91福利

Skip to the main content.

PLEXA Core 2.0 Intelligence Layer.

 
AI agents plan, make decisions
and control processes autonomously, 24/7.
Rendering_intelligence-1
//AGENT-DRIVEN AUTOMATION
//FROM IDEA TO MOTION
//PHYSICAL AI INSIDE
//NO PROGRAMMING. JUST RESULTS.
//PROMPT TO PRODUCE
//AI YOU CAN TRUST
| PleXA CORE 2.0

The layer on which agents work together.

In the Intelligence Layer, specialized agents that have been trained with data from thousands of real-world applications work together.

Using VLA (Vision-Language-Action) models, they process real-world input (Vision and sensor data) and user input (Language) to plan sequences and make decisions. Thanks to the seamless integration of the Intelligence Layer into the horstOS robot operating system, the agents can not only derive decisions but also immediately translate them into actions and control the robot in the real-world environment (Action).

This is how Physical AI becomes a reality. The agents react in real time to changing conditions and enable truly simple and flexible automation, without requiring any expert knowledge.

| AUTOMATION AGENTS

Each agent is an expert.

Specialized agents take over the planning, implementation and operation of your application. Depending on the task at hand, the appropriate agents are specifically approached to provide their input and contribute to the optimum result.

All agents always operate within clearly defined roles, permissions, and approvals, ensuring that you, as the user, never lose control over your processes.
Agents-10
AGENT

Project Creation

Creates setups from voice and image input.

Learn more
Agents-09
AGENT

Logic
Builder

Creates and optimizes robot logic and programs.

Learn more
Agents-08
AGENT

Safety &
Error Handling

Monitors operation and prevents errors.

Learn more
Agents-07
AGENT

Operation & Support

Supports users with their questions.

Learn more
Agents-11-1
AGENT

Supervising & Execution

Coordinates agents and controls the
robot.

Learn more

| PROJECT CREATION AGENT

Project setups created in seconds

The Project Creation Agent generates automation concepts based on inputs such as process descriptions, CAD data, or images. This enables the feasibility of an automation request to be assessed in a very short time and a suitable concept to be provided.
Agents_individual-12-1

| Logic Builder Agent

Program logic at the touch of a button

The Logic Builder Agent creates program sequences based on described process objectives or specified videos. During operation, it continuously optimizes the processes and adapts them to changing conditions.
agents_individual-13-1

| Safety & Error Handling Agent

Everything in view at all times

The Safety & Monitoring Agent acts as an independent safety instance and monitors the entire operation in real time. It detects potential risks such as collisions or impending failures at an early stage, before they occur. If problems occur, it analyses the cause and provides troubleshooting assistance to minimize downtimes.
Agents_individual-15

| operation & support agent

Always by your side

The Operations & Support Agent supports ongoing operations through the targeted adaptation of programs and the continuous optimization of processes. It also supports users as an active assistant, answers questions, provides recommendations for action and helps to ensure that robots are used efficiently and smoothly.

agents_individual-14-1

| Supervising & execution agent

Everything under control

The Supervising & Execution Agent is the central coordinator in the intelligence layer. It monitors and orchestrates all specialized agents, continuously processes their input and compares it with the data from vision and sensors from the real world. On this basis, it derives specific actions in real time and translates them directly into control commands. It is the agent that actually moves the robot in the real world.
Agents_individual-16


91福利
Macairestra脽e 3
78467 Konstanz

+49 (0) 7531 976 240


Contact

      Subscribe to our Newsletter

      @ 2026 91福利