⚙️

Context Engineering

Managing inputs, memory, history compression, and Claude skills integration.

1

Context Engineering: Memory & History

advanced~8h

Learn context assembly, the 6 types of contexts for AI agents, memory hierarchies, token compression, and context engineering workflows.

2

Conversational Memory

intermediate~3h

Techniques for persisting context across multiple conversation turns in LLM chat applications: full buffer, windowed buffer, summary memory, and entity memory — and how to choose between them given context window constraints and conversation length.

3

Context Engineering for Agents: The 6 Types of Context

intermediate~4h

The CPU/RAM mental model for context engineering, the 4 fundamental stages (Write, Read, Compress, Isolate), and the 6 types of context every production agent needs (Instructions, Examples, Knowledge, Memory, Tools, Tool Results).

4

Build a Multi-Source Context Engineering Workflow [Hands-On]

advanced~6h

A full hands-on build of a multi-agent research assistant gathering context from documents, memory, web search, and arXiv — using Tensorlake, Zep, Firecrawl, Milvus, and CrewAI, deployed as a Streamlit app with citations.

5

Context Engineering in Claude Skills

intermediate~3h

Anthropic's Claude Skills mechanism — a 3-layer context system that lets an agent use hundreds of specialized workflows without overloading its context window.

6

Manual RAG vs. Agentic Context Retrieval: Building for Multi-Source Enterprise Data

advanced~4h

Why naive 'embed it and RAG it' fails for real multi-source enterprise data, and the 3-layer Ingestion/Retrieval/Generation architecture (grounded in the open-source Airweave framework) needed to actually solve it.