowAI, Itential MCP Server, Itential Automation Platform
Agentic orchestration platform for network and infrastructure operations where AI reasons and proposes but never touches infrastructure directly. Every human, workflow or agent action executes through one governed engine with RBAC, approval gates, blast radius limits, validation, rollback and immutable audit trails.
Itential is an orchestration platform for network and infrastructure operations. AI reasoning plans and decides, but AI never touches infrastructure directly. Every change (whether a person, a workflow, an ITSM ticket or an AI agent initiates it) flows through the same governed execution engine with role based access control, approval gates, blast radius limits, pre and post validation, rollback and immutable audit trails. It is used by Lumen, Southern California Edison, US federal agencies, global carriers and financial services firms.
The agentic layer is FlowAI. FlowAgent Builder creates role based agents from natural language descriptions with defined reasoning styles and toolsets. The Itential MCP Server exposes governed automations as tools any LLM can discover and invoke, and the FlowMCP Gateway calls outward to external MCP servers such as NetBox and Selector to enrich a running task. Underneath sits a deterministic Workflow Engine that executes predefined logic identically every time, with no token cost, at 10 tasks per second on the Scale tier, 50 on Enterprise and no limit on Custom. Spec-Driven Development converts a proven agent session into exactly that kind of workflow without a rebuild.
Customers choose their own model. Anthropic, OpenAI, Google, Mistral, Ollama, Azure OpenAI and AWS Bedrock are supported, with provider keys held in profiles that are write only, and Itential offers a bundled model only on its two entry tiers. Work Center gives operators a human in the loop queue for approvals, and the customer sets the autonomy level.
The platform keeps no copy of customer data and federates a live view across systems of record instead. It runs as managed SaaS, or self managed on premises, in a private cloud or in a public cloud the customer controls, with data and execution remaining in the customer's environment. Validated designs cover high availability and disaster recovery across regions. Itential holds SOC 2 Type II, supports SSO through OpenID Connect or SAML, and publishes a trust center. Pricing is by tier on agent runs and workflow throughput, never by device, node or seat.
Vendor details
Canonical URL
https://www.itential.com
Category
SRE / DevOps agent
Subcategory
Agentic network and infrastructure orchestration
Funding status
Independent, headquartered in Atlanta, Georgia, co-founded in 2014 by CTO Chris Wade to accelerate network automation adoption, with its most recent Crunchbase-listed funding a convertible note. Itential reports that some of the world's largest networks run on its platform, with named customers including Southern California Edison and quantified outcomes such as enterprise activation dropping from forty five days to under one.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Integrations span ITSM (ServiceNow, Jira), infrastructure as code (Ansible, Terraform, OpenTofu), CI/CD (GitHub, Jenkins), observability (Datadog, Splunk), AIOps (Selector, Forward Networks), secrets and vault systems, cloud providers (AWS, Azure) and multi vendor network estates (Cisco, Juniper, Arista, Palo Alto, VMware). The Itential Gateway executes Python, Ansible and OpenTofu directly against infrastructure with secure multi vendor connectivity. The ServiceNow App, published in the ServiceNow App Store, pushes governed automations into the customer's ServiceNow catalog as native Flow steps. The Itential MCP Server exposes governed workflows as tools any LLM can discover and invoke, the FlowMCP Gateway calls outward to external MCP servers such as NetBox and Selector, and the FlowMCP Server manages multiple MCP instances centrally. Developer documentation lives at docs.itential.com, alongside public GitHub and GitLab organizations and an AWS Marketplace listing.
In practice
An AIOps platform such as Selector detects a network anomaly. The detection starts a governed remediation workflow through Itential's event triggers, the workflow validates the fix against policy before applying it, and the loop closes back through the same governed path.
A network team wants agents without giving AI the keys. Itential starts agents read only against infrastructure state, then progressively grants write access through approval gates and blast radius limits as trust builds.
An engineer troubleshooting a BGP flap kicks off a workflow that pulls device and cloud logs, calls an LLM partway through to pinpoint the misconfigured peer, validates the suggested fix against policy, and applies it through the governed engine.
Sources & related URLs
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool Calling | Full |
|---|---|
|
Itential's integrations cover ITSM (ServiceNow, Jira), infrastructure as code (Ansible, Terraform, OpenTofu), CI/CD (GitHub, Jenkins), observability (Datadog, Splunk), AIOps (Selector, Forward Networks), and security and vault systems, alongside cloud providers (AWS, Azure) and multi vendor network estates (Cisco, Juniper, Arista, Palo Alto, VMware). The Itential Gateway runs Python scripts, Ansible playbooks, OpenTofu and Terraform plans, and AI initiated actions directly against the customer's infrastructure with secure multi vendor connectivity, taking authenticated action inside systems and devices Itential does not own. The ServiceNow App, published in the ServiceNow App Store, pushes governed Itential automations into the customer's ServiceNow catalog as native Flow steps, so Itential's actions run inside ServiceNow as first class objects. Existing Ansible, Python and OpenTofu assets become governed services without rewriting. The architecture page says the platform unifies 300+ integrations into a single orchestration fabric, while the pricing and platform pages describe 1,000+ open source integrations in the Itential Marketplace; these are likely different scopes, governed prebuilt connectors and the open community library, though the pages do not say so. Sourceitential.com/cloud-platform/architecture, /pricing and /marketplaceread 2026-09-08 |
|
| Workflow Orchestration | Full |
|
The Workflow Engine runs pre-defined logic identically every time at a published throughput, 10 tasks per second started on Scale, 50 on Enterprise and no limit on Custom, while FlowAgents combine LLM reasoning with governed tools to solve a goal described in natural language and are metered in agent sessions. Workflow Studio is the authoring surface, a drag and drop builder with versioning and testing that needs no scripting, and Lifecycle Manager runs multi-day sequences with explicit state and full rollback across the resource lifecycle from provisioning to retirement. Workflows are published as microservices through an open API to northbound systems and AI agents, so a change can start from a person in the Operations Manager self service portal, an ITSM ticket in ServiceNow, a CI/CD pipeline, an AIOps detection or an external LLM through MCP, and the same governed path carries it out across network, cloud, security and IT infrastructure. Stateful orchestration tracks services with resource models that detect drift and automate lifecycle changes. Together these form a deterministic orchestration engine with a reasoning layer on top. Sourceitential.com/pricing and /cloud-platform/architectureread 2026-09-08 |
|
| Knowledge Grounding & RAG | Partial |
|
Agents work from a live, federated view of the customer's systems. Federation and Unified Data Models create a unified view of resources across disparate systems, so agents and workflows operate on normalized data models, and Data Transformation converts diverse formats into common JSON that people and agents can read across multi vendor environments. The FlowMCP Gateway lets agents call external MCP tools, NetBox, Selector and Forward Networks, for enrichment during execution, and Configuration Manager adds golden templates and compliance plans as a stored reference state. Itential does not create copies of data, so the customer's systems of record stay the source of truth, and there is no maintained index, graph or embeddings layer over the customer's knowledge, with context assembled for each run. Sourceitential.com/cloud-platform/architecture and /cloud-platform/flowairead 2026-09-08 |
|
| Human Oversight & Guardrails | Full |
|
Work Center, a human-in-the-loop task queue for operators, ships on every pricing tier and handles approvals and inputs when agents and workflows need a person. Approval gates, blast radius limits, pre and post validation checks and rollback apply equally to AI-triggered and human-initiated changes. AI never touches infrastructure directly, since agents observe state, analyze conditions and propose actions, every change flows through the orchestration engine with policy enforcement, and agent proposed automations pass validation, testing and approval before production deployment. The customer sets how much autonomy agents get, from human in the loop to human on the loop, adoption can start read only, and RBAC sits alongside. Sourceitential.com/cloud-platform/architecture and /pricingread 2026-09-08 |
|
| Security, Identity & Governance | Full |
|
SOC 2 Type II, covering security, availability, confidentiality and processing integrity, appears on all five pricing tiers, GDPR and CCPA compliance is stated, and a Trust Center is published at itential.com/trust-center, linked from the Company menu and the site footer. Access runs through single sign on (SSO) via OpenID Connect or SAML, with programmatic identity for AI agents, RBAC and GBAC, granular permissions, secrets management, approval workflows for all infrastructure changes, and encryption in transit and at rest. RBAC policies apply the same way to human users and AI agents, the MCP Server authenticates by user or agent identity, and platform policy decides which caller may run what. An immutable audit trail and on premises or customer controlled deployment add to this. Sourceitential.com/cloud-platform/architecture, /pricing and /trust-centerread 2026-09-08 |
|
| Observability & Auditability | Full |
|
Audit trails are immutable on every pricing tier, audit evidence is captured on every change, and every action can be traced back to the AI intent that started it, so a reviewer can see which agent request caused a change as well as what happened. The MCP Server receives, validates and translates every request before anything touches infrastructure, applying RBAC, OAuth and audit logging automatically, so the agent's request and the resulting execution are captured together. Output, telemetry and result state are captured per task. Insights adds activity dashboards and SLA metrics on FlowAgent and workflow activity, performance and ROI from the Scale tier up, while the audit trail ships on all five tiers. Sourceitential.com/cloud-platform/architecture, /pricing and /cloud-platform/itential-mcp-serverread 2026-09-08 |
|
| Memory & State Persistence | Not documented |
|
Lifecycle Manager runs multi-day sequences with explicit state and full rollback, and stateful orchestration tracks infrastructure services with AI enhanced resource models that detect drift and automate changes from provisioning through retirement. That state is the orchestration's position in a running sequence and the resource model of the customer's infrastructure, so deleting it deletes the service record. Itential defines an agent run as one full instance of the agent executing its instructions, including all reasoning and tool usage, ending in a result, and nothing carries across to the next run. Itential also does not create copies of data, and there is no memory scope, lifetime, retention or deletion control over agent memory, or taught preference store carried between sessions. Sourceitential.com/pricing and /cloud-platform/architectureread 2026-09-08 |
|
| Deployment & Data Residency | Full |
|
Itential runs on premises, in a private cloud or in a customer-controlled public cloud, with data and execution remaining in the customer's environment, and also offers a self managed option for organizations with regulatory or internal security requirements, alongside a fully managed SaaS offering. Itential Validated Designs cover single server high availability, active/standby with full component redundancy that tolerates a catastrophic failure, and blue/green multi region disaster recovery, with a developer architecture marked as unsuitable for production. The Enterprise tier adds a 99.9% availability SLA and custom VPN connectivity, a dedicated private network path into regulated environments. Itential gives national governments and industry regulators placing controls on where customer data is physically located as the reason for these options. All of this concerns where Itential itself runs, separate from the hybrid and multi cloud infrastructure it orchestrates. Sourceitential.com/cloud-platform/architecture and /pricingread 2026-09-08 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
The Itential Marketplace, at itential.com/marketplace, is an open source library of API integrations and pre-built skills, agents and workflows, and customers can contribute their own. It is unlimited and never metered on all five pricing tiers, with a community forum alongside and public GitHub and GitLab organizations behind it. FlowAgent Builder creates governed, purpose built agents from natural language descriptions with defined personas, scopes and toolsets, and Itential Builder Skills and Spec-Driven Development generate automation from intent and turn a proven agent session into a deterministic workflow without a rebuild. Golden workflow patterns and Configuration Manager golden templates supply reusable starting points, and the ServiceNow App publishes governed automations into the customer's ServiceNow catalog. Sourceitential.com/pricing, /marketplace and /itential-builder-skillsread 2026-09-08 |
|
| Triggers & Channel Coverage | Full |
|
Event Triggers and Closed-Loop Automation connects FlowAI agents to observability and AIOps platforms for event driven orchestration with autonomous remediation and human in the loop governance, so a Selector, Forward Networks, Datadog or Splunk detection starts a workflow with no operator, and the loop closes back through the same governed path. ITSM tickets in ServiceNow and Jira resolve through integration, with the ServiceNow App embedding Itential actions as native Flow steps, and CI/CD pipelines in GitHub and Jenkins trigger builds and deployments. The Operations Manager self service portal lets NOC, operations and service desk staff launch and monitor automation without developer access, and external LLMs invoke platform workflows as governed tools through the MCP Server. Infrastructure actions can be triggered by people, automation systems or intelligent agents, through workflows published as microservices on an open API. Lifecycle Manager adds sequences that run over multiple days. Sourceitential.com/cloud-platform/architecture and /pricingread 2026-09-08 |
|
| Model Flexibility & Routing | Full |
|
The pricing matrix has an LLM provider row listing Anthropic, OpenAI, Google, Azure, Bedrock and Ollama, with the option to bring your own model or use Itential's. With a customer provided LLM, the customer configures a compatible provider on an account it controls and pays for, among them Anthropic, OpenAI, Google, Mistral, Ollama, Azure OpenAI and AWS Bedrock. With the Itential provided option, available only on Essentials and Compliance, Itential includes Anthropic as a turnkey part of the subscription, while Scale, Enterprise and Custom require a customer supplied model. Provider API keys are managed through LLM provider profiles and are write only once saved, masked in the UI and never returned through the API or export. Any LLM, SLM or open weight model is supported, including a custom one, and Ollama gives a self hosted open weight option. Sourceitential.com/pricing and /cloud-platform/flowairead 2026-09-08 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Extensions run in both directions. Inbound, the Itential MCP Server exposes governed automation as tools any LLM can discover and invoke through the same policy enforced engine, receiving, validating and translating every request between AI systems and the platform, and the FlowMCP Server is its enterprise form, managing multiple MCP instances centrally through virtual MCP servers with persona based access control and multiuser authentication. Outbound, the FlowMCP Gateway invokes external MCP tools. A developer documentation site at docs.itential.com carries release notes, and an open API publishes workflows as microservices to northbound systems. Every API already integrated with Itential is an agent tool without a new MCP server, every self service catalog item is registered as an MCP tool automatically, and internal APIs and automation endpoints can be registered as tools. Public GitHub and GitLab organizations, an Itential MCP product page, Builder Skills, native git connecting the customer's own repos, a community marketplace and an AWS Marketplace listing procurable against committed AWS spend sit around it. Sourceitential.com/cloud-platform/itential-mcp-server, docs.itential.com and /cloud-platform/flowairead 2026-09-08 |
|
| Testing, Debugging & Optimization | Full |
|
Workflow Studio, its own line on the pricing matrix from the Scale tier, is a drag and drop builder with versioning and testing for designing and testing workflows on a visual low code canvas. All agent proposed automations pass validation, testing and approval before production deployment, and human review plus guardrails keep anything but validated, compliant workflows out of live environments. Spec-Driven Development converts a proven agent session into a deterministic workflow, so a session that has been exercised becomes the artifact that ships. Testing covers the workflow artifact and shows the customer pass or fail against its own logic. No scored result, holdout, benchmark or drift score is published. Pre and post validation with audit evidence and rollback on each change checks that a change installed correctly, and Insights activity dashboards track live operations. Sourceitential.com/pricing and /cloud-platform/architectureread 2026-09-08 |
|
| Browser & Computer Use | Not documented |
|
The agent reaches infrastructure programmatically. The Itential Gateway runs Python scripts, Ansible playbooks and OpenTofu plans against devices and cloud estates over API and CLI with secure multi vendor connectivity, and every other path, MCP, the northbound open API, ITSM and CI/CD, is programmatic. Itential has no hosted or local browser, desktop session or remote or local computer control, and nothing navigates, clicks, fills or advances anything through an interface built for a person. Terminal and shell access work over machine protocols, so changes to a rendered interface do not affect an SSH session to a router or a Terraform plan. Sourceitential.com/cloud-platform/architecture and /pricingread 2026-09-08 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Itential AI Skills is an open source set of skill packs that lets teams build, run and administer the Itential Platform from Claude Code, Codex CLI, GitHub Copilot and Cursor through plain language requests. Builder Skills creates workflows, FlowAgents and other platform assets, Operator Skills runs and troubleshoots jobs and works on manual tasks awaiting a decision, and Admin Skills manages users, roles, SSO and integrations built from an OpenAPI specification.
Bears on: MCP / tool calling / API
View sourceEvent Auditing, new in Itential Platform 6.6, is an immutable audit trail that records who performed an action, what they changed and when, and actions taken by FlowAI agents are written to the same trail as actions taken by users. It ships in 6.6.1, released October 15 to replace the 6.6.0 build, which is no longer available. The release also sends web server logs to Grafana over OpenTelemetry, and its changelog adds audit logging for authorization, service and Studio resources.
Bears on: Security / enterprise
View sourceItential launched Agentic Builder Skills on the Anthropic Claude Marketplace, bringing spec-driven development to infrastructure automation. The plugin connects Claude Code to the Itential Platform, providing 13 skills and 5 agents that translate natural-language requirements into deterministic, production-ready workflows and FlowAgents.
Bears on: MCP / tool calling / API
View sourcePricing
Quote only
Agent runs. Each tier carries a monthly allowance of agent runs, the higher tiers add Workflow Engine throughput, and users are unlimited at every tier, with no device, node, server or per seat licensing.
What is public
The packaging is complete, with no figures. Five named cloud tiers are listed with quantified limits. Essentials includes 5,000 agent runs a month and Compliance 10,000, while Scale, Enterprise and Custom carry unlimited runs, with Workflow Engine throughput published as 10 tasks per second started on Scale, 50 on Enterprise and no limit on Custom. A side by side comparison table sets out which applications ship at each tier. Essentials includes FlowAI, Operations Manager, Work Center, Itential Gateway, ServiceNow App, Spec-Driven Development, Marketplace and Security and Governance. Compliance adds Configuration Manager, Scale adds Workflow Studio, Workflow Engine and Insights, and Enterprise adds Lifecycle Manager, HA architecture with a 99.9% SLA and custom VPN connectivity. The pricing principles are explicit. There is no device, node, server or per seat licensing, users are unlimited at every tier, FlowAI is core rather than a paid extra, and pricing is set by adoption measured in agent runs and throughput. Subscription terms run one, two, three or five years. On premises FlowAI is a separate purchase licensed per production server with no monthly run limit, and the platform is procurable through AWS Marketplace against committed AWS spend.
Billing mechanics
A tiered subscription sold through sales, on terms of one, two, three or five years. The tier is set by agent runs and Workflow Engine throughput, not by devices, nodes, servers or seats, and no rates are published. Interactive product tours and an automation value calculator support evaluation.
Cost watchouts
Expanding across domains, adding integrations, and scaling FlowAI agents and MCP instances raise cost as far as they push agent runs or throughput into a higher tier, since devices, nodes and seats are not licensed. From Scale upward the LLM is customer supplied, so model spend moves onto the customer's own provider account.
Variable cost rationale
Agent runs are metered, where one run is one full agent session, and the allowance is small at the entry tiers, 5,000 runs a month on Essentials and 10,000 on Compliance. Use tracks how much reasoning work the platform is asked to do rather than the size of the estate, and devices, nodes and seats are not licensed. Going past a tier's runs moves the account to the next tier rather than billing overage. The tier structure bounds the bill, since runs are unlimited from Scale. Converting proven agent sessions into deterministic workflows, which carry no token charge, moves mature processes off the metered path. LLM token cost sits on the customer's own provider account at Scale and above, outside the subscription entirely.
Additional watchouts
Itential defines the metered agent session as one full instance of an agent executing its instructions, including all reasoning and tool usage. Reasoning heavy agents therefore consume the allowance faster than simple ones. Essentials includes only 5,000 runs a month and Compliance 10,000, and exceeding either triggers a tier upgrade rather than an overage, a cliff rather than a gradient. The mitigation is architectural. The Workflow Engine runs deterministic logic 10x to 1,000x faster than an agent with no token charges, and Spec-Driven Development converts a proven agent session into a workflow, so mature processes can be moved off the metered path. The Itential provided LLM is available only on Essentials and Compliance. Scale, Enterprise and Custom require a customer supplied model, so LLM spend moves onto the customer's own provider account at exactly the point volume grows.
Sales call required
Yes, required for paid access
Free / trial
None published
Lowest paid plan
Not published
Key ambiguities
Every structural term is published and every number in dollars is not, which is an unusual combination. A customer can work out exactly which tier it needs but cannot estimate what it costs. The overage rule is also unusually blunt. Exceeding monthly agent runs is not billed as overage but forces a move to the next tier, and Itential does not sell additional runs on top of a tier, so the cost curve is a staircase rather than a slope, with no published step heights.
Missing data
All monetary figures. No price, band, minimum or per tier fee is published for any of the five cloud tiers, and on premises FlowAI is licensed per production server with no published rate. Professional services and Itential Academy lab environments are optional, with no published cost. The step between tiers is undefined in money, which matters more here than usual because exceeding agent runs forces a tier move rather than an overage charge.
Related vendors
- AlertD — AI agents for AWS operations that run read only in the customer's…
- Anyshift — AI SRE built on a versioned knowledge graph of infrastructure, apps…
- Avesha — Obliq, Avesha's autonomous AI SRE for Kubernetes and agentic…
- Better Stack — Better Stack offers incident management with built in on call,…
- Bluebricks — Context and control layer that lets AI agents operate cloud…
- Cased — AI workflows for infrastructure and platform engineers: default and…
Alternatives to Itential
The closest documented capability profiles to Itential among SRE and DevOps agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Fabrix.ai12.5 / 14Adds documented Memory & State Persistence
- Komodor13.0 / 14Adds documented Memory & State Persistence
- NeuBird11.0 / 14Adds documented Memory & State Persistence
- Doctor Droid11.5 / 14Adds documented Memory & State Persistence
- Kubiya11.5 / 14Adds documented Memory & State Persistence
- NudgeBee11.5 / 14Adds documented Memory & State Persistence
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded