Vizuara Books
AI Context Engineering
Engineer the context window like a system.
Move past prompt engineering to treat everything an LLM sees — instructions, tools, retrieved knowledge, and memory — as one engineered system. Learn the four strategies (write, select, compress, isolate), then build RAG, MCP tools, memory, and agents from scratch.
Read on your Kindle
We'll send this whole book straight to your Kindle — it opens natively, so you can resize the text, read fully offline, and it remembers where you left off. Nothing to download or manage.
Sending to Kindle is for subscribers — subscribe to read the whole library on your Kindle.
00Context Foundations6 capsules
Context Foundations — 6 chapters.
01Why Context Engineering, Not Prompt Engineeringconceptfree12 min02Software 1.0, 2.0, and 3.0concept🔒12 min03Anatomy of the Context Windowconcept🔒13 min04The Four Strategies: Write, Select, Compress, Isolateconcept🔒14 min05Context Failure Modes: Poisoning, Distraction, Confusion, Clashdeep-dive🔒16 min06Your First Context Lab: Measuring Tokens and Effectscode🔒11 min01The Instructional Layer5 capsules
The Instructional Layer — 5 chapters.
07System Prompts as Programsconcept🔒13 min08Instructions, Examples, and Guardrailsintuition🔒15 min09Designing Roles and Personasintuition🔒11 min10Structured Output and Formatting Contractscode🔒14 min11Instructional Layer Labcode🔒14 min02Write and Select: RAG7 capsules
Write and Select: RAG — 7 chapters.
12Write vs Select: Two Halves of Knowledge Injectionconcept🔒15 min13Why RAG Exists: Grounding, Freshness, and Costconcept🔒15 min14Chunking and Embeddingsmath🔒14 min15Vector Search and Retrievalcode🔒14 min16Reranking and Hybrid Searchdeep-dive🔒14 min17Building a RAG Pipeline End-to-Endproject🔒17 min18RAG Lab and Interactive Quizcode🔒16 min03Tools and MCP6 capsules
Tools and MCP — 6 chapters.
19Tools as Context: Giving the Model Handsconcept🔒15 min20Tool-Calling Mechanicscode🔒13 min21What Is MCP? The Model Context Protocolconcept🔒13 min22MCP Servers and Clientscode🔒15 min23Building a Useful MCP Server and Clientproject🔒14 min24Tool-Context Hygienedeep-dive🔒14 min04Compress and Isolate5 capsules
Compress and Isolate — 5 chapters.
25Why Compress: The Token Budget Is Finiteconcept🔒13 min26Summarization and Pruning Strategiesintuition🔒13 min27Isolation: Quarantining Context Across Sub-Agentsconcept🔒14 min28Multi-Agent Context Boundariesdeep-dive🔒14 min29Compress and Isolate Labcode🔒14 min05Memory Architectures5 capsules
Memory Architectures — 5 chapters.
30The Stateless LLM Problemconcept🔒13 min31Short-Term vs Long-Term Memoryconcept🔒14 min32Episodic, Semantic, and Procedural Memoryintuition🔒15 min33Building Memory with Retrievalcode🔒13 min34Memory Architectures Labcode🔒16 min06Setting Up the Build Workflow4 capsules
Setting Up the Build Workflow — 4 chapters.
35A Coding-Agent Build Workflowconcept🔒11 min36Claude Code and OpenClawconcept🔒13 min37Context Files and Repo Hygienecode🔒14 min38Workflow Setup Labproject🔒13 min07Capstone Builds5 capsules
Capstone Builds — 5 chapters.
39Capstone: Building an Email Agentproject🔒13 min40Mega Build: Driving Claude Code End-to-Endproject🔒12 min41OpenClaw and RL Agentsdeep-dive🔒14 min42Building Conversational Voice Agents for Bharatproject🔒16 min43Putting It All Together: A Context-Engineering Playbookconcept🔒15 minRatings & reviews
No ratings yet. Yours would be the first.