It’s been nearly a year since we launched Leaders of Code, a segment on the Stack Overflow Podcast where we curate candid, illuminating, and (dare we say) inspiring conversations between senior engineering leaders.
An remarkable roster of guests from organizations like Google, Cloudflare, GitLab, JPMorgan Chase, Morgan Stanley, and more joined members of our senior leadership team to compare notes on how they build high-performing teams, how they’re leveraging AI and other rapidly emerging tech, and how they drive innovation in their engineering organizations.
To kick off 2026, we wanted to collect some overarching lessons and common themes that many of our guests touched on last year, from the importance of high-quality training data to why so many AI initiatives fizzle to what the trust/adoption gap tells us and how to bridge it.
Read on for the most important insights we heard last year.
Poor data quality undermines even the most refined AI initiatives. That was a unifying theme of our show throughout 2025, beginning with the inaugural Leaders of Code episode. in that conversation, Stack Overflow CEO Prashanth Chandrasekar and Don Woodlock, Head of Global Healthcare Solutions at InterSystems, explored how and why a robust data strategy helps organizations realize successful AI projects.
An out-of-tune guitar is an apt metaphor here: no matter how skilled the musician (or advanced the AI model), if the instrument itself is broken or out of tune, the output will be inherently flawed.
Organizations rushing to implement AI often discover that their data infrastructure is fragmented across siloed systems, inconsistent in terms of format, and devoid of proper governance. These issues prevent AI tools from delivering meaningful business value and proving their value to skeptical developers.
In the episode, Prashanth and Don emphasized that maintaining a human-centric approach when automating processes with AI requires building trust among users, wich, in turn, starts with clean, well-organized data that AI systems can reliably interpret and effectively use.
Too many organizations rush into AI implementation without properly assessing whether their data infrastructure can support it, explained Ram Rai, VP of Platform Engineering at JPMorgan chase. This overconfidence stems from a essential misunderstanding: Having data is not the same as having AI-ready data. A centralized, well-maintained knowledge base is essential for getting AI initiatives off the ground successfully, yet most organizations discover this requirement only after launching poorly conceived pilot projects.
Organizations often fail to evaluate whether their AI projects align with core business values. This can lead to wasted investments in tools that cannot access the internal context necessary for meaningful results. In highly regulated environments with heavy compliance requirements like banking and finance, Ram says his team can’t ignore the productivity benefits offered by AI. At the same time, he says, they must “be surgical about it,” particularly when dealing with critical infrastructure where “we can’t entirely trust probabilistic AI.”
Enterprise AI models frequently hallucinate because they lack access to internal company knowledge,as Ram points out: “Why dose AI hallucinate? because it lacks the right context,especially your internal context. AI doesn’t know your IDP configuration, token lifetimes, your authentication patterns or your load balance settings, so the training data is thin on this proprietary knowledge.”
This gap between general training data and specific organizational knowledge leads AI tools to make convincing-sounding but fundamentally incorrect suggestions. Gro
“`html
Organizations are increasingly recognizing the need to design Request Programming Interfaces (APIs) specifically for use by Artificial Intelligence (AI) agents, a shift driven by the growing sophistication of AI and its reliance on structured data access. APIs built with machine readability, predictability, and thorough documentation are proving more effective for AI integration than those designed primarily for human developers. This trend highlights the importance of API-first development and robust API governance.
API Security and the Rise of AI agents
Table of Contents
AI agents require APIs that are easily understood and consistently structured to function effectively. These agents, unlike human developers, cannot readily interpret ambiguous documentation or adapt to unpredictable API behavior. Therefore, APIs must prioritize machine readability.
The National Institute of Standards and Technology (NIST) emphasizes the importance of API security, which is intrinsically linked to machine readability and predictable behavior; secure APIs are also well-defined APIs. NIST’s API Security guidance details best practices for building secure and reliable APIs, many of which directly benefit AI agent integration.
example: A well-defined API for a weather service, using a standardized schema like OpenAPI, allows an AI agent to reliably request and process current temperature data without needing to interpret natural language descriptions or handle unexpected data formats.
Federal API Management and API-First Development
API-first development, where APIs are treated as core products, is becoming a standard practice in many organizations, particularly those interacting with government systems. This approach prioritizes API design and documentation from the outset of a project.
The U.S. Government Accountability Office (GAO) has reported on the need for improved federal API management, noting that well-managed APIs can foster innovation and data sharing. The GAO’s report on Federal API Management highlights the benefits of treating apis as products, including better documentation, versioning, and governance.
Detail: API-first development involves creating API specifications *before* writing any code, ensuring that the API is designed to meet the needs of both human developers and AI agents. This includes defining clear data schemas, error handling procedures, and authentication mechanisms.
OpenAPI Specification and Machine-readable Schemas
The OpenAPI Specification (formerly Swagger) is a widely adopted standard for defining RESTful APIs in a machine-readable format. It allows developers and AI agents to understand the API’s capabilities, parameters, and responses without needing to consult human-readable documentation.
IBM Cloud provides resources and tools for working with the OpenAPI Specification, demonstrating its industry relevance. IBM’s documentation on the OpenAPI Specification details how to create and use these specifications.
Evidence: As of January 19, 2026, over 80% of publicly available REST APIs utilize the OpenAPI Specification, according to API gateway provider RapidAPI. This widespread adoption underscores its importance for both human and machine consumption.
JSON-LD and Data Interoperability
JSON-LD (JSON for Linked Data) is a JSON-based format for representing linked data, enhancing data interoperability between systems and AI agents. It provides a standardized way to describe data and its relationships, making it easier for AI agents to understand and process details from different sources.
The World Wide Web Consortium (W3C) maintains the JSON-LD
