Track-first tutorials that follow the Technician → Developer → System & Deployment → Architect ladder. New tutorials appear here each week as tracks release, so you can progress in order without missing a step.
Recommended starting points and popular tutorials
An Extensible Advisory Agent with Multiple Read-Only Tools
Build a professional, end-to-end advisory diagnostic agent that analyzes conveyor alarm logs and correlates them with known fault patterns.
Build stateful agent graphs with nodes, edges, and cycles
Master StateGraph to build stateful agent workflows with typed state, conditional edges, and cyclic reasoning patterns.
Organized by learning track progression
Use AI safely in industrial workflows. Advisory-only, no risky autonomy.
Configure Your AI Workbench in 20 Minutes
Set up your OpenAI API access safely and correctly. Get your API key, configure your environment, and make your first test call in 20 minutes.
The Only Python You Need to Safely Use Agentic AI as a PLC Engineer
Learn the minimal Python needed for industrial AI. Variables, loops, conditions - nothing more. Ready in 45 minutes.
From Deterministic Control to Reasoning Under Uncertainty
Learn the fundamental difference between traditional automation and agentic AI. From execution to reasoning.
From Static PLC Code to Transparent, Step-by-Step Machine Reasoning
Apply ReAct reasoning to PLC code analysis. Learn transparent, auditable AI reasoning for industrial automation.
What Actually Makes Something an Agent in Industrial Automation?
Distinguish rule-based automation from autonomous agents. Goals, state, and reasoning make the difference.
How Memory Transforms Stateless LLM Calls into Context-Aware Reasoning
Learn how conversation memory enables agents to detect patterns across observations and maintain context for industrial diagnostics.
How to Control AI So It Generates Consistent, Read-Only PLC Code Drafts
Control AI code generation with prompt engineering. Create reviewable, consistent PLC code drafts safely.
Teaching AI What Good Looks Like Using Curated PLC Examples
Learn how to guide AI toward consistent and reliable PLC code validation by supplying high-quality examples --- without giving it control.
Making AI Show Its Work on IEC 61131-3 ST
Learn how to get AI to explain its reasoning step-by-step when reviewing PLC logic, improving clarity, trust, and debuggability.
Connecting Reasoning to a Single Read-Only Tool
Learn how to safely connect an AI agent to a single, read-only tool to analyze PLC logic without any control authority.
From Free-Text Reasoning to Machine-Readable Results
Learn how to force AI agents to return deterministic, structured outputs when analyzing PLC logic, enabling reliable downstream processing.
An Extensible Advisory Agent with Multiple Read-Only Tools
Build a professional, end-to-end advisory diagnostic agent that analyzes conveyor alarm logs and correlates them with known fault patterns.
Build multi-agent systems with validation, coordination, and engineering discipline.
TypedDict, async/await, logging, and safe failure modes
Use TypedDict, async/await, logging, and error handling to make industrial AI agents reliable with PLC and alarm data.
async/await, retry, backoff, and safe failure modes
Deepen your async, retry, and backoff strategies so agent workers stay safe and predictable under real plant conditions.
ChatModels, prompt templates, output parsers, and runnable chains
Build composable LLM workflows for industrial agents using LangChain: ChatModels, prompt templates, output parsers, and runnable chains.
with_structured_output(), nested BaseModel, and typed agent contracts
Design production-grade schemas with with_structured_output(), nested Pydantic models, and validation patterns that become the typed contracts LangGraph state and tool returns depend on.
Build stateful agent graphs with nodes, edges, and cycles
Master StateGraph to build stateful agent workflows with typed state, conditional edges, and cyclic reasoning patterns.
Model Context Protocol for industrial tool integration
Learn MCP concepts with a read-only tool server, shared tooling, and security boundaries for industrial agents.
Embeddings, Vector Stores, and Citation-Ready Retrieval
Build citation-ready RAG with LlamaIndex: ingest docs, embed & store vectors, retrieve evidence, and log citations for audits.
Line-scoped persistence across shifts
Design line-scoped agent memory with LangGraph checkpointing plus persistence (SQLite/Redis) for 24/7 industrial shift handovers.
Shared tool layer for multi-agent systems
Wrap your plant data sources and services behind MCP servers so multiple agents can share reliable tools.
Coordinator-worker with shared MCP servers
Design multi-agent coordinator–worker systems sharing MCP servers for industrial diagnostics.
Multi-agent voting patterns for industrial validation
Build agent swarms with weighted consensus voting, health checks, and majority thresholds for PLC code validation.
Citation-ready retrieval with vendor filtering
Build vendor-specific RAG for PLC documentation with citation tracking and metadata filtering for multi-vendor systems.
Streaming processing, anomaly detection, and advisory-only recommendations
Build shadow-mode diagnostic loop from live PLC tags: stream processing, anomaly detection, advisory recommendations without PLC writes.
Seasonality, similar-episode retrieval, and predictive maintenance signals
Turn SCADA alarm history into seasonal baselines, similar-episode retrieval, and predictive maintenance signals (advisory-only).
Zero-Cost Testing with Historian Replay, Physics Checks, and Shadow Mode
Test agent recommendations at $0 using historian replay, constraint gates, physics checks, mock OPC UA tags, and shadow mode logging.
Assemble memory, tools, coordination, RAG, live signals, and validation into one end-to-end system
Build one integrated diagnostic system combining agent memory, MCP tools, multi-agent coordination, RAG context, live and historical signals, and validation layers.
Start with the foundation tutorials and progress to advanced multi-agent patterns. All tutorials include working code and honest failure stories.
GET STARTED