The EU AI Act for AI Agent Builders
High-risk deadlines moved to 2027, but transparency obligations applied on 2 August 2026 — and they hit conversational …
Read articleBrowse
Topics
Explore articles by topic area, discover featured content, and stay up to date with the latest insights.
Agent Fundamentals
Core concepts and architectural patterns for building AI agents. From ReAct to multi-agent systems, memory management to tool integration.
View articles →Agent Design & Frameworks
Design patterns, frameworks, and methodologies for building production-ready AI agents. From the AI Agent Canvas to testing strategies.
View articles →Protocols & Standards
The protocols and standards enabling agent-to-system and agent-to-agent communication. MCP, AsyncAPI, OpenAPI, and the emerging standards landscape.
View articles →Governance & Operations
Frameworks for governing AI agents in enterprise environments. Risk management, observability, cost control, and avoiding the false economy of speed.
View articles →Enterprise Integration
Connecting AI agents to enterprise systems, data, and workflows. API management, security, authentication, and hybrid human-agent operations.
View articles →Research
Cutting-edge research, academic papers, and scientific advances in agentic AI systems
View articles →Featured Article
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 governance. A practical framework for enterprise agent design.
Read article →Recent
Latest articles
MCP 2026-07-28: The Stateless Rewrite Explained
The newest MCP specification removes sessions, the initialize handshake, and SSE resumability. What breaks, what …
Read articleWho Owns the Agent? Team Topologies for AI
Agents fail organisationally before they fail technically. Who owns an agent in production, who is accountable for its …
Read articleRAG, Tools, or Long Context? A Decision Framework
Three ways to get enterprise knowledge into an agent, each with different failure modes. A decision framework based on …
Read articleCost Attribution for AI Agent Fleets
A single API bill for fifty agents is not a cost model. How to attribute spend per agent, task, and tenant — and build …
Read articleAI Agents and Legacy Systems: The Other 80%
MCP assumes a modern API on the other end. Most enterprise value sits behind SOAP, batch jobs, and green screens. How to …
Read articleIndirect Prompt Injection via Tool Results
The dangerous prompt injection is not typed by your user — it arrives in a tool response. Why the data path is the real …
Read articleThe AI Agent Canvas: Design Agents on One Page
A structured design tool for translating business requirements into agent architecture — before you write code. Nine …
Read articleEvaluating AI Agents: Evals That Predict Production
Benchmarks tell you a model is capable. Evals tell you your agent works. How to build golden datasets, LLM judges, and …
Read article