Issue #75

AI is moving fast and most people are falling behind. 

The Rundown AI keeps you ahead of the curve. 

It's a free AI newsletter that keeps you up-to-date on the latest AI news, and teaches you how to apply it in just 5 minutes a day.

Plus, complete the quiz after signing up and they’ll recommend the best AI tools, guides, and courses — tailored to your needs.

Sign up to start learning.

Miguel Quintero is a platform engineer and a member of the OpenAPI Technical Steering Committee. Miguel has helped several companies with API governance and platform teams. In this podcast episode I recorded with him, he shares stories from the trenches implementing API governance in large organisations.

Bill Doerrfeld explains that an MCP gateway provides a single point for authentication, authorisation, role-based access control, and credential management across all MCP servers. Rather than allowing agents direct access to tools and services, organisations can define which users, teams, or agents are permitted to access specific capabilities, reducing the risk of overprivileged access and unauthorised actions.

Roy Bar Yosef presents the “agentic stack” as a layered architecture comprising the AI model, orchestration components such as MCP servers, and the API layer where decisions are translated into real-world actions. The central argument is that security failures at the API layer can undermine even well-protected AI models.

Rather than treating APIs solely as technical interfaces, Moseif positions them as strategic business assets that drive integrations, automation, digital ecosystems, and revenue generation. AI can help API leaders navigate the growing complexity of API portfolios by transforming large volumes of operational and usage data into actionable insights.

The article argues that if Anthropic’s projections prove accurate, current approaches to AI governance, regulation, and risk management may be insufficient. This would require policymakers and industry leaders to move beyond discussions of model performance and focus instead on questions of control, accountability, alignment, and the governance of increasingly autonomous systems.

While MCP has emerged as a promising standard for connecting AI agents to tools and services, organisations often face significant challenges when discovering, configuring, authenticating, and maintaining MCP integrations. The result is a poor developer and user experience that slows adoption and increases operational complexity.

Art Anthony explores a provocative idea: the future of SaaS may not be about better user interfaces, but about better APIs. As AI agents take on more work, the companies best positioned to win could be those whose services are easiest for machines—not humans—to consume.

What if your AI agent only woke up when something actually changed? For anyone building AI agents, research workflows, or API-driven monitoring solutions, this launch offers an interesting glimpse into how the next generation of autonomous systems may stay current with a constantly changing web.

Everyone is talking about MCP, but is it simply the next API standard or something much bigger? This guide explores why MCP is rapidly becoming the connective tissue between AI agents and enterprise systems. More importantly, it raises a question every API leader should be asking: what happens when software is designed not just for developers, but for autonomous agents?

Based on a QCon London 2026 presentation by Ian Cooper , this article explores why managing asynchronous APIs becomes significantly more complex at scale, and how leading engineering teams are tackling discovery, governance, and operational visibility. It also highlights a growing shift towards treating event-driven interfaces with the same discipline traditionally reserved for REST APIs.

AI can generate content at unprecedented speed, but there's a catch: much of it sounds remarkably similar. ApyHub explores why content uniqueness is becoming a competitive advantage in an AI-saturated world and how organisations are rethinking content creation, SEO, and scalability.

Zylos explores the emerging discipline of "graceful degradation"—how AI agents can continue delivering value when models, tools, APIs, or external services become unavailable. Rather than failing outright, the most resilient systems adapt, recover, and operate with reduced capabilities.

Context Hub is an open-source project from Andrew Ng that helps AI coding agents access accurate, up-to-date API and SDK documentation instead of relying on stale training data or noisy web searches. It provides a curated, versioned documentation registry that agents can query via a simple CLI tool (chub) to retrieve language-specific documentation when generating code. Example prompt to your agent: "Use the CLI command chub to get the latest API documentation for calling OpenAI. Run 'chub help' to understand how it works."

Bryam Vega proposes an eight-stage API delivery flowline that treats the API contract (typically OpenAPI) as the primary artifact throughout the lifecycle. The model combines AI-assisted API design with governance, automated quality gates, documentation generation, SDK generation, developer adoption, and feedback loops, creating a continuous path from specification to production. He provided demo repos for the flowline here.

Emmanuel Paraskakis spoke at FOST New York 2026 on “Design OpenAPI with Skills”. He has shared his talk slides here.

Speak your prompts into ChatGPT or Claude and get detailed, paste-ready input that actually gives you useful output. Wispr Flow captures what you'd cut when typing. Free on Mac, Windows, and iPhone.

Try Wispr Flow free

The Ikenna Consulting Newsletter curates intelligence on the trends, technologies, and practices shaping API platforms.