A Plug-and-Play Conversational API?
Since we got into the bot space last Fall, we’ve wished for a simple API that we could connect with to deploy conversational AI into an already-existing chatbot. Since we didn’t find one, we decided to build an API for developers.
Three Types of Bot-Building Platforms
The bot-building platforms seem to fall into three broad categories. The first are natural language processing (NLP) platforms like api.ai and wit.ai which require you to create your inputs and outputs. Platforms like these can be powerful, but the drawback is that you have to “train” your bot over long periods of time. You also must constantly add intents, edit and improve responses, and adjust the machine learning to get the chatbot to respond appropriately.
The second type of bot-building service are the drag-and-drop kind. Examples of these include motion.ai and Chatfuel. These tend to be a little simpler to use than the NLP platforms. However, these services generally don’t offer much in the way of conversational AI.
The third type are the AIML-based services. AIML stands for “Artificial Intelligence Markup Language.” Basically it is a form of XML that encodes rules for questions and answers. One good example of this kind of chatbot builder is Botlibre. With Botlibre, you can add inputs and responses in the form of AIML scripts.
Why A Conversational API?
Of the three types mentioned above, the third gets you the closest to a plug-and-play solution — but not really. You still have to code the AIML scripts yourself. And the others, forget it. Api.ai has a “small talk” domain — sort of a set of pre-scripted responses to common conversational speech. But it still doesn’t work all that well out of the box; you have to train the system over time. Needless to say, this is super time consuming.
Our API was borne out of our own frustration with this. We wanted to enable developers to quickly and easily deploy conversational AI into their chatbots — and without having to do it from scratch. It’s a major hassle to have to train a bot to understand simple platitudes like “hello,” “good-bye,” and “how are you?” No one wants to spend weeks creating AIML scripts or entering question/response pairs into a form.
We thought, “Wouldn’t it be useful if there were a conversational API where you could just launch a session through a simple RESTful HTTP request?” You would make an HTTP GET request to an endpoint URL, add a couple of parameters, and boom! The API would respond back with the appropriate response.
So, that’s what we built.
For a small fee, you can license your API key here. Here’s some documentation with sample code snippets and a demo. And when you want to add a question/response pair or modify an existing one, no need to script a new AIML node or create new intents or entities inside a platform. Just email the details to our friendly support chatbot, Sophia, and she’ll take care of you. ;)
Review Text Engine on BotList
I’m a social entrepreneur who has been building telephony and SMS applications since 2008. An artist at heart, I won a full scholarship to The University of Texas at Austin for classical piano in 1993. In 2007, I began teaching myself Javascript, PHP and Ruby in the evenings while working as a marketing professional by day. I started my first business in 2008 (Gnosis Media Group), a communications consultancy whose first successful product was a text-to-donate application for nonprofits.
Building on that technology, I later built Text Engine, which was awarded the distinction of “Tech Company to Watch 2015” by the Connecticut Technology Council. Text Engine was later accepted into the award-winning ReSET Impact Accelerator in January 2016, and soon after we received significant funding from Backstage Capital, a Los Angeles venture capital fund. When I’m not coding, I enjoy power naps, reading philosophy texts, playing chess, and bowling.
