LangGraph for Agents: Stateful, Cyclic Workflows
How LangGraph models agents as stateful, cyclic graphs: state schemas, nodes, checkpointing, human review interrupts, and when to…
Category
AI Agents
This series is about building AI agents that survive production. It starts with design choices and ends with security, cost and operations.
First, read multi-agent vs single-agent to pick a shape. Then how to evaluate AI agents shows how to measure success. Finally, prompt injection in agents covers the attacks that come through tools and data. Each post is short, with code and trade-offs rather than theory.
27 articles
-
-
Human-in-the-Loop: Approvals, Escalation, and Guardrails
Designing human-in-the-loop agents: approval boundaries, escalation, review, override, audit trails, and how guardrails differ from permission checks.
-
Planning and Reasoning: ReAct, Plan-and-Execute, and Tree-of-Thought
AI agent planning and reasoning patterns: how ReAct, plan-and-execute, and tree-of-thought work, and when each one earns its…
-
Agent Memory: Short-Term, Long-Term, and Episodic
Agent memory for AI agents: short-term, long-term, and episodic stores, with write policies, retrieval, freshness, and how memory…
-
Tool Use and Function Calling: Giving Agents the Ability to Act
How tool use and function calling work in AI agents: tool contracts, JSON schemas, validation, authorization, and error…
-
When to Use an AI Agent (and When a Workflow Is Enough)
When to use an AI agent instead of a workflow: a decision framework comparing predictability, cost, and failure…
-
The Anatomy of an AI Agent: LLM, Tools, Memory, and the Control Loop
Inside the anatomy of an AI agent: the control loop, model calls, tool execution, state transitions, memory, and…
-
What Is an AI Agent? Definitions, Components, and How It Differs from a Chatbot
What is an AI agent? A practical definition: the components inside an agent system, how agents differ from…
-
AI Agents: The Complete Guide to Architecture, Frameworks, and Production Deployment
A complete guide to building reliable AI agents: architecture, tools, memory, frameworks, evaluation, observability, security, and production deployment.
-
MCP Explained: Model Context Protocol Guide
MCP standardizes how apps expose tools, resources, and prompts to LLMs. I cover architecture, security, and working server…
-
AI Agent Harnesses, Explained
The model is the brain; the harness is the room it works in. A field guide to loops,…
-
Core Concepts of AI: Beyond ChatGPT | Agentic AI Series
Go beyond ChatGPT and discover the core concepts of AI. From data and algorithms to models and learning,…
-
What AI Really Is for New Programmers | Agentic AI Series
A plain-language map of AI for new programmers: models, data, inference, and where it shows up in real…
