Agentic Engineering

Your C# skills are worth more today than they were a year ago — if you know how to put a language model in the loop. This book shows you how, with the Microsoft Agent Framework: real tools, RAG, multi-agent orchestration, plus the hosting, observability, and safety that separate a demo from a system you ship. Nineteen chapters. 120 runnable projects. No Python detours. Just C# and .NET 10.

This book teaches harness engineering as a discipline. Not magic prompts. Not vendor tricks. Engineering practice applied to a new substrate.

A practical, code-first guide to building production-ready AI agents and multi-agent systems in C# with Microsoft Agent Framework, Microsoft.Extensions.AI, tools, context, orchestration, observability, workflows, and enterprise-ready patterns.

How to put AI agents in production without ending up in the news. A field guide to bounded AI autonomy, MCP security, and AgentSecOps.

Software development is changing fast, and Claude Code is at the center of that shift. Learn how to work effectively with AI agents to write code, automate workflows, and build larger projects with confidence. From setup and prompt design to real-world engineering practices, this book provides a practical guide to modern software development in 2026.

OpenClaw in Production shows you how to run OpenClaw as a secure, reliable service that can handle real workloads. Whether you're deploying on a Raspberry Pi or operating a Kubernetes cluster, you'll learn the practical skills needed to keep your agents stable, secure, and easy to manage as they grow from a single instance to production at scale.

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

AI agents become truly powerful when they can reason, adapt and recover instead of following a fixed sequence of steps. This book shows you how to design intelligent agent systems with computational graphs, giving you the tools to build scalable, reliable applications that can handle real-world complexity with confidence.

Ein Coding-Agent liefert in Sekunden makellosen Code, mittendrin eine Funktion, die es nie gab: Halluzinations-Lasagne. Claude Shannons verrauschter Kanal von 1948 erklärt, warum plausible Ausgaben nicht verlässlich sind, und wie ein geschärfter Sender, ein beherrschter Kanal und ein prüfender Empfänger daraus verlässliche Software machen.

88 per cent of AI agent projects never reach production, not because the model failed, but because the harness around it was never built. This is the practitioner's handbook for engineers who deploy AI inside real organisations, covering the complete journey from discovery to handover with harness engineering as the core technical discipline.

What if TransE, ComplEx, RotatE and the rest of the knowledge graph “model zoo” were different views of one geometric operator? Learn the mathematics, code and practical design principles behind structured memory for trustworthy AI.

This book is a practical guide to building and running local AI systems in 2026. Learn how to choose hardware, run modern LLMs, build RAG pipelines and AI agents, and deploy secure, efficient infrastructure while keeping full control of your models and data.

RAG, Agent Bricks, the Multi-Agent Supervisor with MCP, Lakebase, MLflow 3, Lakehouse Monitoring, Feature Store, Vector Search. Every AI surface Databricks shipped at GA in 2025 and 2026, taught by a practitioner, current to 2026. What you will learn - Build RAG pipelines with Vector Search, embedding models, and citation grounding- Ship Agent Bricks for classification and information extraction- Orchestrate specialist agents with the Multi-Agent Supervisor and MCP- Use Lakebase as the operational Postgres layer for AI apps and agents- Detect data and model drift with Lakehouse Monitoring; wire alerts to retraining- Manage the ML lifecycle with MLflow 3 and the UC Model Registry- Govern features across training and serving with Feature Store (offline + online)- Serve foundation and custom models with AI Gateway controls Who this book is for Data engineers, ML engineers, and AI/ML architects who know PySpark and the Databricks platform and now need to ship production AI. Volume 3 is the recommended prerequisite. Table of Contents 1. Databricks SQL in Production. Warehouses, materialized views, three latency signals (admission, compilation, execution), the full dashboard backend wiring.2. External BI: Tableau, Power BI, dbt. Performance tips that take a dashboard from sluggish to instant, dbt configuration at incremental scale, the seam between BI and the lakehouse.3. AI/BI Dashboards. Anatomy of a Lakeview dashboard, draft vs published flow, the Dashboard Agent's reliable patterns, the five-grant permission model.4. Genie: Natural-Language Analytics. Grounding sources, the priority rule, the SQL Genie actually writes, the questions Genie answers cleanly versus the ones that confuse it.5. AI SQL Functions. ai_query, ai_parse_document, ai_extract for PDFs and HTML, univariate forecasts, the daily cost math for production AI SQL pipelines.6. Model Serving. Endpoints, the three fields that decide capacity and cost, the chat-completion payload, the five moving pieces of a production recommender.7. Foundation Models. Five major providers, the External Models config, the vendor-swap pattern (Claude to Gemini in hours, not weeks), the three habits that keep swap cost low.8. Vector Search and RAG. Six delta-sync arguments, three chunking strategies compared, the RAG function your app imports, end-to-end answer evaluation with traces.9. MLflow 3 and UC Model Registry. Versions, aliases, tags (and what each is not for), five tracking calls and what each one writes, the experiment-to-production lifecycle.10. Feature Store. Why SDP is the right producer, the six-file project layout, four parity-failure classes between offline and online stores and what causes each.11. MLOps as a Practice. Seven sources every incident reads from, three deploy patterns (canary, shadow, blue-green), three retrain strategies, five golden signals for an ML endpoint.12. Lakehouse Monitoring: Drift Detection. Six monitor parameters, the loop from drift alert to retraining, what to do when the baseline table is missing.13. Distributed Deep Learning. Three signals that force distributed training, picking the flavor (data, model, hybrid) from the bottleneck, four pieces of GPU memory worked out for a 7B model.14. Agent Bricks. Declarative classification and information-extraction agents, eval-set ingredients, the pre-compute pattern that makes small seed sets work.15. Multi-Agent Supervisor and MCP. The supervisor build, synthetic-turn evaluation, three real conversations end to end, the auth-passthrough chain across child agents.16. Lakebase: Operational Postgres for AI. Five alternatives compared, sub-10ms reads for AI apps, the lineage from Delta source through SDP into Postgres and onward to the endpoint.17. Capstone: Retail Intelligence App. Ten stages, each anchored to an earlier chapter. The smoke test that confirms every stage of the platform is reachable, the new-data path through the recommender.18. Certification and What's Next. The certification paths that actually map to the book, and the reading list the on-call team uses when something breaks.

It's never been easier to build an AI agent — and never been harder to make one that actually works. This book takes you from language model foundations to production-ready multi-agent systems with the depth to predict failure before it happens, engineer graceful degradation over catastrophic failure, and take absolute architectural ownership. Get the paperback from amazon.

An agent can score well on average and still fail exactly where it matters. Beyond “Ship and Pray” shows how to replace benchmark averages with designed experiments, geometric ground truth and failure attribution—so teams can discover when an agent breaks, identify the responsible component and test whether it fails safely under tool faults.