API World + CloudX + Dev Innovation Summit 2024

Sridhar Kunisetty, Equinix, Principal Architect

An API linter plays a crucial role in ensuring that API specifications adhere to established standards, best practices, guidelines, and are free from potential errors. It is an essential component in the development process to ensure that APIs are well-designed, consistent, maintainable, reliable, secure and follow the organization's conventions and guidelines.

We present a new approach to API linting by harnessing the power of Generative AI (GenAI). Our solution involves training a Large Language Model (LLM) to act as an Advanced API Linter, capable of not only answering correctness queries but also analyzing API specifications and providing a comprehensive list of errors, violations, and issues.

Unlike traditional API linters, our GenAI solution eliminates the need for complex validation rules and specialized expertise. By training the LLM with our organization's API standards, best practices, and guidelines, we enable it to understand and enforce these rules effortlessly. Moreover, the training process is straightforward, and we can alternatively provide the necessary content as a context in the prompt to the LLM.

One of the key advantages of our GenAI approach is its user-friendliness. Instead of grappling with new syntax or programming languages to define validation rules, users can express their requirements in plain English. This democratizes API linting, empowering developers to improve API quality through self-service and facilitating the seamless adoption of an API-First approach.

During this session, we will showcase a range of use cases that demonstrate how GenAI can be leveraged to achieve advanced API linting capabilities. Additionally, we will explore the potential of utilizing a Small Language Model (SLM) as an alternative to the LLM, opening up new possibilities for API linting efficiency.

Join us as we unveil the future of API linting, where GenAI revolutionizes the development process, enhances API quality, and empowers developers to build robust and reliable APIs effortlessly.

Anushrut Gupta, Hasura, Senior Product Manager, Generative AI

“Over the last 3 months, summarize the top billing issues faced by my enterprise customers within the first 30 days of their onboarding.”

On the surface, building an internal AI customer intelligence application that can answer questions like this is a perfect use-case for Gen AI.
However, building a production ready app that retrieves the data (RAG) before hauling it off to your favorite LLM for summarization soon becomes a terrible engineering experience.

The data is spread across 3 places: a tickets database (eg: elastic), a CRM (eg: salesforce) and your user-accounts transactional database (eg: postgres).
In production, your app can’t access the data from these databases directly. Given security & privacy concerns, your app won’t have direct access to these databases.
Making independent retrieval requests to each of these sources and then joining them in memory might be prohibitively expensive and needs a level of query planning to do efficiently.
Moving all data into one location is expensive to build, maintain and govern
Predictable quality is further made hard because underlying data formats and storage interfaces are continuously changing.
Different types of user queries might require additional filtering and joining of data, which becomes hard to generalize.

APIs solve almost all of these very well known challenges. APIs offer standardization and security. APIs can provide a stable contract to interact with underlying data.

And in all likelihood, you already have APIs on these internal and external data sources.

Ironically, while APIs have become a necessity for other parts of the stack, they are clearly not the first thing that AI engineers building RAG reach for.

In this talk, we’ll discuss:
Why API based retrieval doesn’t work well for RAG
What we need from our existing internal and external APIs to make them RAG ready
How we can get existing APIs to become RAG ready without needing to rebuild the APIs

This talk will be technical, with code demos (possibly with some live coding!) and end with key resources (reference architectures, API best practices, tools/technologies) that attendees can take back to their work.

Matt McLarty, Boomi, CTO & VP, Boomi Innovation Group

As AI becomes more prevalent, communication between API endpoints is expanding rapidly. The current API economy is just the tip of the iceberg compared to what lies ahead in an AI-driven future. In this landscape, APIs are crucial for enabling AI integration and readiness, fundamentally transforming application development.

Discover techniques for strategic AI implementation, responsible automation, and effective API management to establish an AI-ready enterprise. Whether you’re an API developer, AI practitioner, or business stakeholder, this talk will provide insights for effective AI orchestration and turning AI readiness into a competitive advantage.

Key Takeaways:
- Practical methods to enhance AI integration with APIs
- Using AI ethically with APIs
- Insights on achieving AI readiness and avoiding pitfalls

Vishal Motwani, Numbers Station AI, Founding Product Manager

Unlock the power of AI in data analytics with Numbers Station's bespoke platform. Join Vishal Motwani, Founding Product Manager of Numbers Station, and uncover how Large Language Models (LLMs) are revolutionizing production-level data workflows. 

Via a multi-agent architecture and embeddable API, Numbers Station is built to seamlessly integrate with your existing knowledge sources—dashboards, databases, APIs, dbt, query logs and more. Numbers Station’s AI agents actively search, query, analyze, and take it two steps further—suggesting the next best action and automating downstream tasks in real-time.

Whether you're looking to embed Generative AI into legacy systems or elevate your organization's data capabilities, this session offers a glimpse into the future of AI-powered analytics that won't disrupt your current infrastructure. Don't miss this opportunity to supercharge your data strategy!

Ken Huang, DistributedApps, CEO and Chief AI Officer

This presentation introduces a comprehensive framework for testing and validating the security of generative AI applications, particularly those built on large language models (LLMs). Developed by Ken Huang (the Speaker) and World Digital Technology Academy's AI Safety, Trust, and Responsibility (STR) working group, the framework addresses the new attack surfaces and risks introduced by generative AI.

The standard covers the entire AI application stack, including base model selection, embedding and vector databases, prompt execution/inference, agentic behaviors, fine-tuning, response handling, and runtime security. For each layer, it outlines specific testing methods and expected outcomes to ensure AI applications behave securely and as designed throughout their lifecycle.

Key areas of focus include model compliance, data usage checks, API security, prompt injection testing, output validation, and privacy protection. The framework also addresses emerging challenges like agentic behaviors, where AI agents autonomously perform tasks based on predefined objectives.

Harsh Sharma, Shell, Associate Software Engineer

How to build API/Interfaces using Azure Integration Services like logic App, APIM, Service Bus, Function App.
 

Michael Kwan, Broadcom, Architect

Quantum computing seems like a distant-future technology, but if you consider the pace of enterprise modernization, the quantum threat may be just around the corner - and APIs are a primary target. When is Q-day exactly? Nobody knows yet, but equally unknown is the scale of the corrective measures that will be required of your API infrastructure.

In this presentation you will learn:
- How quantum computing introduces a new security risk
- What is the API-specific exposure associated with this threat
- How and when do you need to start preparing your APIs
- What will be the costs in terms of computing resources and API retrofit projects
- What we are learning from post-quantum API security research and initial tests so far

Cameron Delano, F5, Sr Strategic Architect 
Corey Ball, Moss Adams, Senior Manager - Penetration Testing

F5 secures and optimizes traffic for some of the largest AI projects in the world, and organizations are planning to spend an average of 18% of 2025 IT budgets on AI implementation.
What many are missing is that outside of a few edge cases, nearly all training, usage, attacks, and data loss against AI models come through APIs, and APIs themselves expose critical information about models such as data labels and confidence scores, facilitating model theft, transfer attacks, and other issues unique to securing LLMs.
In this session, we’ll talk about the ties between AI security, APIs, and how to structure a Defense in Depth architecture to secure your AI factory and models from the beginning, rather than after the fact.

Shashank Ashtikar, M9, Co-Founder & CTO

With the viral adoption of AI driven by commercially available LLMs newer venues of business have opened up. These new business models are driven by the likes of Co-pilots and virtual agents that bring in tremendous productivity gains across business workflows. Concepts like Generative AI and Conversational AI have already gained mainstream popularity. A new branch of AI that is gaining momentum is that of Agentic AI. This talk is geared towards identifying mechanisms that make inter-agentic communication possible and the ontology of such interactions solving for needed concepts of roles, tasks, memory, tools, context and prompts for a scalable and reliable inter-agentic business workflow.
 

Ed Olson-Morgan, Marsh McLennan, Core API & Innovation Lead

Driving value from generative AI isn't just about large language models. Integrating them with the right data, services and supporting capabilities through APIs is just as important.

Learn how Marsh McLennan's Generative AI Services project built an API-based environment to nourish AI experimentation and underpin AI impact through production applications serving their 90,000 employees as well as a world-wide client base.

Brenton House, IBM, Principal Cybersecurity and AI Advisor

Generative AI has revolutionized the tech world in the past months. With its insatiable thirst for data, all eyes have turned to APIs and the security (or lack of) protecting them. Large data breaches have become so common that security researchers are overwhelmed with the terabytes of leaked data finding its way to the Dark Web. Learn both the ugly secrets behind cyber threats and the successful strategies used to stop them.
 

Dominik Rampelt, APICHAP, CEO & Co-Founder

Artificial Intelligence is rapidly transforming every facet of our lives, including the way we approach API development. In this talk, we will explore the profound impact AI will have on developers and the necessary steps to harness its full potential. The future of API development will focus heavily on an API-Contract First approach, where developers become architects defining APIs and data flows. The implementation will then be assisted by various AI tools.

Join us to discover how tools like APICHAP enable developers to implement APIs for your services and integrate with any datasource in just a few seconds. Learn how to leverage the power of AI in your daily development work. In the future, the best API developers won't just write code—they'll design the blueprint for AI to follow.  

Amol Gote, Innova Solutions, Solutions Architect

In the evolving landscape of financial services, implementing a cash flow underwriting system aims to expand credit access and enhance risk assessment. This session will cover an approach that leverages open banking, machine learning, and dynamic underwriting rules to provide creditworthiness evaluation beyond traditional credit scoring methods. It will cover the case study of iCreditWorks - a Fintech organization where this pattern was implemented.

The system consists of four critical components:

(1) A financial data aggregator to securely link customers' bank accounts, utilizing open banking APIs and traditional integration techniques.

(2) Collaboration with a specialized partner that employs machine learning models to analyze transaction data, generating a comprehensive cash flow score and identifying verifiable income.

(3) Developing and implementing underwriting rules that integrate the cash flow score and income data to make informed lending decisions.

(4) The seamless integration of these components into a mobile application and backend infrastructure, ensuring a user-friendly experience and efficient loan application processing.

This session discusses the cash flow underwriting system's design, implementation, and strategic significance. It highlights its potential to extend credit access by surpassing traditional credit scores and opening new avenues for financial inclusion and risk assessment. It also introduces a technical implementation approach for cash flow underwriting by integrating multiple services and using open banking for bank account linking for transaction data.

Vamsi Ravula, Red Hat, Developer Advocate
Hugo Guerrero, Red Hat, Sr Principal Developer Advocate

Locationless API management is a paradigm shift in API governance and security. This innovative approach allows organizations to efficiently manage their APIs distributed across multiple clouds and clusters without exposing them publicly over the internet. Instead, it leverages a sophisticated layer seven service network, offering a secure and seamless solution for API management. By operating locationless, businesses can maintain a high degree of control and privacy over their APIs, mitigating the risks associated with public exposure while facilitating efficient communication between services across diverse deployment environments.

A Layer 7 service network provides the necessary infrastructure to establish secure connections between services, regardless of location. Through this network, APIs can be efficiently managed and accessed within a controlled environment, ensuring that sensitive data and functionalities remain protected. This locationless API management approach not only enhances security but also streamlines operations, as it minimizes the complexities of public-facing API management. As organizations continue to prioritize data privacy and security, locationless API management, powered by technologies like a Layer 7 service network, emerges as a game-changing solution that empowers businesses to securely manage and utilize their APIs without the need for public internet exposure.

Ayesha M. Ali, Metavisionaries, Co-Founder / Creative Director

This session will explore the transformative potential of APIs in the realm of Fusion Tech Art and interdisciplinary content creation. Emphasizing the integration of frontier technologies such as Artificial Intelligence (AI) and Machine Learning (ML), we will discuss how APIs serve as the vital connectors enabling seamless communication and collaboration across diverse creative fields. Participants will gain insights into how APIs facilitate innovative approaches that merge art, technology, fashion, and more.
Objectives:
• Introduce the Concept of Fusion Tech Art: Explain the importance and impact of Fusion Tech Art in the modern digital and creative industries.
• Highlight the Role of APIs: Discuss how APIs act as the backbone of integrating AI, ML, and various creative disciplines.
• Demonstrate Practical API Integration Techniques: Showcase new interdisciplinary approaches enabled by APIs and practical techniques that can be adopted by entrepreneurs and creatives.
• Case Study: Present a detailed case study of my project sent to space in collaboration with NASA and SpaceX, illustrating the power of API-driven integration.
• Ethical and Sustainable Practices: Address the ethical considerations and sustainability issues related to API-driven AI and tech projects, both on Earth and in space.
Session Outline:
1. Introduction to Fusion Tech Art:
• Definition and significance of Fusion Tech Art in contemporary creative practices.
• Overview of how APIs enable the integration of AI, ML, and other technologies into creative projects.
2. Current Landscape of Frontier Technologies:
• In-depth look at the latest developments in AI, ML, and their applications through APIs.
• Examples of cutting-edge tools and platforms that utilize APIs for interdisciplinary integration.
3. Seamless Interdisciplinary Techniques through APIs:
• Step-by-step guide on adopting an interdisciplinary approach using APIs.
• Demonstration of API functionalities that enable the merging of art, technology, fashion, and other fields.
4. Case Study: Art Project to Space via APIs:
• Detailed narrative of my project sent to the International Space Station (ISS) with NASA and SpaceX, focusing on the API integrations that made it possible.
• Insights into the creative process, collaboration, and execution of the project.
• Lessons learned and tips for aspiring creatives and entrepreneurs on leveraging APIs.
5. Ethics and Sustainability in API-Driven Fusion Tech Art:
• Discussion on the ethical implications of using APIs in AI and content creation.
• Sustainability discourse and its importance in tech-driven projects.
• How to ensure responsible and sustainable practices when utilizing APIs in creative projects.
Target Audience:
• API developers and technologists interested in the creative applications of their work.
• Artists and designers looking to integrate technology into their projects using APIs.
• Entrepreneurs and creatives seeking innovative interdisciplinary approaches.
• Educators and students in the fields of art, technology, and design.
Expected Outcomes:
• Increased awareness and understanding of Fusion Tech Art and the role of APIs in enabling it.
• Practical knowledge of API-driven tools and techniques for merging diverse creative disciplines.
• Inspiration from real-world examples and successful case studies.
• A framework for ethically and sustainably implementing API-driven AI and tech in creative projects.