Nafitko Capabilities

For this episode of the Naftiko Capabilities podcast we sat down with Budhaditya Bhattacharya from Tyk and Supreet Nagi from Northwestern Mutual to talk API governance. Supreet shares his practitioner perspective on achieving zero touch governance, where compliance is baked into the development lifecycle rather than being a gate or checkpoint. Budha discusses governance as consistency, reliability, and predictability for APIs, and the importance of reframing governance from something that creates friction to something available by design. We explore the cultural shift needed to get stakeholders aligned, the value of maturity models for tracking progress, and the importance of iterative value delivery over big-bang governance projects. Supreet also discusses his new book From Chaos to Connectivity, the API Practitioner's Handbook.

For this episode of the Naftiko Capabilities podcast we had a conversation with Dániel Kovács from Speakeasy about their newly released agent skills and what they signal for SDKs and developer experience. Daniel discusses how coding agents like Claude and Codex are changing workflows, and how deterministic SDK generation can prevent costly contract mismatches between clients and APIs. Daniel explains agent skills as on-demand context snippets and how Speakeasy uses them for common tasks like getting started with their CLI and improving OpenAPI specs for better SDK outcomes. A key focus is balancing AI-driven, non-deterministic changes with deterministic processes using OpenAPI overlays to refine generated specs, improve method naming, and organize endpoints.

In today's Naftiko Capabilities podcast we sat down with freelance journalist and developer experience expert Jennifer Riggins about the current state of developer experience amid rapid AI adoption. We discussed how AI can improve individual productivity and broaden participation in building technology, while raising concerns about security, missing guardrails, and best practices. We explored platform engineering as a conduit for AI success, the persistence of organizational silos, and the reality that enterprise “swarms of agents” aren’t happening yet due to legacy constraints and unresolved integration and data challenges. This episode also touches on job precarity, unemployment, at-will employment impacts, and implications for junior developers.

As part of recent work on spec-driven development I sat down for conversation with Chris Hood about experience-based API design, arguing that APIs should be expressed in human, business-oriented language rather than CRUD-centric engineering terms to improve contextual understanding. we discuseds why traditional REST approaches may be insufficient for AI and agent-based systems, concerns about introducing new protocols like MCP, and the “agentic API” paradigm for agent-to-agent communication with built-in security and web-embedded protocols. We also explore how AI could help by making APIs more intelligent and contextual, and by incorporating feedback loops where agents and humans report missing skills.

I sat down with Emmanuel Paraskakis to talk about the intersection of API products, API design-first, and spec-driven development. I think it is important that we revisit how we got here and Emmanuel had a front-row seat for the emergence of API design-first as part of his work on Apiary and API Blueprint, and markdown format used to define and mock your APIs before you development them. Emmanuel shared insight about how we can use product requirement definitions and problem statements to help align out engineer with product specs, bringing the much needed business alignment required to move in the direction enterprises are needing to go in 2026.

In this episode, I sit down with Clemens Vasters, Principal Architect for Messaging and Real-Time Intelligence Services at Microsoft, to talk about JSON Structure — a new spec designed to take on the territory JSON Schema has dominated for years. Clemens shares the origin story behind JSON Structure, why JSON Schema and Avro both fell short for Microsoft's real-time data pipeline needs, and how he built a cleaner, more focused data definition language that keeps the familiar shape developers already know while cutting out the complexity that breaks tooling.

This episode of the Naftiko Capabilities podcast features a full conversation with Patrick Kelly (SideKo, Port of Context) about context engineering for AI agents, MCP, and evolving API tooling. Patrick explains SideKo’s shift from generating developer-facing API products (docs, SDKs, mock servers from API specs, with customers like Prudential) toward Port of Context as agent consumption grows, including leveraging techniques like giving agents SDKs and dynamically exposing documentation. Kin shares his background across OpenAPI/Swagger tooling, SDK efforts (including Microsoft Kiota and dynamic SDK sizing), API management, and his Postman experience with collections and right-sizing context windows. He describesNaftiko’s work-in-progress API consumption gateway/proxy and a catalog of sandboxes for tools like Notion, GitHub, and Slack, organized into tagged capabilities to support safe experimentation for design partners (including banks) and to enable mocking and generating agent skills/cards. The conversation covers evaluating agent API usage more precisely via proxy/state control approaches, bridging enterprise governance and MCP adoption, and Port of Context’s runtime techniques (including translating many upstream MCP tools into a smaller set of agent-facing tools and exploring a virtual file system approach) while iterating safely through measurement. Patrick outlines spec linting and rules for OpenAPI-to-MCP generation, emphasizing improving descriptions so they work as tools, and handling messy real-world specs by letting agents explore context dynamically rather than stuffing everything into the prompt. Ken closes by noting the tactical vs. strategic perspectives, inviting listeners to connect for recorded conversations and sharing his contact details and recording times.

In this episode of Naftiko Capabilities we sit down down with Anna Daugherty of Arnica to delve into the important topic of application security governance. From pinpointing the sweet spot for identifying vulnerabilities to the role of governance in the development workflow, this episode covers it all. Learn how AppSec practices are evolving, the difference between AppSec and AI security, and how enterprises can make their security measures more effective and less intrusive.

In this episode of Naftiko Capabilities podcast we dive deep into the complex landscape of artificial intelligence. Through conversations with experts like Simon Wardley, Kevin Swiber, and Mike Amundsen, we explore the broad impacts of AI, from geopolitical considerations to practical technology applications. Learn about 'vibe coding,' large language models, and the balance between hype and realistic expectations in AI development. Ideal for tech enthusiasts, industry professionals, and anyone looking to stay informed about AI's evolving role in society.

In this episode of the Naftiko Capabilities podcast, I sit down with Kevin Swiber to tackle one of the hottest debates in AI integration: are agent skills going to kill MCP? Spoiler — it's more nuanced than that. Kevin breaks down the difference between MCP tools (the what) and agent skills (the how), explains why most enterprise teams are still using AI as a glorified Stack Overflow, and makes the case that skills are more accessible to non-developers than MCP servers will ever be. We also dig into the context window problem plaguing MCP hosts, why progressive disclosure matters, and when MCP is overkill for headless agents. If you're trying to cut through the noise and figure out what actually matters for AI-powered workflows, this one's for you.