Case Study

How a Tier 1 European Telecom Is Building Agentic Service Provisioning with Itential

Multi-Domain Service Orchestration, Agent-Based Provisioning, & Spec-Driven Development Across SD-WAN, IP/MPLS, and Branch Connectivity Domains

Challenge

Manual, multi-domain service provisioning across SD-WAN, IP/MPLS, and branch connectivity required deep per-controller expertise, slowed activation, and could not be safely opened to AI-driven execution without governance, audit, and human-in-the-loop controls.

Solution

Itential FlowAI and the Itential Platform provided a unified orchestration layer where the architecture team could build goal-based agents, deterministic workflows, and end-to-end multi-domain service flows – with the same governance applied to AI and human actions.

Why Itential

Chosen for the deterministic-plus-agentic execution model, native multi-controller integration, Spec-Driven Development, and platform-level governance that let agents act on real infrastructure with auditability, approval gates, and policy controls built in.

The Challenge

When Service Complexity Outpaces Manual Integration

A Tier-1 communications service provider operates across consumer, enterprise, and wholesale markets, delivering connectivity, SD-WAN, and managed services across multiple countries and customer segments.

As enterprise demand for hybrid connectivity grew, the architecture team faced a familiar problem: every new service required orchestration across multiple controller domains, each with its own API surface, service model, and operational pattern. Provisioning a single customer service often meant coordinating actions across multiple SD-WAN platforms, an IP/MPLS service orchestrator, and branch connectivity infrastructure – with manual handoffs, custom integration code, and engineer-intensive validation between each step.

The team had built strong internal automation. But scaling that automation across new services, new controllers, and new customer segments meant rebuilding integration logic each time. And as AI entered the conversation, leadership needed a way to introduce agent-driven execution without giving up the governance, traceability, and control their enterprise customers required.

Three Fault Lines Beneath the Fragmentation

Each gap blocked the path to scaled automation – and made it impossible to safely introduce AI on top.

Integration Sprawl Across Controllers

Service activation across SD-WAN, IP/MPLS, and branch connectivity required deep familiarity with each controller’s service models, API conventions, and execution patterns. Engineers had built integrations that worked – but maintaining them, extending them, and onboarding new domains required engineering bandwidth the team did not have.

AI Reasoning Without Runaway Execution

Adding agentic AI raised harder questions: how would agents know which tools to use, how would the team prevent runaway execution, and how would they audit what an agent did, who approved it, and what it changed? The team needed AI reasoning without losing the governance and predictability that made automation safe in the first place.

Tool Selection & Cost from Day One

The team was thinking past the demo: token consumption per run, which agents could be safely converted to deterministic workflows once their patterns stabilized, and how to govern what tools agents could access at build time versus runtime. A deployment readiness question, not a curiosity one.

The speed at which my team was able to build this – and how much they learned in the process – was a shock. This was one of the best POCs we have ever run.

Enterprise Connectivity Architecture Lead

Tier 1 Telecom

The team did not want another vendor demo. They wanted to build it themselves – and prove what was actually possible in their environment.

Why Itential

Why They Chose Itential

Rather than watch a vendor demo, the architecture team asked for four working days, access to the platform, and Itential’s team in a support role – not leading. Several criteria shaped the decision.

An Orchestration Foundation Built for Both Humans & AI Agents

Six capabilities sat at the center of the decision – together giving the team a governed foundation for both deterministic execution and agentic operations.

Explore the Platform

An Orchestration Foundation That Makes AI Action Safe

AI agents can only act responsibly when they have a governed, deterministic execution layer beneath them. Itential provides exactly that – well-defined, auditable workflow execution that AI can invoke reliably, with policy enforcement and access controls built in. For the team, this was not just an automation requirement. It was the prerequisite for agentic operations.

Native Multi-Controller Integration

The Itential Platform integrated with multiple SD-WAN controllers, the IP/MPLS service orchestrator, and branch connectivity infrastructure through native API ingestion – with the same integration model exposed as tools to FlowAI agents. Agents could reason across multiple controller domains, including across competing controllers in the same domain, without custom integration code per service.

Spec-Driven Development for Domain Experts

Itential’s published Claude skills allowed architects to define agent intent in plain language, then watch the system check feasibility, design the solution, build the agent, self-test it against the live environment, and document what it learned – including its own deviations and corrections.

Platform-Level Governance Applied to Agents

Enterprise governance – RBAC, audit logging, secrets management, approval workflows, SSO – applied natively to agent execution, not bolted on after the fact. Every agent action was traceable, every change auditable, every approval recorded.

Token Consumption Visibility

The platform exposed per-step token consumption for each agent execution, giving the team the foundation to track agent cost over time, identify high-cost agents, and convert stabilized patterns to deterministic workflows when appropriate.

Human-in-the-Loop by Default

Approval gates could be inserted at any point in agent execution, with the option to route approvals through change management systems the team already used. Agents could draft, validate, and stage changes – but humans approved them.

The Solution

5 FlowAgents, 3 Controller Domains, 1 Governed Execution Layer

Over four working days – supported, not led, by the Itential team – the architecture team built five working FlowAgents, multiple deterministic workflows stitching them into end-to-end service flows, and a Spec-Driven Development build that delivered a working agent in under fifteen minutes.

End-to-End Multi-Domain Orchestration

A deterministic workflow crossed three controller domains in a single execution – IP/MPLS service activation, branch site provisioning, and SD-WAN customer creation combined into one customer service.

Goal-Based FlowAgents

Five FlowAgents spanning SD-WAN customer creation, branch site provisioning, multi-domain L3VPN activation, configuration compliance, and day-two operations – built around customer outcomes rather than per-controller tasks.

Spec-Driven Agent Generation

One architect stated intent in plain language. The system asked clarifying questions, generated a spec, validated feasibility, designed the solution, built the agent, self-tested against the API, hit a permissions error, self-corrected, and delivered a working agent – fully documented – in under fifteen minutes.

Governance Applied Equally

Per-run token consumption visibility, build-time tool selection, RBAC, audit trails, and human-in-the-loop approvals – applied to every agent and routed through the team’s existing change management process.

Itential is the vendor agnostic abstraction layer. Everything is just an API. Everything looks the same, regardless of what is underneath – and that is exactly the foundation you need before AI can act on your infrastructure.

Infrastructure Automation Lead

Tier 1 Telecom

The Outcome

From Architecture Team to Agentic Operations in Four Days

The engagement validated that agentic operations could be deployed in a production-grade telecommunications environment – without the months-long integration cycles required by traditional approaches, and without trading off the governance enterprise customers require.

5

FlowAgents Built

Spanning SD-WAN customer creation, branch site provisioning, multi-domain L3VPN activation, configuration compliance, and day-two operations.

4

Working Days

From kickoff to a working multi-domain proof of concept, built by the customer’s own architecture team.

3

Controller Domains

Crossed in a single deterministic execution combining IP/MPLS service activation, branch site provisioning, and SD-WAN customer creation.

~15m

Spec to Working Agent

From plain-language intent to a self-tested, documented FlowAgent running against the live environment.

Every Agent Action – Auditable, Approvable, Reversible

Human-in-the-loop approvals, RBAC, audit logging, and explicit build-time tool selection were applied to every agent – demonstrating that agentic operations can meet enterprise governance requirements without compromise.