API World 2018 has ended

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

PRO: AI & Machine Learning APIs [clear filter]
Monday, September 10

12:00pm PDT

PRO TALK: Building Conversational Experiences
Conversational interfaces are quickly becoming an essential component of every service and product. Will we ever be able to talk to machines the way we talk to people? Science fiction says we will, but as an industry our early experiences have left a lot to be desired. In this talk we will explore the latest design and development techniques for building natural language interfaces. We will use the Google Assistant, Actions on Google and Dialogflow as example show cases to explore conversational user interface best practices.

avatar for Neto Marin

Neto Marin

Actions on Google Developer Advocate, Google
With more than 15 years of software development experience, Neto Marin has been at Google for 5 years and is currently a Developer Advocate on the Actions on Google team, helping developers create high-quality Actions for Google Assistant. Neto is an expert in mobile development... Read More →

Monday September 10, 2018 12:00pm - 12:50pm PDT
Workshop Room 4

1:00pm PDT

PRO TALK: The Operating System for AI: How Microservices and Serverless Computing Enable the Next Generation of Machine Intelligence
AI has been a hot topic, but there has not been much discussion of the infrastructure and scaling challenges that come with it. How do you support dozens of different languages & frameworks, and make them interoperate invisibly? How do you elastically run abstract code from thousands of different developers with under 15ms overhead? In my time at Algorithmia, we’ve built, deployed, and scaled thousands of algorithms and machine learning models, using every kind of framework. We’ve seen many of the challenges faced in this area; in this talk I’ll share insights into the problems you’re likely to face, and how to approach solving them. In brief, we’ll examine the need for, and implementations of, a complete “OS for AI”: a common interface for different algorithms to be used and combined, and a general architecture for serverless ML which is discoverable, versioned, scalable & sharable.

avatar for Jon Peck

Jon Peck

Developer & Advocate, Algorithmia
A full-stack developer with two decades of industry experience, Jon Peck now focuses on bringing scalable, discoverable, and secure machine-learning microservices to developers across a wide variety of platforms via Algorithmia.com--------Speaker at: DeveloperWeek 2018+19, SeattleJS... Read More →

Monday September 10, 2018 1:00pm - 1:50pm PDT
Workshop Room 4

2:00pm PDT

PRO TALK: My App Broke and It's All the API's Fault
Utilizing a continuous integration pipeline reduces the risk of failure as code is updated for your application. However, evolutions to a codebase no longer represent all of the changes that a developer could make to an application. Modern development heavily depends on utilizing external APIs to speed up the time it takes to ship code; this creates additional risk of failure as an untested change to a 3rd party system can create unexpected downtime for your application. In this talk Shy Ruparel, developer evangelist at Contentful examines strategies to bring API management into your continuous integration pipeline and outlines how that enables your codebase to integrate, change, and play well with systems outside of your control. 

avatar for Shy Ruparel

Shy Ruparel

Developer Evangelist, Contentful
Shy Ruparel is a Python developer by heart with a passion for day-long board games, good jokes and the staying power to wish you a great day on Twitter every single day.

Monday September 10, 2018 2:00pm - 2:50pm PDT
Workshop Room 4

3:00pm PDT

PRO TALK:Autonomous Optimization: Leveraging AI for Quality & Growth
In this talk we look at how Autonomous Optimization (AO) can help us drive quality improvements & growth in our products and services. AO is a new paradigm for leveraging AI (or Machine Learning) without dealing with complex pipelines, algorithms, models, or even data. We present a complete walkthrough & live demo as well as several case studies including comparisons against traditional methodology such as A/B testing or Custom AI implementations. We also look at how experiments that appear perfectly sensible on the surface can still waste precious time and effort when compared to an AO procedure that can virtually guarantee metric improvements simply by eliminating inherent human biases and allowing relevant segments and personal/contextual behavior to emerge out of the optimization process.

avatar for Olcan Sercinoglu

Olcan Sercinoglu

CEO & Founder, Scaled Inference
Olcan is the Founder & CEO at Scaled Inference. Before founding Scaled Inference, Olcan was an engineer in Google Brain, where he worked on efficient inference methods for general-purpose statistical models and task-specific adaptations that can utilize deep learning. Early on at... Read More →

Monday September 10, 2018 3:00pm - 3:50pm PDT
Workshop Room 4

4:00pm PDT

PRO TALK : Supercharging Self-Service API Integration with AI
Using an AI-Driven Model for Self-Service API Integration Developers must often build new applications that pull together multiple back-end services delivered via APIs. A new mobile app, for example, may need to connect to backend ERP or CRM systems using a variety of third-party APIs, which are then integrated and delivered as a new API that provides the mobile app interface. By applying machine learning to this process, developers can greatly increase the speed and reduce the complexity of API integration and management, empowering non-developers with the benefits of API integration. For example, with a machine learning model trained by integration pipeline metadata, analysts across the organization in different lines of businesses with varied skill sets can be presented with recommendations on API integration workflows, to automatically start selecting and assembling APIs to build new applications. This self-service model for API integration greatly increases the speed of new application development while following recommended best practices and reducing security and compliance risks. In this session, Ravi Dharnikota will outline the challenges of API integration in a modern cloud context and explain how developers can leverage machine learning to speed application development, reduce errors and improve security and compliance.

avatar for Ravi	Dharnikota

Ravi Dharnikota

Chief Enterprise Architect, snaplogic
Ravi Dharnikota is the Chief Enterprise Architect for Integration-Platform-as-a-Service (iPaaS) company SnapLogic, where he leads the company’s enterprise architects team. Prior to joining SnapLogic, Ravi was at CA Technologies, where he served as advisor and senior principal solutions... Read More →

Monday September 10, 2018 4:00pm - 4:50pm PDT
Workshop Room 4