Authors
Meet the contributors to Agentic Academy
Markus Müller
Co-Founder
Global Field CTO for API Management at Boomi
Markus Müller is the Global Field CTO for API Management at Boomi, where he helps organizations navigate the intersection of APIs, AI agents, and enterprise integration. Before Boomi, Markus was co-founder and CTO at APIIDA, helping customers adopt Federated API Management practices. He is a regular speaker at industry conferences addressing AI agent governance, enterprise integration patterns, and the evolving protocol landscape shaping how agents communicate and operate.
Speaking & Media
Conference
AI Agent Governance in the Enterprise
Regular keynote and conference speaker on governing AI agents at enterprise scale.
Conference
The Protocol Landscape for Agentic AI
Talks on MCP, OpenAPI, AsyncAPI, and the evolving standards shaping agent communication.
Conference
Federated API Management
Industry talks on federated approaches to API governance and multi-platform management.
Learning Path • Module 2
agent-design
Error Handling and Recovery in Agentic Systems
Agent failures are not like software bugs. Partial completions, semantic errors, cascade contamination, and cost runaway …
Read articleLearning Path • Module 2
agent-design
From Primitives to Patterns: How Building Blocks Become Systems
Knowing the 17 agentic primitives is necessary but not sufficient. The real skill is understanding how they compose into …
Read articleLearning Path • Module 2
agent-design
From Prototype to Production: What Actually Changes
The gap between a working agent demo and a production deployment is not about code quality. It is about the security …
Read articleLearning Path • Module 2
agent-design
Governance Patterns: Constraining Agents Without Killing Their Value
Agent governance is not about restriction — it is about creating the conditions under which agents can be trusted with …
Read articleLearning Path • Module 2
agent-design
Multi-Agent Coordination: When and How to Split the Work
Multi-agent systems solve problems that single agents cannot — but they introduce coordination costs that most teams …
Read articleLearning Path • Module 2
agent-design
Orchestration Patterns: Choosing How Agents Coordinate
Single, sequential, parallel, or hierarchical — the orchestration pattern you choose determines your system’s …
Read articleAgentic Governance: A Practical Guide to Governing AI Agent Systems
How do you govern AI agents in production? From API governance and security to observability and lifecycle management, a …
Read articleHow Do AI Agents Work? Architecture, Components, and Patterns
AI agents combine large language models with tools, instructions, and memory to perceive, reason, and act autonomously. …
Read articleOp-Ed
agent-fundamentals
Product Engineers Were Ready for This
Organizations that already shifted from software to product engineering will find the AI coding revolution unremarkable. …
Read articleWhat AGENTS.md Actually Does to Your Coding Agent
The first rigorous benchmark of repository context files finds LLM-generated files hurt performance and raise costs, …
Read articleAI Agent Security in 2026: 88% of Enterprises Report Incidents
Gravitee’s 2026 survey of 919 enterprises reveals a dangerous gap: 88% report AI agent security incidents, yet …
Read articleAAuth: A New Authentication Standard Built for the Age of AI Agents
Dick Hardt, the creator of OAuth, has proposed AAuth—a protocol designed from scratch for agent-to-resource …
Read articleAgent Identity and Authentication: Why OAuth Alone Isn't Enough
AI agents can’t click consent screens. How to build identity systems that handle delegation, credential scoping, …
Read articleAgent Lifecycle Management: From Development to Decommission
Building an agent is the easy part. Managing it through development, testing, deployment, monitoring, updating, and …
Read articleMCP Registry: How Agents Discover and Connect to Tools
MCP standardizes agent-to-tool connections. The MCP Registry standardizes discovery. What it provides, how namespace …
Read articleSecurity Boundaries for Agentic Systems
Agents cross trust boundaries that traditional software never touches. How to design security perimeters that contain …
Read articleA2A Deep Dive: What the Agent-to-Agent Protocol Actually Does
Google’s A2A protocol enables collaboration between opaque AI agents. What it provides, how it compares to MCP, …
Read articleAPI Gateway Patterns for Agentic Workloads
Traditional API gateways weren’t built for agents that chain tool calls and consume tokens unpredictably. How …
Read articleBenchmarking Agent Reliability
SWE-bench, GAIA, AgentBench—agent benchmarks are proliferating. Here’s what they actually measure, what they miss, …
Read articleObservability for AI Agents: Beyond Traditional APM
Traditional APM breaks down when agents make autonomous decisions across multi-step tool chains. Here’s what …
Read articleThe Protocol Landscape for Agentic Systems
MCP, A2A, OpenAPI, AsyncAPI—the protocol landscape for agentic systems is taking shape. Here’s what each provides, …
Read articleLearning Path
agent-fundamentals
AI Economics: Cost, Latency, and Model Selection
The pragmatic reality of running AI in production—model tiers, cost-latency tradeoffs, caching strategies, rate limits, …
Read articleLearning Path
agent-fundamentals
From Chat to Capabilities: Tool Use and Function Calling
How LLMs go from generating text to taking actions—the bridge from chatbot to agent building block through tool use, …
Read articleLearning Path
agent-fundamentals
From LLM to Agent: The Architectural Leap
What makes an agent more than a prompted LLM—the combination of planning, tools, memory, and autonomy that transforms a …
Read articleLearning Path
agent-fundamentals
How LLMs Process Information: Tokens and Context Windows
The operational realities of LLMs that shape every agent architecture decision—from token economics to context window …
Read articleLearning Path
agent-fundamentals
Memory, State, and Learning: What LLMs Remember (and Don't)
Why LLMs are stateless by default, what that means for agent design, and the approaches to giving agents persistent …
Read articleLearning Path
agent-fundamentals
Planning, Reasoning, and the Limits of AI Judgment
How LLMs think—chain-of-thought, multi-step reasoning, and decomposition. And equally important: where reasoning breaks …
Read articleLearning Path
agent-fundamentals
What Is a Large Language Model?
Mental models for enterprise practitioners. What LLMs actually do, how to think about them, their capabilities and …
Read articleLearning Path • Module 1
agent-fundamentals
What Are AI Agents? Definition, Architecture, and How They Work
AI agents are entities that perceive, reason, and act to accomplish goals. Learn how agents combine LLMs, tools, and …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Dynamic Connections?
Dynamic connections use registries and catalogs to discover endpoints at runtime—enabling agentic systems that evolve …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Point-to-Point Connections?
Point-to-point connections are direct, explicit links between two specific components in an agentic system—the simplest …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Queued Connections?
Queued connections use message infrastructure to decouple senders and receivers in time—enabling resilient, scalable …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Users?
Users are the human participants who interact with, oversee, and ultimately benefit from agentic systems—the actors …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Agentic Orchestration?
Agentic orchestration is dynamic, LLM-driven coordination where a central agent reasons about how to decompose, …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Choreography?
Choreography is decentralized coordination where autonomous agents react to events and coordinate without a central …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Conversation?
Conversation is the interaction pattern where actors engage in sustained, contextual exchange over multiple turns—the …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Delegation?
Delegation is the interaction pattern where one actor instructs another to perform specific work—the command that sets …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Notification?
Notification is the interaction pattern where an actor announces that something happened—the event-driven signal that …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Retrieval?
Retrieval is the interaction pattern where one actor requests information from another without expecting any state …
Read articleLearning Path • Module 1
agent-fundamentals
What Is Workflow Orchestration?
Workflow orchestration is deterministic, centralized coordination that executes predefined sequences of steps—the …
Read articleAI Agent Autonomy Borders: When to Escalate to Humans
Every AI agent operates within boundaries. Success depends on whether the agent recognizes its limits and escalates …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Action Tools?
Action tools enable AI agents to modify state in the outside world—creating records, sending messages, triggering …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Agent Instructions?
Agent instructions define an individual AI agent’s identity, expertise, and behavioral guidelines—the constitution …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Knowledge Tools?
Knowledge tools are read-only interfaces that give AI agents access to information beyond their training data—the eyes …
Read articleLearning Path • Module 1
agent-fundamentals
What Are System Instructions?
System instructions are platform-level rules, constraints, and objectives that govern all AI agents within an …
Read articleLearning Path • Module 1
agent-fundamentals
What Are Workflow Instructions?
Workflow instructions provide step-by-step procedures that guide AI agents through multi-step tasks—the runbooks and …
Read articleThe Applied Autonomy Framework: Bridging Agent Design and Operations
The gap between what you design and what your organisation can operate is where most AI agent initiatives fail. The …
Read articleThe Four Dimensions of Agent Autonomy
Why ‘how autonomous is your agent?’ is the wrong question—and what to ask instead. A framework for …
Read articleOp-Ed
agent-fundamentals
Agents Are Not Magic: Why Autonomous AI Hype Is Dangerous
The obsession with ‘autonomous agents’ sets enterprises up for failure. Agents need structure, constraints, …
Read articleLearning Path • Module 1
agent-fundamentals
Building Your First AI Agent: A Practical Introduction
Start your journey into agentic AI with a hands-on introduction to building a simple but functional AI agent. Learn the …
Read articleWhat is AsyncAPI? The Standard Your Event-Driven Architecture Needs
AsyncAPI brings the same contract-first discipline to event-driven systems that OpenAPI brought to REST. For enterprise …
Read articleTasks, Skills, and Tools: The Essential AI Agent Framework
Learn the three core components every production AI agent needs: tasks define what to do, skills define how, and tools …
Read articleAPI Governance for AI Agents: How to Avoid Agentic Technical Debt
When every team can deploy an agent, API governance becomes the difference between compounding value and compounding …
Read articleWhat Is MCP? A Practitioner's Guide to Model Context Protocol
Model Context Protocol (MCP) is the standard for agent-to-tool communication. What it actually provides, how the spec …
Read articleAI Agent Orchestration Patterns: Single, Sequential, Parallel, and Hierarchical
Choosing the right orchestration pattern is one of the most consequential decisions in AI agent architecture. Compare …
Read articleHow to Design APIs for AI Agent Consumption
Your APIs were designed for human developers, but agents read them differently. A practical guide to making APIs truly …
Read article
Matt McLarty
Co-Founder
Chief Technology Officer at Boomi
Matt McLarty is the Chief Technology Officer for Boomi. He helps organizations around the world thrive in the age of AI. Starting his career in financial services, Matt previously led global technical teams at Salesforce, IBM and CA Technologies. Matt is an internationally known expert on AI, APIs, microservices, and integration. He has co-authored books for O'Reilly, co-hosts the API Experience podcast, and is co-author of the book Unbundling the Enterprise from IT Revolution.
Speaking & Media
Book
Unbundling the Enterprise
IT RevolutionCo-authored guide to modern enterprise architecture and the composable enterprise.
Book
Microservice Architecture
O'Reilly MediaCo-authored comprehensive guide to designing, building, and deploying microservices.
Podcast
API Experience Podcast
Co-host of the podcast exploring API design, strategy, and developer experience.
Agentic Solution Patterns: From Chatbots to Multi-Agent Systems
Four enterprise agentic patterns — from chatbots to multi-agent systems. The real unlock is combining deterministic and …
Read articleLearning Path • Module 1
agent-fundamentals
Agentic Primitives: 6 Building Blocks Every AI Agent System Needs
The six fundamental building blocks of AI agent systems: actors, tools, instructions, coordination, interactions, and …
Read article