⚠️ Unsupported Browser

Your browser is not supported.

The latest version of Safari, Chrome, Firefox, Internet Explorer or Microsoft Edge is required to use this website.

Click the button below to update and we look forward to seeing you soon.

Update now

PolyAI Blog

Explore posts from PolyAI’s team of conversational AI experts that cover topics including deep dives into the tech behind our voice assistants, tips to building the best voice assistant, news in the conversational AI industry and more.

All Posts

PolyAI Named a Gartner 2020 Cool Vendor in Conversational AI Platforms

We’re delighted to announce that PolyAI has been named a Cool Vendor in Gartner’s latest Cool Vendors in Conversational AI Platforms report. The report – which focuses on vendors representing rising trends in conversational technologies – finds that “voice is becoming increasingly common, with end-to-end, human-like voice dialogues now possible within limited scopes.” Transactional Dialogue […]

Few-Shot Slot Labeling with ConVEx: The Most Accurate Value Extractor on The Market

We’re thrilled to announce our recently published paper on the PolyAI ConVEx framework. Our new technique, ConVEx (Conversational Value Extractor), is the most accurate value extractor on the market. It requires significantly less data than previous best systems, which means that PolyAI can create virtual assistants faster and better than anyone else, across any customer […]

Intent Classification with Geometrically-Friendly Embeddings

At PolyAI, our conversational agents are powered, in part, by machine learning models that detect the intent behind what a user says. For example, in a banking environment, if a customer says “When did you send me my new card?”, the models will detect that you’re enquiring about card arrivals and the agent will route […]

The State of AI 2020: Creating a Model That Performs Better than Google, at a Fraction of the Cost

The latest State of AI report from Nathan Benaich and Ian Hogarth has just been released and we’re thrilled that PolyAI has featured – twice! The report highlights the vast costs of training a model. “Based on variables released by Google et al., you’re paying circa $1 per 1,000 parameters. This means OpenAI’s 175B parameter […]

Our Voice Assistant Spoke to Google Duplex. Here’s What Happened…

This summer, Google has been deploying its AI voice assistant called Duplex to call bars and restaurants in order to update their opening hours on Google Maps listings. Here’s a call their system had with our virtual assistant for restaurants.  As far as we’re aware, this is the first naturally-occurring conversation between AI voice […]

Digital Transformation Paralysis: The Doldrums of Customer Experience Transformation

Over the last few months, we have spoken with many B2C organisations with large contact centres. Without fail, we constantly hear the following digital transformation concerns from business leaders, operations directors, and customer experience professionals: “We want to transform our business and we are evaluating several projects at the moment our plans will finalise in […]

Virtual Assistant Value Streams: Identification & Verification

This is part two of a four part article series in which we demonstrate how to identify value streams of using a virtual assistant to partially or fully automate “customer-to-business” interactions. We will detail how to measure quantifiable cost savings and track qualitative benefits in a contact center environment. You can read part one–which discusses […]

Virtual Assistant Value Streams: Misrouted Calls

This is part one of a four part article series which will demonstrate how to identify value streams a virtual assistant can deliver through automating “customer-to-business” voice interactions. This series will look at how to measure quantifiable cost savings and track qualitative benefits that a virtual assistant can deliver in a contact center environment. In […]

The Business Case for Customer Service Automation

Customer service automation is nothing new, but very little has actually changed since the IVR was developed in the 1970s… until now. We have now reached a point where speech recognition and conversational AI technologies are sophisticated enough to reliably handle customer queries, and the next 3-5 years will see this technology totally transform the […]