AI Agent Knowledge Library

Build

Hands-on guides, implementation patterns, and practical techniques for building useful AI agents and agentic applications.

15 Published resources

Explore: Knowledge & RAG Tools & Integrations Tutorials

Editor’s pick

Start with this guide

An MCP testing workflow inspects the contract, exercises success and failure cases, and verifies downstream effects.

Troubleshooting Intermediate

Testing and Debugging MCP Servers

A practical workflow for inspecting, testing, and debugging MCP servers from protocol exchange to downstream side effects.

Knowledge library

Latest resources

15 published articles

A well-designed MCP tool moves from clear intent through a bounded input schema to a typed structured result.

Best Practices Intermediate

MCP Tool Design: Schemas, Descriptions, and Structured Outputs

Practical MCP tool-design guidance covering names, descriptions, JSON Schema, structured results, errors, permissions, and testing.

An MCP client discovers tools, routes an approved request to the correct server, and normalizes the result.

Tutorial Intermediate

Build an MCP Client: Discovery, Routing, and Results

An implementation guide to MCP client connection management, tool discovery, model mapping, routing, result handling, and observability.

A typed Python function is exposed through a FastMCP server to an MCP client.

Tutorial Intermediate

Build Your First MCP Server in Python

A step-by-step Python tutorial for building, running, testing, and hardening a small MCP server with a typed tool.

A vector database architecture showing documents becoming embeddings and vectors before similarity search returns results to an AI agent or LLM.

Explainer Beginner

Vector Databases Explained for AI Agents

Learn how vector databases store embeddings, power semantic search, and support RAG and memory without replacing a knowledge base or relational database.

A RAG pipeline where a fast top-K retrieval stage feeds candidates to a precise reranker before better context is sent to an LLM.

Explainer Intermediate

Reranking in RAG: Why Retrieval Quality Matters

Learn why RAG pipelines rerank retrieved candidates, how cross-encoders and other methods improve ordering, and what reranking cannot fix.

A single user query branching into sparse retrieval for exact terms, dense retrieval for semantic meaning, and hybrid retrieval for combined evidence.

Comparison Intermediate

Hybrid Search vs Dense vs Sparse Retrieval

Compare sparse, dense, and hybrid retrieval by matching signal, strengths, failure modes, fusion methods, and the evidence needed to choose a RAG baseline.

A knowledge-preparation flow showing a document divided into chunks, converted into embeddings, and made available for retrieval.

Explainer Beginner

Chunking Strategies for RAG

Compare fixed-size, recursive, semantic, and document-aware chunking for RAG, with practical guidance on chunk size, overlap, metadata, and evaluation.

An architecture showing a user, AI agent, reasoning step, retrieval tool, knowledge base, retrieved context, observation, and answer or next action.

Tutorial Beginner

Build Your First RAG Agent

Build a framework-neutral RAG agent with a controlled retrieval tool, attributable evidence, bounded loops, citation checks, traces, and layered evaluation.

Build

Explainer Beginner

Embeddings Explained for AI Agents

A beginner-friendly mental model of embeddings, vectors, similarity, and how AI agents use them for retrieval and memory without confusing similarity with truth.