Context Engineering for Multi-Agent Systems

Move beyond prompting to build a Context Engine in a transparent architecture of context and reasoning

🎞️▶️ In 21st‑century Agentic AI, Natural‑Language‑Programmed LLMs are the execution agents, and the domain‑agnostic dual‑RAG MAS is the environment they operate in.
This repository provides a production-ready blueprint for the Agentic Era, allowing you to replace rigid, hard-coded workflows with a dynamic, transparent, observable, and sovereign Context Engine. By building universal, domain-agnostic Multi-Agent Systems through high-level semantic orchestration, you can save thousands of lines of code while maintaining 100% observability.

Copyright 2025-2026, Denis Rothman. Last updated: March 14, 2026

See the Changelog for updates, fixes, and upgrades(past, present, coming).

Save thousands of lines of code by building universal, domain-agnostic Multi-Agent Systems (MAS) using the ultimate new programming language:
🛰️ View Software Evolution Timeline

🐬 March 14, 2026 update of the January 24, 2026 Release: OpenAI gpt-5.4 implemented in the Universal Context Engine
Sovereign Universal Context Engine: A new Glass Box Context Engine implementation - Chapter10/Universal_Context_Engine.ipynb and Chapter10/Universal_Context_Engine_UI.ipynb- demonstrating domain-agnostic architecture by running cross-domain use cases on the same core.
Token Analytics: engine.py and the Dashboard provide rigorous transparency into token usage (Input, Output, Difference) for cost and verbosity analysis.

🔧 LLM API Update

For a detailed list of affected notebooks and all changes, see the ➡️ CHANGELOG.md

LLM API update:
Several notebooks have been upgraded to use GPT‑5.1 along with the latest OpenAI library standards.
These improvements provide better performance, lower reasoning latency, and more reliable handling of structured agent outputs.

This update also includes fixes to the Moderation API, ensuring safer and more robust processing of multi‑agent interactions.

Alternative: Sovereign AI Without External LLM APIs:

If you prefer not to rely on an external LLM API, a full DeepSeek‑R1 Sovereign AI Implementation Guide and the Hardware benchmark notebook (with code) is available:

➡️ DeepSeek‑R1 Sovereign AI Guide

🚀 NEW: Interactive Trace Dashboard
Available in the Context Engine Room of Chapters 8 & 9: Visualize agent reasoning with our new HTML-based trace renderer.

Denis Rothman

                       

About the book

.

Generative AI is powerful, yet often unpredictable. This guide shows you how to turn that unpredictability into reliability by thinking beyond prompts and approaching AI like an architect. At its core is the Context Engine, a glass-box, multi-agent system you’ll learn to design, strengthen, and apply across real-world scenarios.
Written by an AI guru and author of various cutting-edge AI books, this book takes you on a hands-on journey from the foundations of context design to building a fully operational Context Engine. Instead of relying on brittle prompts that give only simple instructions, you’ll begin with semantic blueprints that map goals and roles with precision, then orchestrate specialized agents using the Model Context Protocol (MCP). As the engine evolves, you’ll integrate memory and high-fidelity retrieval with citations, implement safeguards against data poisoning and prompt injection, and enforce moderation to keep outputs aligned with policy. You’ll also harden the system into a resilient architecture, then see it pivot seamlessly across domains, from legal compliance to strategic marketing, proving its domain independence.
By the end of this book, you’ll be equipped with the skills needed to engineer an adaptable, verifiable architecture you can repurpose across domains and deploy with confidence.

Key Architecture Highlights

• Glass Box Architecture: Provides 100% observability into agent reasoning through interactive trace dashboards and detailed execution logs.
• Universal Context Engine: A domain-agnostic core that runs cross-domain use cases (e.g., Legal and Marketing) without changing a single line of code.
• Dual High-Fidelity RAG: Implements research agents(dual: instructions and facts) with automated input sanitization and source-verifiable citations to ensure accuracy and defense.
• Telemetry‑driven context layers: Continuous ingestion and structuring of environmental signals that form the dynamic operational context for multi‑agent reasoning.
• Protocol-Driven: Orchestrates specialized agents using the Model Context Protocol (MCP) for seamless, modular multi-agent workflows.
• Token & Cost Analytics: Integrated tracking of input/output tokens to monitor cost-efficiency and model verbosity at every step.

Key Learnings

• Develop memory models to retain short-term and cross-session context
• Craft semantic blueprints and drive multi-agent orchestration with MCP
• Implement high-fidelity RAG pipelines with verifiable citations
• Apply safeguards against prompt injection and data poisoning
• Enforce moderation and policy-driven control in AI workflows
• Repurpose the Context Engine across legal, marketing, and beyond
• Deploy a scalable, observable Context Engine in production

🎥 Deep Dive: Architecture → Context → Agents → Code

This recorded session walks through the entire stack behind the sentence:
“In 21st‑century Agentic AI, Natural‑Language‑Programmed LLMs are the agents, and the domain‑agnostic dual‑RAG MAS is the environment they operate in.”
The deep dive unpacks each term step‑by‑step:

• 21st‑century Agentic AI — why agents are natural‑language‑programmed programs
• LLMs as agents — how reasoning, memory, and protocols turn models into actors
• Domain‑agnostic Context Engine — the universal core that runs any use case
• Dual‑RAG MAS — the two‑channel research architecture (instructions + facts)
• Environment design — how telemetry, context layers, and MCP orchestrate agents
• Full drill‑down to code — notebooks, pipelines, and execution traces
• Full climb back up — how the code re‑forms the architecture end‑to‑end
  📺Watch the full deep dive on LinkedIn
  If you are an architect or lead looking for:
  ✅ ROI & Domain Agnosticism logic
  ✅ Glass-Box Observability traces
  ✅ Sovereign RAG blueprints
  Join the engineering discussion here: Link to GitHub Discussion

Chapters: From Architecture to code

Chapters	Colab	Kaggle	Studio Lab
Chapter 1: From Prompts to Context: Building the Semantic Blueprint
SLR.ipynb
Use_Case.ipynb
Chapter 2: Building a Multi-Agent System with MCP
MAS_MCP.ipynb
MAS_MCP_control.ipynb
Chapter 3: Building the Context-Aware Multi-Agent System
RAG_Pipeline.ipynb
Context_Aware_MAS.ipynb
Chapter 4: Assembling the Context Engine
Context_Engine.ipynb
Chapter 5: Hardening the Context Engine
Context_Engine_MAS_MCP.ipynb
Context_Engine_Pre_Production.ipynb
Chapter 6: Building the Summarizer Agent for Context Reduction
Context_Engine_Content_Reduction.ipynb
Chapter 7: High-Fidelity RAG and Defense: The NASA-Inspired Research Assistant
Domain‑agnostic Universal Context Engine architectures are powered by environment‑ingestion agents illustrated in High_Fidelity_Data_Ingestion.ipynbthat dynamically construct the operational context for complex, cross‑domain agentic systems.
High_Fidelity_Data_Ingestion.ipynb
Domain‑agnostic Universal Context Engine architectures are also driven by MAS‑RAG‑Context Engines, illustrated in NASA_Research_Assistant_and_Retrocompatibility.ipynb, which combine high‑fidelity retrieval, defense, and multi‑agent reasoning into a unified operational environment.
NASA_Research_Assistant_and_Retrocompatibility.ipynb
Chapter 8: Architecting for Reality: Moderation, Latency, and Policy-Driven AI
Data_Ingestion.ipynb
Legal_assistant_Explorer.ipynb
Chapter 9: Architecting for Brand and Agility: The Strategic Marketing Engine
Data_Ingestion_Marketing.ipynb
Marketing_Assistant.ipynb
Chapter 10: The Blueprint for Production-Ready AI
The Universal Context Engine provides full architectural sovereignty through glass‑box reasoning, verifiable multi‑agent traces, and complete control over memory, dual RAG, moderation, and orchestration. Its domain‑agnostic core can be deployed in restricted, mission‑critical, strategic environments where transparency, auditability, and sovereignty are mandatory.
The Universal_Context_Engine.ipynb version runs a list of explicit scenarios for batch processing.
🐬Universal_Context_Engine.ipynb - March 14, 2026 update of the January 24, 2026 Release: OpenAI gpt-5.4
The Universal_Context_Engine_UI.ipynbprovides an IPython interface for interactive sessions that highlights how the industry is converging toward domain‑agnostic, environment‑driven agentic systems built on transparent, context‑rich architectures.
🐬Universal_Context_Engine_UI.ipynb - March 14, 2026 update of the January 24, 2026 Release: OpenAI gpt-5.4

🛡️ Sovereign AI & Open-Source Engineering

For organizations requiring 100% data privacy and zero external API dependencies, this repository provides a dedicated Sovereign Path.
By leveraging high‑reasoning open‑source models like DeepSeek‑R1, you can achieve industrial‑grade performance entirely on your own infrastructure.

🔑 Key Highlights of the Sovereign Path

⚡Performance: Benchmarked at ~9.75 seconds on NVIDIA H100 hardware for complex multi‑step reasoning.

🔍Transparency: Provides 100% Glass‑Box observability using local reasoning traces (</think> blocks).

🛠️Independence: Fully disconnected execution with no vendor lock‑in and no unpredictable API costs.

Read the DeepSeek-R1 Sovereign AI Guide and the Hardware benchmark notebook

Launch the DeepSeek‑R1 Sovereign AI Guide in Google Colab

Requirements for this book

Before running the code, ensure your development environment is properly configured.

✅ Prerequisites

• Python: Version 3.10+
• Environment Options: Google Colab, Kaggle, or Local

Requirements for this book

Before running the code, ensure your development environment is properly set up. All hands-on chapters use reproducible Python-based environments, tested in Google Colab and VS Code.

A Note on Latency: The Context Engine built in this book and repository performs complex, multi-step reasoning, not simple, single-shot answers. The delay you observe in Colab is the "thinking" time, as the engine dynamically plans and executes a sequence of API calls (e.g., planning, then RAG, then generation). This is the same reason advanced platforms like Gemini or ChatGPT require a moment to "think" for complex requests, even though they benefit from significantly more powerful environments.

✅ Prerequisites

• Python: Version 3.10+
• Environment Options:
  • Google Colab or
  • Local Python environment with:
    • openai
    • pinecone-client
    • tiktoken
    • tenacity
    • fastapi

🚀 Quick Start

Get up and running using cloud-based virtual machines using the Google Colab links provided for each notebook.
No local installation is required.

1. Get Your API Keys

Before running the notebooks, you will need valid API keys for the underlying services:

• OpenAI: Sign up and generate a key at platform.openai.com.
• Pinecone: Sign up and generate a free API key at pinecone.io.

2. Run the Notebooks

Click the badges below to launch the notebooks directly in a pre-configured Google Colab VM. You will be asked to add your API keys to the Colab Secrets Manager upon launch.

Chapter	Notebook	Launch
Chapter 4	Context Engine
Chapter X	Another Notebook

✅ Project Structure

Create a GitHub or local workspace containing at least:

• helpers.py
• agents.py
• registry.py
• engine.py
• Notebook files for each chapter

✅ Required API Keys

• OpenAI – model access and moderation
• Pinecone – vector database storage and retrieval
• (Optional) Google Cloud or AWS – for deployment sections in Chapter 10

✅ System Requirements

Requirement	Minimum	Recommended
CPU	Dual-core	Any modern multi-core
RAM	8 GB	16 GB or Google Colab Pro
GPU	Optional, but helpful for embeddings and token-heavy operations

Note: From Chapter 5 onward, modular components depend on earlier notebooks. Ensure your environment is configured correctly, as setup steps may not be repeated in later chapters.

✅ Additional Notes

• Local execution may incur token and API costs with large contexts.
• The Summarizer Agent (Chapter 6) helps reduce token usage.
• Familiarity with RAG workflows and MCP-based agent orchestration is recommended.
• Refer to Appendix: Context Engine Reference Guide for quick lookup of component structures and explanations.

About the Author

✅ Get to know the Author

Denis Rothman is an AI systems architect and author whose work bridges foundational AI research with today’s generative and agentic architectures. A graduate of Sorbonne University and Paris‑Diderot University, he designed one of the earliest patented word2matrix numerical encoding systems which was a precursor to modern embedding techniques. He designed one of the first industrial conversational agents, deployed as an automated language teacher for Moët & Chandon and other global companies.

Throughout his career, Denis has built large‑scale AI systems across industries, from IBM resource optimizers to worldwide Advanced Planning and Scheduling (APS) solutions, always focusing on transparent, explainable, and production‑ready architectures.

Building on decades of applied AI engineering, he has become a leading voice in the agentic era of AI, authoring influential books on transformers, RAG pipelines, business‑ready generative AI, and now Context Engineering for Multi‑Agent Systems. His work emphasizes model‑agnostic engineering, semantic design, and the construction of resilient, domain‑independent AI systems that go far beyond prompting.

Denis continues to publish hands‑on frameworks, open‑source architectures, and practical guides that help engineers, researchers, and organizations build the next generation of verifiable, context‑driven AI systems.

✅ Other Related Books

• Building Business-Ready Generative AI Systems, First Edition
• RAG-Drive Generative AI, First Edition
• Transformers for Natural Language Processing and Computer Vision, Third Edition

Contributing

We welcome contributions! High interaction through Issues, PRs, and Comments helps the Context Engine grow and improves the trending visibility for the community.

How to get started:

1. Check Issues: Look for the good first issue label for approachable tasks.
2. Discussions: Join our Discussions tab to propose new features or "Context Chaining" techniques.
3. Pull Requests: Submit improvements to the core engine.py or new specialized agents in agents.py.