Introduction

Next week, I’ll be at ApiDays Helsinki & North 2025, where I’ll be presenting two talks. The first talk titled “Building High Performance API Platform Teams”, and the second talk is titled “AI APIs: Taming the Wild West with AI Gateways”. Do reach out if you are at the conference.

In this issue, I am renaming the ‘Runtime AI Governance’ section to ‘AI API Consumption Governance‘ to better reflect the focus of that section, which is about defining the policies, practices and processes for consuming AI model APIs. This is important as organisations build more AI applications. I am also renaming the ‘API Governance and Delivery‘ section to ‘Platform API Production Governance’ to make it clearer that the focus is on governing business platform APIs created by an API provider. In Gregor Hohpe’s Platform Strategy, he describes business capability platforms as platforms that expose functions from the business domain. These platforms have APIs that not only enable internal integration, but also integration across organisational boundaries, leading to the development of open business ecosystems. Governing these APIs is the focus of my governance toolkit, and the Platform API Production Governance section.

Enjoy!

Interesting Content for the Week

AI API Consumption Governance

MCP Is Here — This is the Infrastructure It Needs : Eyal Solomon addresses the advent and implications of the Model Context Protocol (MCP), a developing standard aimed at standardising how AI agents interact with external tools and data sources.

AI Reliability Engineering For More Dependable Humans :In this article Christian Posta introduces and explores the concept of AI Reliability Engineering (AIRE), presenting it as a significant advancement for enhancing software reliability through the integration of artificial intelligence agents into platform engineering workflows

Unlocking Machine-to-Machine Intelligence: How MCP Shapes Agentic Workflows : This article by Xano presents the operational details of the Model Context Protocol and its significance in enabling sophisticated machine-to-machine (M2M) interactions and agentic workflows.

The AI Agent Reality Gap: Why 75% of Agentic AI Tasks Fail in 2025 (And How to Fix It): Zdenek "Z" Nemec explores why AI Agents frequently falter and suggests the development of specialist agents for improving their efficacy.

 Pete Bryan, et al. (2025). Taxonomy of Failure Mode in Agentic AI Systems [white paper]. Microsoft. : In this white paper the authors identify, analyse, and categorise potential vulnerabilities and failure modes within agentic AI systems, with a particular emphasis on multi-agent configurations.

Streamline scalable AI governance with Domino in AWS Marketplace : James Yi and David Schulman emphasise the critical challenge of balancing rapid AI innovation with the imperative for stringent governance, including transparency, repeatability, and risk management.

Platform API Production Governance

llm-d: Distributed Inference Serving on Kubernetes : Christian Posta introduces llm-d, a novel open-source project designed for distributed inference serving on Kubernetes. It seeks to address the inherent challenges in operating cost-effective and high-performing inference platforms for Large Language Models (LLMs).

Embracing the Design-First Methodology with SmartBear API Hub and ReadyAPI: Nick DiMartino shares that defining and agreeing upon the API's contract or interface before commencing any coding leads to more efficient development cycles, enhanced collaboration, a reduction in software defects. SmartBear's tooling, specifically API Hub and ReadyAPI, facilitates the adoption and implementation of this approach.

5 Smart API Gateway Strategies to Unlock Developer Productivity: Immánuel Fodor presents that contemporary API gateway practices can significantly enhance the developer experience and productivity, presenting five key strategies that forward-thinking platform teams are employing to achieve these gains whilst concurrently maintaining effective governance, observability, and system performance.

Tools/New Release/Updates

SnippetAI for your API documentation : Snippet AI presents as a solution that integrates directly into API documentation, enabling developers to obtain contextualised code examples by posing questions in natural language.

Kong Event Gateway: Unifying API and Events in a Single Platform : The Kong Event Gateway endeavours to unify Application Programming Interfaces (APIs) and event streams, and facilitating the transformation of real-time data streams into marketable products.

Gloo Gateway 1.19 accelerates context-rich, real-time AI apps alongside expanded support for Gateway API: this release brings new functionalities designed to support production-grade AI applications and ensure up-to-date interoperability with Kubernetes.

Meet Zapier's AI orchestration platform: Add AI agents to nearly 8,000 apps : Significant updates made to Zapier’s AI, introduces a comprehensive approach, encompassing the building of AI systems, their management, and crucially, their governance and security at an enterprise level.

Simplifying Enterprise Connectivity: Traefik Labs Expands Microsoft Partnership with Azure Arc and AKS: Traefik Labs announce an enhanced collaboration with Microsoft, aimed at streamlining connectivity for enterprises operating in hybrid and multi-cloud environments.

Secure by design: Introducing Postman Spec Hub and BYOK encryption: Postman announces the introduction of two significant new features within the Postman platform: Spec Hub and Bring Your Own Key (BYOK) encryption. These additions are designed to streamline the Application Programming Interface (API) development lifecycle and bolster security for Postman users, particularly enterprises.

Upcoming API Conferences

Postman's annual user conference: POST/CON 25. Date: June 3rd & 4th 2025, Location: JW Marriott Los Angeles L.A. Live, Los Angeles, CA Register Here

APIdays Helsinki: Theme: “APIs for Innovation, Intelligence, and Impact” Date: June 3rd & 4th 2025. Location: Pikku-Finlandia, Helsinki Register Here. I will be speaking on ‘Beginning Lean API Governance (with some AI help)’.

Kong API Summit Live 2025, Join developers, leaders, and visionaries from around the world as we explore the latest innovations around APIs, microservices, and AI. Date: Oct 14 - 15, 2025, Location: New York City

APIdays Germany: Theme: “Accelerate AI Use Cases with APIs” Date: July 2nd & 3rd, 2025. Location: Smartvillage Bogenhausen, München, Germany. Register Here

APIdays London: Theme: “No AI Without APIs” Conference Date: September 22nd - 24th, Location: Convene 155 Bishopsgate, London EC2M 3YD

API Governance Consulting

Feedback & Share

I appreciate your feedback. Please help me improve this newsletter by filling out this 1 minute survey. If you find my newsletter useful, please forward and share it with a friend