Use Case Intelligence RSS Search use cases Search
Google Cloud Telecommunications Finland

Nokia

IT Operations Automation

Today's telecom networks generate massive volumes of complex data. Traditionally, managing this has been a highly manual process, with operators spending hours digging through minor alert logs to find the root cause of network issues.

Read the original story Explore all use cases
A central router agent acts as the orchestrator, flawlessly managing communication between the different agents and network tools.
Driven by a surge in autonomous machines and AI agents, machine-to-machine communication is creating unpredictable traffic patterns that are much more uplink-heavy than traditional networks.
Finally, at the agent level, Nokia utilized the Google Cloud Agent Development Kit and the Gemini Enterprise to integrate a dynamic ecosystem of six specialized AI agents into the Assurance Center.
Slashes troubleshooting times by 50% to 80%, resolving complex network issues in minutes instead of hours

Reported impact

Business outcome

Using Google's Agent Development Kit and the Gemini Enterprise, we have seen a 50% to 80% time reduction in problem-solving, essentially cutting time from hours into mere minutes.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

At the infrastructure level, Nokia built its foundations on Google Cloud. By moving workloads to standard compute and storage-specifically Google Kubernetes Engine and Cloud Storage-Nokia broke down historical data silos. This provides operators with a single, unified view across their highly complex multi-cloud, multi-vendor, and multi-domain environments, crucially eliminating the need to "rip and replace" their existing infrastructure investments. Finally, at the agent level, Nokia utilized the Google Cloud Agent Development Kit and the Gemini Enterprise to integrate a dynamic ecosystem of six specialized AI agents into the Assurance Center. Each agent plays a specific, coordinated role in troubleshooting. An event triage agent instantly analyzes incoming network alarms, cutting through massive volumes of background noise to isolate actual critical infrastructure threats.

Solution architecture

5 components · 3 layers
  1. Compute
    • Google Kubernetes Engine (GKE) Runs containerized or virtualized application workloads with the elasticity needed for production scale.
    • Google Kubernetes Engine Runs containerized or virtualized application workloads with the elasticity needed for production scale.
  2. Storage
    • Cloud Storage Stores source documents, media, or raw files that feed the automated workflow.
  3. Orchestration
    • Gemini Enterprise Provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis.
    • Agent Development Kit (ADK) Coordinates multi-agent workflows, tool calling, and governed automation across the application.

Architecture clues

  • Automating troubleshooting with multi-agent AI
  • By transitioning from rigid, manual workflows to this advanced multi-agent workflow, Nokia is delivering massive operational efficiency to its customers.

Evidence from the source

At the infrastructure level, Nokia built its foundations on Google Cloud. By moving workloads to standard compute and storage-specifically Google Kubernetes Engine and Cloud Storage-Nokia broke down historical data silos
Finally, at the agent level, Nokia utilized the Google Cloud Agent Development Kit and the Gemini Enterprise to integrate a dynamic ecosystem of six specialized AI agents into the Assurance Center. Each agent plays a spe
Nokia builds autonomous networks and cuts troubleshooting time by 50-80% with Gemini Enterprise
Nokia uses Gemini Enterprise to automate network troubleshooting, cutting problem-solving time by up to 80%.
Using Google's Agent Development Kit and the Gemini Enterprise, we have seen a 50% to 80% time reduction in problem-solving, essentially cutting time from hours into mere minutes.
Transparency Evidence & methodology 80/100 reference value · 77% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value80/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth15/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence77%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Google Cloud

    Nokia customer story

    First-party
    https://cloud.google.com/customers/nokia-gemini-enterprise
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Oct 2, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Sep 25, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Google Cloud Modified · Oct 8, 2026 Ericsson Telecommunications Sweden Telecom operators today face a rapid influx of artificial intelligence, orchestration, and automation tools. But converting these technologies into real business value is a constant challenge. To prove the business case… Accelerates and lowers the cost of launching new network services IT Operations Automation Gemini platform Google Cloud Feb 25, 2026 Deutsche Telekom Telecommunications Germany Deutsche Telekom needed to move network operations beyond fragmented, reactive troubleshooting so it could predict, diagnose, and resolve service-impacting issues across RAN, transport, and core domains before customers… Only 5 sites experienced peak loads IT Operations Automation A2A (Agent-to-Agent) protocol · Google Cloud Autonomous Network Operations framework · Google Gemini models Google Cloud Nov 11, 2025 Deutsche Telekom Telecommunications Germany Deutsche Telekom needed a faster way to detect, classify, and resolve mobile network issues around demand spikes and other exceptional situations because growing network complexity made traditional automation… Processes that previously took roughly an hour can now be completed within just a few minutes. IT Operations AutomationReal-time Analytics BigQuery · CloudRun · Firestore