Bespoken Selected by Amazon to Add Automated Testing to the Alexa Skills Kit

Aug 16, 2018 · 3 min read

Bespoken, the leader in automated testing for voice interactive artificial intelligence, announced today that it will begin to integrate its automated testing products into the sample projects for the Alexa Skill Kit (ASK) for Node.js. This will allow developers building upon the ASK sample projects to effortlessly begin unit and end-to-end testing of their Alexa skills.

“We are proud that Amazon selected Bespoken to provide automated testing to thousands of developers who are building voice apps for the Alexa platform. We believe that testing is the key to improving productivity of developers and increasing the quality of skills that are introduced,” said John Kelvie, CEO and co-founder of Bespoken. Kelvie noted that fixing bugs found early in the development process costs 1% of what it would cost to fix them once a skill has been released. “The return on investment from unit and end-to-end testing by developers and quality assurance is large and upfront,” he added.

“Amazon has made a commitment to help developers increase the quality of their skills. We believe that testing throughout the development cycle is key to achieving that goal. Bespoken is the recognized leader in developing testing tools for Alexa, and we are very happy to partner with them to make testing tools easily available to all Alexa developers,” said Bespoken co-founder and Executive Chairman Frank Raines.

Bespoken was founded in 2017 and currently has over 2,500 people using its tools and testing products. The products are designed to automate the testing of voice applications by developers, quality assurance, and dev-ops teams.

Bespoken has a broad portfolio including:

  • Command-line development tools
  • Automated testing products for manual, unit, end-to-end, and continuous testing
  • Enterprise automated testing solution, incorporating continuous deployment, continuous integration, and code coverage

This announcement comes on the heels of Bespoken releasing its case study on automated testing and monitoring for Mercedes-Benz R&D North America. They used Bespoken to adopt an automated approach for for their Mercedes me Alexa skill and Google Action. Mercedes-Benz R&D North America has been an early mover in the voice space, and with it, they have seen the possibilities as well as become aware of the limitations of these cutting edge new technologies. The ultimate goal was to guarantee exceptional quality for its connected car voice interaction experiences — quality which is synonymous with the Mercedes-Benz name.

To ensure this level of quality, the Mercedes-Benz R&D North America team adopted the four-layer testing cake articulated by Bespoken. After using Bespoken testing and monitoring tools, the dev cycle was nearly completely automated, with quality assurance baked into each step. All of it comes together to provide the best possible connected car experience to Mercedes owners, one that provides convenience and delight. Bespoken is proud to assist in this effort.

Kelvie noted that automated testing is like a superpower. “Incorporating a disciplined approach to testing unleashes developers to write more high-quality code, faster. And using our test scripting language, non-developers can quickly create and reuse hundreds of test scripts for end-to-end testing to improve the quality of their voice applications,” Kelvie explained.

This product announcement comes just over a month after reporting the completion of a $2.4 million seed funding round. Bespoken has operations in Lima Peru, Seattle, and Washington DC. For more information, contact or visit

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch

Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore

Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store