Artificial Intelligence

MLStation · Artificial Intelligence

Artificial Intelligence

Language models, retrieval, agents and perception: how modern AI systems work and how to build them.

Models

Large Language ModelsHow LLMs are trained, aligned, evaluated and served. Prompt EngineeringReliable prompting patterns, structure and evaluation. Computer VisionImage classification, detection, segmentation and generation. NLPTokenization, embeddings and classic language tasks.

Systems

RAGRetrieval-augmented generation: chunking, embeddings, ranking. Agentic AIPlanning, tool use, memory and multi-agent systems. MCP & Tool UseModel Context Protocol and connecting models to real tools. ToolsFrameworks and platforms for building AI applications.

Latest articles

Agentic AI with Multi-Agent Systems — Part I

14 min

Learn how to design tools, agents, state, routing, review, and human escalation with LangGraph—without requiring the article itself to execute.

Agentic AI with Multi-Agent Systems — Part III

29 min

The same Northstar Cloud incident-control problem, now combining LangGraph workflow control with MCP capability boundaries.

Agentic AI with Multi-Agent Systems — Part II

32 min

Build the Northstar Cloud multi-agent incident-control system with CrewAI agents and MCP servers, and compare it with the LangGraph/local-tool architecture from Part I.

Memory and State in AI Applications

Understand context, workflow state, short-term conversation history, and persistent memory without treating them as the same thing.

Oct 1, 2026

Validation and Evaluation of LLM Applications

Move from ‘the output looks good’ to systematic checks of correctness, grounding, retrieval, tool use, and end-to-end behavior.

Oct 1, 2026

Production AI: From Prototype to Reliable System

Bring the full MLStation AI path together with observability, versioning, cost, latency, security, evaluation, and controlled deployment.

Oct 1, 2026