Pandorabots has rolled out their Artificial Intelligence as a Service (AIaaS) platform. I wrote about the recently launched Pandorabots Playground in a previous post. The Playground offers a great option for businesses and app developers looking for a do-it-yourself approach to building conversational virtual assistants. The new AIaaS gives developers a ready-made toolkit for incorporating interactions with their conversational bots into apps and websites using client-side code. Both the Playground and the AIaaS platform support the new and improved AIML 2.0 bot scripting language. Not only does AIML 2.0 offer many new features over the previous AIML 1.x versions, but it also enables your app to control native operations on a mobile device, such as making a phone call or setting reminders.
To get started with the Pandorabots AIaaS platform, you need to register for an account. (The AIaaS account is separate and distinct from your Playground account). You can choose between a freebie option and several paid plans. The freebie option offers you 2 bots and up to 25 API calls per day. The paid plans start for as low as $9 a month for 10 bots and up to 250 API calls per day. More robust plans are available.
When you activate your account, an app is created for you. Once the Pandorabots team approves your app, it acts as your gateway into the Pandorabots API. You can use the APIs to access and control your bot from a website, mobile app, or social media site. The bot must be hosted on the Pandorabots hosting platform. The APIs are RESTful (adhering to REST architectural principles), so you can use client-side code to access all the functions of your server-side bot. Software Development Kits (SDKs) are available for several common web programming languages that provide methods for all of the Pandorabots APIs.
As part of your app, you’re issued a unique User Key and Application ID. You use these two parameters when you make calls to the Pandorabots APIs. The API Documentation provides a basic overview of how everything works. It also provides access for testing out the API operations, which include: Create bot, Delete bot, Upload file, Compile bot, and Talk to bot, among others. You can try most of them out from the documentation platform by providing your User Key and App ID.
To actually build and deploy your bots, you’ll want to leverage the detailed documentation available in the Pandorabots Blog. For example, there’s a post on Creating a Virtual Service Representative that walks you through all the steps of building and deploying a simple conversational assistant. There’s even a basic template that you can leverage to provide your virtual assistant with the core information it needs to answer frequently asked questions about your business. While you’ll want to give your bot more information over time, the template can get your assistant up and running quickly.
DIYers should definitely take a look at the Pandorabots Playground and the newly launched AIaaS. If you’d rather leave the scripting, programming, and configuring to the experts, It seems that Pandorabots also offers consulting and other engineering services.