Issue #77

Customer expectations keep rising. Support budgets don't. On July 9, Fin and AWS are hosting a live executive session on how leading enterprises close that gap: scaling AI-powered support while simplifying how they buy it.

You'll see how to resolve an average 76% of conversations with Fin on AWS enterprise-grade infrastructure, procure through AWS Marketplace to put committed cloud spend to work, and turn the Fin and AWS collaboration into lower support costs. Register for the live session to see how.

Save your spot

In my latest API Platforms for Scale podcast, I talk with Andreas Reetz of DATEV, a major German software and IT services company. Millions of small and medium sized enterprises and tax professionals depend on their services for financial compliance and business management. Andreas shared insights on how he runs DATEV’s API governance function, to support 4.5k engineers. Our discussion covered:

Get the episode on YouTube, Apple Podcasts, and Spotify.

Here are other interesting links for you this week.

What if the next wave of innovation is driven by API consumers instead? Kin Lane in this thought-provoking article challenges traditional API thinking, arguing that governance and control are shifting closer to where APIs are consumed, particularly by AI agents. As agentic AI reshapes how applications discover and use APIs, the gateway itself may need to evolve.

Your APIs may work perfectly for developers, but will they work for AI agents? Kristopher Sandoval outlines ten practical factors that determine whether an API is truly AI-ready, from machine-readable documentation and access controls to observability and MCP support. As agentic AI changes how APIs are discovered and consumed, these considerations are quickly becoming essential rather than optional.

Three AI Blind Spots That Could Be Costing You Developers Developers aren't just searching Google anymore, they're asking AI which tools to use. Adam DuVander explores three often-overlooked blind spots that determine whether AI recommends your product, how it evaluates your offering, and whether developers can successfully adopt it. As AI increasingly shapes the developer journey, visibility may depend on far more than traditional SEO.

Giving AI agents unrestricted access to production APIs might seem powerful but it could also become your biggest governance risk. Ahmet Soormally explores a different approach: allowing agents to execute only pre-approved GraphQL operations rather than creating their own at runtime. As organisations hand more autonomy to AI, controlling what agents are allowed to do may become just as important as giving them access in the first place.

After years of discussion, HTTP has a new method. But is it just another addition to the specification, or could it change how APIs are designed? Alexander Karan explores the arrival of the new QUERY method and why it addresses a long-standing gap in HTTP. For API designers and architects, it could signal a subtle but significant shift in how complex read operations are handled.

MCP is evolving at a remarkable pace, but are you keeping up? Prachi Jamdade highlights the key changes, security considerations, and architectural shifts that every MCP builder should understand before the next wave of adoption. As enterprises move from experimentation to production, staying current is becoming just as important as building quickly.

Building capable AI agents is no longer the hardest challenge. Governing them is. This thought-provoking article argues that as AI agents begin making high-impact decisions and interacting with enterprise systems, the focus must shift from what agents can do to what they should be allowed to do. It explores why accountability, authority, and governance are becoming the defining challenges of the agentic AI era.

API management is no longer just about gateways, rate limits, and documentation. This article explores how AI is reshaping the entire API lifecycle, from automated governance and anomaly detection to predictive analytics and intelligent security. As API ecosystems grow in scale and complexity, AI is emerging as a powerful tool for helping platform teams stay ahead.

The most useful AI agents don't wait for instructions, they react to what's happening around them. This article explores how webhooks, event streams, and real-time notifications are enabling AI agents to respond automatically to changes in external systems. As organisations build more autonomous workflows, event-driven architecture is emerging as a key ingredient for making agents truly proactive.

Building an MCP server is easy. Building one that performs reliably in production is another matter. This article by Bump.sh outlines four practical principles for designing efficient MCP servers, from reducing unnecessary complexity to creating predictable, agent-friendly interactions. As MCP adoption accelerates, thoughtful design is becoming a key differentiator.

What if the future of API innovation isn't creating new standards, but extending the ones we already have? Kin lane explores how OpenAPI's vendor extension mechanism enables organisations to add powerful gateway and operational capabilities without abandoning the industry's most widely adopted API specification. It's a timely reminder that sometimes the most impactful innovations are built on top of existing standards, not alongside them.

Join the Fin and AWS team on July 9 to see how you can scale customer support with AI. Save your spot.

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