Four tracks.

Tool design/MCP, Context engineering, Hybrid search, Reranking, and Evaluation basics are live cards. Hybrid search and Reranking stay separate, matching the registry. Tool design includes the Model Context Protocol. Prompt injection cites OpenAI's computer use guide instead of the Agent Builder safety page. Temperature notes top-p. Agent loop says AI agent. RAG says retrieval-augmented generation. No rate or usage count was added.

Tool design/MCP, Context engineering, Hybrid search, Reranking, Evaluation basics

The home page opens on what the site is, four browser demos, the tracks, and the pricing tiers. The token split in the demo is an illustration, not a model tokenizer. Example prices are labelled and match the Foundations pack. No model is called.

Agent loop, Tool calling, and Prompt injection are live cards. They cite OpenAI, Anthropic, and Gemini docs. Prompt injection also cites the OWASP Top 10 for LLM Applications. No rate or usage count was added.

Agent loop, Tool calling, Prompt injection

RAG, Chunking, and Embeddings for retrieval are live cards. Foundations Embeddings stays without a card. The retrieval card links to that entry.

RAG, Chunking, Embeddings for retrieval

Prompt Caching, Model Selection & Routing, Structured Outputs, and Hallucination are live cards. Those four cite vendor API docs. The earlier cards still have no sources.

Prompt Caching, Model Selection & Routing, Structured Outputs, Hallucination

Cost on Tokens covers output versus input, cached input, and a higher rate past a size threshold. Cost on Context Window notes that resending the same history or documents adds up, and that prompt caching can make the repeated part cheaper.

Tokens, Context Window

Live cards use the v2 layout. Prerequisites and related concepts come from the registry.

Tokens, Context Window, Prompting

The concepts product is the site root.