# Welcome to AMESA ## What is AMESA? AMESA is a platform for building, training, and deploying **multi-agent AI systems** that optimize physical and industrial processes. At its core, AMESA connects data, simulations, agents, training infrastructure, and runtime environments into a cohesive system that turns real-world domain knowledge into autonomous behavior. The architecture below provides an overview of how the AMESA platform works:

*** ### 🧩 Platform Overview #### 1. **Import Data to Build Simulations** AMESA supports two ways to generate simulations: * Upload **historical industrial data** (CSV format) to generate data-driven simulations automatically. * **Connect an existing simulation**, such as a physics model or emulator, using a Docker container. These simulations provide a safe environment for skill agents to learn and be evaluated. *** **2. Create Skill Agents in the No-Code UI** In the **Agent Orchestration Studio**, you can create skill agents without writing code by defining: * **Goals** – what the agent is trying to achieve (e.g., maximize throughput, maintain temperature) * **Constraints** – rules the agent must follow (e.g., stay within safe operating bounds) * **Success Criteria** – signals that the agent is performing correctly This no-code method allows domain experts to encode their expertise directly into agent logic. #### 3. **Import Skill Agents and ML Models** You can bring in your own logic and models using the **Agent Import API**. Examples include: * Python-based MPC and PID controllers * LLM-powered agents * Custom applications and heuristics * Pretrained ML models Once imported, these skill agents are available in the **Agent Orchestration Studio**—a no-code interface for assembling agents into a multi-agent system. *** #### 3. **Design Multi-Agent Systems** Use the **Agent Orchestration Studio** to visually compose and coordinate skill agents, perceptors, and orchestrators. This is where domain experts design system-level behavior using drag-and-drop components. *** #### 4. **Train Agents with AMESA’s AI Engine** Once orchestrated, your multi-agent system connects to AMESA’s **AI Training Engine**, which leverages scalable infrastructure—such as Microsoft Azure or AWS Kubernetes clusters—to train and evaluate agents in simulation. Training uses a reward-driven learning process that improves agent performance over time. *** #### 5. **Export to Runtime and Edge Environments** Once trained, agents can be **exported for deployment**: * Into real-world production environments * To external **Edge IoT platforms** * Or into downstream runtime applications that need to embed intelligence This closes the loop from simulation to action—turning data into autonomy at scale. *** ### Why AMESA? By unifying simulation, orchestration, training, and deployment into a single platform, AMESA enables teams to: * Reduce time to deploy autonomous agents * Leverage existing models, data, and controls * Combine rule-based, learned, and ML-driven behavior * Bridge the gap between operational expertise and AI *** ## Quick Links Find articles on key topics with these links. ### Try Out a Tutorial


Industrial Mixer	Build four agent systems for a realistic use case with step by step instructions		tanks.jpg	industrial-mixer

### Import Agents and ML-Models to AMESA You can use any model, API, or Python algorithm with AMESA for training agent systems, adding perception, analysis, and communication, and making decisions. See how to configure different types of modules in the UI and by publishing them via the data science workflow for agent system design, training, and deployment.


Create a data-driven simulation	Use your historical dada and our no-code simulation tool to create a data-driven simulation.	data-driven-simulation
Integrate a machine learning model	Use existing ML models for machine vision, prediction, or analysis in AMESA agent systems	configure-an-ml-model-as-a-perceptor
Integrate a language model	Set up an LLM call to add communication to your agent system	configure-an-llm-model-as-a-perceptor
Integrate a programmed algorithm	Configure any Python algorithm, such as a PID controller or optimization algorithm, as a skill agent in AMESA	configure-programmed-algorithms-as-skills
Integrate third-party software	Use an API call to external software as a skill agent in AMESA	configure-api-connections-to-third-party-software-as-skills
Integrate a simulator	Configure your simulator to work with AMESA	connect-a-simulator-to-amesa
Publish to the platform	Upload configured models and algorithms to the AMESA UI with one CLI command	import-agent-components-to-the-ui

### Create Modular Skill Agents AMESA multi-agent systems are built on modular skills that break down a task into separate parts. Learn how to create skill agents to train with deep reinforcement learning.


Create skill agents with goals and constraints Create skills agents with subject matter expertise by configuring goals and constraints for learning		train-with-goals-using-the-ui
Create skill agents with rewards using the SDK	Create skill agents that learn with rewards and access additional teaching tools in Python	train-with-goals-or-rewards-using-the-sdk
Publish to the platform	Upload skill agents configured with the SDK to the AMESA UI for training and deployment	import-agent-components-to-the-ui

Create skill agents with goals and constraints

Create skills agents with subject matter expertise by configuring goals and constraints for learning

train-with-goals-using-the-ui

Create skill agents with rewards using the SDK

Create skill agents that learn with rewards and access additional teaching tools in Python

train-with-goals-or-rewards-using-the-sdk

Publish to the platform

Upload skill agents configured with the SDK to the AMESA UI for training and deployment

import-agent-components-to-the-ui

## Deploy Multi-Agent Systems Once AMESA agentic systems are designed and trained, you can export them to the AMESA runtime to connect with your system. Learn how to deploy an agent within the runtime container and how to use AMESA's tools to analyze agent behavior during both training and deployment.


Evaluate the performance of your multi-agent system	Evaluate performance using the AMESA benchmarking feature	set-kpi-and-roi
Deploy a AMESA multi-agent system	Export a multi-agent system and connect to the AMESA runtime container	deploy-an-agent-in-a-container
Connect the multi-agent system to your production system	Connect the AMESA runtime container to your system for deployment	connect-runtime-container-to-your-operation
Audit multi-agent system behavior with the historian	Use the AMESA historian to analyze system behavior in detail	analyze-data-in-detail-with-the-historian