AI Agent Tutorials & Guides

Build and Deploy MCP Server from Scratch

A hands-on guide to building, testing, and deploying Model Context Protocol servers with Python — tools, resources, prompts, transports, and production hosting

Building Agents with LangGraph

State machines, conditional routing, cycles, and human-in-the-loop checkpoints for retrieval workflows

Building Skills for AI Agents

Designing modular, reusable agent capabilities — from tool engineering and prompt crafting to skill bundles and the Agent Skills standard

Building a ReAct Agent from Scratch

Implementing the Reason-Act loop with tool calling, observation parsing, and stopping conditions in LangGraph and LlamaIndex

Deep Research Agents: from RAG to Autonomous Investigation

Iterative retrieval loops, web search integration, self-reflection, source triangulation, and automated report generation

Deploying Retrieval Agents in Production

Durable execution, crash recovery, scaling agent workers, streaming intermediate results, and cost monitoring

Design Patterns for AI Agents

A practical catalogue of architectural patterns — from reflection and tool use to multi-agent collaboration — for building reliable, production-grade LLM agents

Evaluating and Debugging AI Agents

Trajectory-level scoring, tool-call accuracy, LangSmith traces, agent benchmarks, and failure root-cause analysis

Guardrails and Safety for Autonomous Retrieval Agents

Input validation, tool-call authorization gates, sandboxed execution, budget limits, and prompt injection defense

Human–Agent Interaction Patterns

Human in the Loop, Human on the Loop, Human over the Loop — choosing the right level of autonomy for AI agents in production

Memory Systems for Long-Running Retrieval Agents

Conversation buffers, working scratchpads, episodic vector recall, and cross-agent memory sharing for persistent agent state

Multi-Agent RAG Orchestration Patterns

Supervisor, swarm, and hierarchical topologies for coordinating specialized retrieval agents

Planning and Query Decomposition for Complex Retrieval

Plan-and-execute agents, sub-question generation, and multi-hop retrieval over heterogeneous data sources

Tool Use and Function Calling for Retrieval Agents

From OpenAI function calling to MCP — building dynamic tool selection for SQL, API, and vector search retrieval

Harness Engineering for AI Agents

Understanding agent harnesses — the systems layer that turns raw LLM intelligence into production agents — from core primitives and middleware to continual improvement loops

23 April 2026