Skip to content
    Flow-alerta.cab

    Edge AI

    AI fundamentals & modelsDecentralised AIOn-Device AIAI on terminals
    Editorially reviewed on: 1 source
    Your reading view

    The short answer · 17 words

    In short

    Execution of AI algorithms directly on local devices or sensors instead of in central cloud data centers.

    Flow-alerta.cab (2026): Edge AI. https://flow-alerta.cab/en/glossar/edge-ai. Editorially reviewed on: 10 October 2026.

    How much detail would you like?

    Practical

    Relevant in response time, connectivity and local processing requirements.

    Hypothetical example: A local camera checks screws for visible defects without transmitting each image for cloud evaluation.

    Local image inspection, sensor evaluation and assistance in industrial plants.

    At a glance

    Core
    Models perform inference on devices or servers near the data source. This can reduce transmission times and data traffic. Offline operation requires locally available models and dependencies; security follows from the entire implementation.
    Use
    Relevant in response time, connectivity and local processing requirements.
    Example
    Hypothetical example: A local camera checks screws for visible defects without transmitting each image for cloud evaluation.
    Limits
    Limited on-site computing and storage capacity of hardware; elaborate distribution of model updates (fleet management).

    In context

    Edge Computing

    Decentralized data processing at the logical edge of the network close to the data source instead of in the central data center.

    Questions about this term

    Does Edge AI need special models?

    Not mandatory; limited hardware may require compression or quantization.

    Does Edge AI work without the Internet?

    Locally configured inference can run offline; updates or other functions may require network connections.

    All details and background

    Models perform inference on devices or servers near the data source. This can reduce transmission times and data traffic. Offline operation requires locally available models and dependencies; security follows from the entire implementation.

    ELI5 – Explained simply

    The AI works directly in the device on site, for example in a robot that performs suitable tasks with a locally available model.

    Why it matters in practice

    Relevant in response time, connectivity and local processing requirements.

    Example

    Hypothetical example: A local camera checks screws for visible defects without transmitting each image for cloud evaluation.

    Pitfalls and limits

    • Limited on-site computing and storage capacity of hardware; elaborate distribution of model updates (fleet management).

    Origin & history

    Edge AI combines on-premises data processing with AI inference; tools such as AWS IoT Greengrass support cloud training and on-premises model deployment.

    Use in mid-sized companies

    • Local image inspection, sensor evaluation and assistance in industrial plants.

    Related terms

    Matching Flow-alerta service

    AI opportunity analysis & roadmapAI consulting: Examine the suitability, data and prerequisites of a possible use case on the topic of “AI on local devices (Edge AI)”.

    Matching tool / use case

    View use casesUse Case: Local image classification / Tool example: AWS IoT Greengrass with TensorFlow-Lite components

    Sources

    Quellenprüfung: 10.10.2026. Definition und dokumentierte Einordnung abgeglichen; Beispiele beschreiben mögliche Anwendungen.

    Editorially reviewed on:

    Next step

    Put knowledge into practice

    Discuss your projectView use cases