Issue #76

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.

On July 12th, I’ll be running an API Platform Roundtable with the title “Agent-Ready APIs: How API Platform Teams Are Preparing for Agentic Workflows“. I will be hosting this one hour Zoom discussion, and in attendance will be API architects and API product managers from large enterprises. We will be looking at questions like “What's the most significant AI-agent question your API platform team is currently trying to answer?“ and “If you had £100k to prepare your API platform for agentic workflows, where would you invest first?“. One person who had a seat reserved can’t make it, and so we have an open slot. There is one requirement to attend though - you must be leading or overseeing an API platform team, and you need to ready to fill out our survey as part of our Beyond the Linter Study. If you would like to attend, email me at [email protected].

For years, developers have been forced to choose between GET and POST for complex queries, even when neither was quite right. Now, the IETF has officially standardised a new HTTP method: QUERY. Designed for read-only operations that require a request body, it could simplify API design, improve caching behaviour, and address a long-standing gap in the HTTP specification.

MCP has rapidly become the standard for connecting AI agents to tools and system but there has been one major gap holding back enterprise adoption. Frederic Lardinois explores a new authorisation framework designed to bring fine-grained access control, delegated permissions, and stronger governance to agent interactions. As organisations move from experimentation to production, the question is no longer whether agents can access systems, but whether they should.

F5 announced AI-powered enhancements to its web application and API protection solutions, introducing features like air-gapped API discovery and virtual patching to defend against rapidly evolving AI-driven threats. The solutions aim to protect enterprises by dynamically assessing risks and preemptively stopping exploits.

Paul Sawers explores Stack Overflow's latest bet: a knowledge-sharing platform designed specifically for AI coding agents. The goal is to tackle a growing challenge in agentic systems—valuable insights disappear when an agent's session ends, forcing others to rediscover the same solutions.

Hugh Carroll explores a growing challenge for DevSecOps teams: as AI generates more APIs, traditional security reviews risk becoming a bottleneck. The solution? Embedding deterministic security guardrails directly into AI-assisted development workflows so vulnerabilities can be identified and addressed before they reach production.

What if the biggest AI security risk isn't the model itself, but what happens after it starts taking action? Claudio Acquaviva and Nadav Lotan explore the growing need for runtime protection in agentic AI systems, where agents can access tools, call APIs, and interact with enterprise data autonomously. As organisations move beyond chatbots and into AI-driven execution, security teams are being forced to rethink where and how controls should be applied.

What happens when an AI agent needs its own account? This Cloudflare announcement tackles an important challenge in the agentic AI era: enabling agents to access services without exposing long-lived credentials or granting excessive permissions. The approach could make it easier for agents to safely interact with platforms while maintaining security and control.

This AWS announcement showcases a new approach to incident management, combining AI agents with observability data to automate investigation and root-cause analysis. As agentic systems gain access to operational tools, the line between monitoring and autonomous operations is starting to blur. For platform engineers, SREs, and DevOps teams, it's a fascinating glimpse into how AI agents may transform incident response in the years ahead.

What’s the secret to staying ahead of the curve in the world of AI? Information. 

Luckily, you can join 2,000,000+ early adopters reading The Rundown AI — the free newsletter that makes you smarter on AI with just a 5-minute read per day.

Sign up to start learning.

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