<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Espresso Labs - Medium]]></title>
        <description><![CDATA[We at Espresso Labs build applications to customise smart devices like Google home and Alexa to be used in enterprises | Voice Applications | Technology | Hotel - Medium]]></description>
        <link>https://medium.com/espresso-labs?source=rss----f7761f1d95c7---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Espresso Labs - Medium</title>
            <link>https://medium.com/espresso-labs?source=rss----f7761f1d95c7---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 17:43:31 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/espresso-labs" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Why voice strategy will be a must for every brand by 2019?]]></title>
            <link>https://medium.com/espresso-labs/why-voice-strategy-will-be-a-must-for-every-brand-by-2019-d34c7accf93f?source=rss----f7761f1d95c7---4</link>
            <guid isPermaLink="false">https://medium.com/p/d34c7accf93f</guid>
            <category><![CDATA[alexa]]></category>
            <category><![CDATA[seo-optimisation]]></category>
            <category><![CDATA[voice-application]]></category>
            <category><![CDATA[voice-strategy]]></category>
            <category><![CDATA[google-home-action]]></category>
            <dc:creator><![CDATA[Pallavi Gupta]]></dc:creator>
            <pubDate>Thu, 25 Oct 2018 21:15:33 GMT</pubDate>
            <atom:updated>2018-10-25T21:15:32.536Z</atom:updated>
            <content:encoded><![CDATA[<p>The adoption rate of voice technology is actually even faster as that of the smartphone and social media when they were first launched. Could you imagine today a brand without a social media presence? Or without an app? <a href="https://globenewswire.com/news-release/2017/06/28/1029885/0/en/Smart-Speaker-Market-to-hit-13bn-by-2024-Global-Market-Insights-Inc.html">With the smart speaker market expected to hit USD 13 billion and over 100 million shipments by 2024</a>, these devices are fast moving from entertainment gizmos to must-have appliances. For now, it is a pleasant surprise to discover your favorite brand’s voice app, but by 2020 it will become an expectation.</p><p>Alexa can not only order your favorite meal from zomato but can also book an uber for you! With these devices becoming increasing popular in day to day usage, big players have already started to capture the domain with their voice enables apps.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*p2fe4ut-ClOJAJFiL9K5QQ.jpeg" /></figure><h3>TAKE ADVANTAGE OF OUR MOST NATURAL INTERFACE</h3><p>Voice is one of our primary and most natural methods of communication, making voice a natural interface for humans. Our world is becoming increasingly digital and connected, as a result, we have greater expectations with regards to our interactions with brands. Consumers today place great importance on customer experience and expect instant gratification. By allowing third-party applications, smart speakers give brands the opportunity to take advantage of this natural interface in order to better meet their customers’ expectations. Voice applications enable brands to have an omnipresence and always be available, no matter where the customer is, be it their home, office or car.</p><h3>BE WHERE YOUR CUSTOMERS ARE</h3><p>There are currently over <a href="https://voicebot.ai/2018/03/22/amazon-alexa-skill-count-surpasses-30000-u-s/">30000 Skills on Alexa </a>and almost <a href="https://uk.pcmag.com/features-2/89025/google-assistant-now-has-1830-actions-here-they-are">2000 Actions for Google Assistant</a> from brands from a variety of sectors. Companies such as Ola, Uber, BigBasket, Zomato have all launched a Skill or Action. Through creating a better user experience, brands are able to boost acquisition, user engagement and improve retention. With an increasing number of <a href="https://www.smartly.ai/blog/smartspeaker-market/">major tech players launching their own smart speaker</a>, the market, originally pioneered by Amazon, is not expected to calm down anytime soon.</p><h3>IMPROVE YOUR VOICE SEARCH RANKING</h3><p>According to Gartner, by 2020, 30% of search queries will be conducted without a screen. Unlike searching on a screen, no one wants to hear endless search results reiterated by a smart speaker. They want one-word answers. If a business doesn’t have an app, in this situation they risk the smart speaker giving incorrect information from any old website or referring to a competitor.</p><h3>GRAB THE EARLY ADOPTER ADVANTAGE</h3><p>Brands need to seize the early adopter advantage and define themselves in this new voice-operated environment. Pioneers who have already launched their voice first strategy should be applauded, as this is no easy feat. A voice first strategy means not only developing a voice application but one that adds value to your customers, but also considers all other touch points in order to create an omnichannel customer journey with a consistent brand message.</p><p>Imagine the frustration of millions of users who ask to speak to your brand voice app and see no result on any voice portal. Imagine that the assistant then offers them to talk to a competitor; who has already rolled out their vocal strategy. Imagine that the voice search engine answers a question that directly concerns one of these brands with an incomplete or erroneous response from any site. It’s time for brands to realize that personal assistants are the interface of tomorrow and that in this new #VoiceFirst paradigm, there will be the winners and the losers.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d34c7accf93f" width="1" height="1" alt=""><hr><p><a href="https://medium.com/espresso-labs/why-voice-strategy-will-be-a-must-for-every-brand-by-2019-d34c7accf93f">Why voice strategy will be a must for every brand by 2019?</a> was originally published in <a href="https://medium.com/espresso-labs">Espresso Labs</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Part 2: Build an Action to make Google Assistant find the food you are craving for.]]></title>
            <link>https://medium.com/espresso-labs/part-2-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-157879711d6b?source=rss----f7761f1d95c7---4</link>
            <guid isPermaLink="false">https://medium.com/p/157879711d6b</guid>
            <category><![CDATA[google-assistant]]></category>
            <category><![CDATA[actions-on-google]]></category>
            <category><![CDATA[nodejs]]></category>
            <category><![CDATA[zomato-api]]></category>
            <category><![CDATA[dialogflow]]></category>
            <dc:creator><![CDATA[Vijay Nandwani]]></dc:creator>
            <pubDate>Thu, 13 Sep 2018 01:39:49 GMT</pubDate>
            <atom:updated>2018-09-16T16:02:00.078Z</atom:updated>
            <content:encoded><![CDATA[<h3>Part 2: Build an Action to make Google Assistant find the food you are craving for!</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*iIC6mgXokLM-LXpYlKw7Sg.png" /></figure><p>In <a href="https://medium.com/espresso-labs/part-1-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-36fb5e9c2631">Part 1</a>, we prepared our intent and entity. Now it is time to create the custom webhook for our Find My Food Action.</p><h4>Implementing a custom webhook</h4><p>The webhook can be implemented in two ways:</p><ol><li>Through inline editor that is powered by cloud function (serverless architecture)</li><li>By writing your own functions in the backend (requires a server)</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NZ9yzSN_DCgPzgRITi_76g.png" /></figure><p><em>For our case, we have chosen option 2 because we will be using Zomato’s API for finding restaurants for the particular food and in order to use any external API in cloud functions, one needs to pay $25. So let’s save ourselves some money and use our own server.</em></p><p>In the Fulfillment section, you can put the URL to your server and receive the post request with the parameters mentioned.</p><p><strong>Defining custom webhook with Node.js</strong></p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/1ee3b6b959b85da3ff16808ef7f20709/href">https://medium.com/media/1ee3b6b959b85da3ff16808ef7f20709/href</a></iframe><p>Let’s take a deep dive into the code. Let’s say the user said ‘I want to eat Manchurian’, Manchurian would be extracted and sent as a post request to the backend. Our primary aim is to find the current location of the user because a user in Delhi won’t be interested in Manchurian available in Mumbai.</p><pre>if(request.body.originalDetectIntentRequest.payload.device)</pre><p>The line above checks if we have the device information or not because that’s where our location is. In case we don’t have the information, we have to ask the user for the location and that’s what our else statement does (we invoke the getLocation() function). Note that line #6–7 in the above code is for extracting Lat and Long from the device location.</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/7d3a49a91c130477f80ae41b5035758c/href">https://medium.com/media/7d3a49a91c130477f80ae41b5035758c/href</a></iframe><p>Let’s explore Line 16–21 in depth with which we are instructing the Assistant to ask the user for their exact location(in lat and long). We are invoking a system intent which is of type-permission and asks the user for DEVICE PRECISE LOCATION to serve the user better.</p><p>Now notice line #17</p><pre>“intent” : “actions.intent.PERMISSION”</pre><p>To better understand how this works, let’s understand what is<strong> Helper Intent</strong>. Webhooks can use <em>helper intents</em> to obtain values such as <strong>user information</strong> to personalize the responses (basically fulfillment calls a helper intent when it wants the Assistant to handle part of a conversation). This returns frequently-requested information such as the user’s name and location.</p><p>Create a new Intent as shown below and enable webhook call in the fulfillment section.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*D8z1J2_1HEGwE0BTy8Q6Sg.png" /></figure><h4>What’s next after getting location and dish from the user?</h4><p>Now that we have the location of the user and the dish user wants to eat today, <strong>lets hit the </strong><a href="https://developers.zomato.com/documentation"><strong>Zomato API</strong></a><strong> </strong>and find out the list of nearest restaurants that will serve the required dish!</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/45fa084485405b9aaaf857a42901c6c7/href">https://medium.com/media/45fa084485405b9aaaf857a42901c6c7/href</a></iframe><h4>That’s it, we are done! Let’s see how it looks in Assistant.</h4><p>This application is live for Google Assistant and you can try it out on your phone. <a href="https://assistant.google.com/services/a/uid/000000deaca14b83?hl=en">Here is the link</a> to the application. Here is a demo video:</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2FHaK54Are7cY%3Ffeature%3Doembed&amp;url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DHaK54Are7cY&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2FHaK54Are7cY%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="640" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/e4fefa96a9bb6fa6c3ba47d1c7007d5c/href">https://medium.com/media/e4fefa96a9bb6fa6c3ba47d1c7007d5c/href</a></iframe><p>We can also provide an additional feature in the app of asking details for a particular restaurant from the suggestions given. It’s simple:</p><ul><li>Add an entity named Restaurant</li><li>Provide 1–2 restaurant names and open it for automated expansion</li><li>Make relevant changes in your index.js and you are done. You can find the entire code <a href="https://github.com/EspressoLabsIN/Find-My-Food">here</a>.</li></ul><h3>What next?</h3><p>I believe that you were able to follow the tutorial till now and have the application running. In case something wasn’t clear or you need help with something, please post a comment down below or write to us at support@espressolabs.in.</p><p>Here are some features which you can try to add yourself to improve your understanding of the Assistant Ecosystem.</p><ul><li>A user might as the action to tell more suggestions</li><li>A user might want to modify the radius of the search</li><li>A user might want to sort the results by cost, rating or distance</li><li>A user might want to see the menu of the place or get its contact details</li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=157879711d6b" width="1" height="1" alt=""><hr><p><a href="https://medium.com/espresso-labs/part-2-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-157879711d6b">Part 2: Build an Action to make Google Assistant find the food you are craving for.</a> was originally published in <a href="https://medium.com/espresso-labs">Espresso Labs</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Part 1: Build an Action to make Google Assistant find the food you are craving for.]]></title>
            <link>https://medium.com/espresso-labs/part-1-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-36fb5e9c2631?source=rss----f7761f1d95c7---4</link>
            <guid isPermaLink="false">https://medium.com/p/36fb5e9c2631</guid>
            <category><![CDATA[actions-on-google]]></category>
            <category><![CDATA[google-assistant]]></category>
            <category><![CDATA[chatbots]]></category>
            <category><![CDATA[zomato]]></category>
            <category><![CDATA[dialogflow]]></category>
            <dc:creator><![CDATA[Pallavi Gupta]]></dc:creator>
            <pubDate>Thu, 13 Sep 2018 01:21:31 GMT</pubDate>
            <atom:updated>2018-09-16T16:00:24.011Z</atom:updated>
            <content:encoded><![CDATA[<h3>Part 1: Build an Action to make Google Assistant find the food you are craving for!</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xXY7_70fENb01zDtBdEslA.png" /></figure><p>Actions on Google is a developer platform that lets you create applications to extend the functionality of <a href="https://assistant.google.com/">Google Assistant</a>. Learn how to build actions from scratch under 10 mins with this simple tutorial. The tutorial is divided into two parts. You can find <a href="https://medium.com/espresso-labs/part-2-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-157879711d6b">part 2 at this link</a>.</p><h3>What we’ll build?</h3><p>In this tutorial, we’ll be building an Action for Google Assistant which would allow anyone to find nearby places which serve the dish they’re craving for! You can find the entire code for the tutorial and the app <a href="https://github.com/EspressoLabsIN/Find-my-food-webhook">here</a>. You can watch the demo video <a href="https://www.youtube.com/watch?v=HaK54Are7cY">here</a>. We have also published our final application on Google Assistant <a href="https://assistant.google.com/services/a/uid/000000deaca14b83?hl=en">here</a>, so you can try it out live on your phone! Here are few important things, we’ll be covering in this article:</p><ul><li>How to create a custom webhook and host it on your own server instead of using cloud functions.</li><li>How to access location of the user using permission helper intent.</li><li>How to store data in userStorage.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*2HELbbI-k-rsCX4eXyD9KA.png" /></figure><h3>Getting Started from basics</h3><p>Let’s start from the beginning by defining some key terms that would be commonly used in this post.</p><blockquote><strong>Action</strong>: An Action is an entry point into an interaction that you build for the Assistant. Users can request your Action by typing or speaking to the Assistant.</blockquote><blockquote><strong>Intent</strong>: An underlying goal or task the user wants to do; for example, ordering coffee or finding a piece of music. In Actions on Google, this is represented as a unique identifier and the corresponding user utterances that can trigger the intent.</blockquote><blockquote><strong>Fulfillment</strong>: A service, app, feed, conversation, or other logic that handles an intent and carries out the corresponding Action.</blockquote><p>To start building the action, you’ll first need to create an Actions project as follows:</p><ul><li>Open the <a href="https://console.actions.google.com/">Actions Console</a></li><li>Click on Add/import project.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*wKjQLjb36lJ2tvrscehtyw.png" /></figure><ul><li>Click on Create Project and press SKIP on the next screen</li><li>Click Build &gt; Actions in the left nav.</li><li>Click Add your first Action.</li><li>Select at least one language for your Action, followed by Update.</li><li>On the Custom intent card, click Build. This will open the Dialogflow Console in another tab.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*pJbTixkRhwO1PONsM616ug.png" /><figcaption>Click on build and you will be directed to Dialogflow Console</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Y2EstGYwgdqAvrY6hx_lwg.png" /><figcaption>Press on Create to begin customizing how your Dialogflow agent responds to user requests</figcaption></figure><h3>Start Talking</h3><p>Users start talking with the action through an invocation. (An example of an explicit invocation is a phrase like <em>“Hey Google, talk to MovieTime”).</em> The Assistant then tries to match the user’s input to one of your Actions (it will be MovieTime in this case).</p><p>The<em> welcome intent</em> in an entry point for users to start conversations. It’s triggered when users explicitly invoke an Action by saying its name.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*HkVcgRGKx3bOcCHC0n4S8w.png" /><figcaption>You can customize the response accordingly</figcaption></figure><p>Now that the welcome intent is added, we can test our app on the <em>simulator</em>.</p><ol><li>In the <a href="https://console.dialogflow.com/">Dialogflow Console</a> left navigation, click on Integrations. Then, click on Google Assistant &gt; Integration Settings.</li><li>Click Test to update your Actions project and load it into the Actions Console simulator.</li><li>To test your Action in the simulator, type “Talk to find my food” into the Input field and press enter.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*UGKyrMr9YKXFYFKxC1ArgA.png" /></figure><p>Now when the action is invoked in the above figure, the welcome intent you wrote is shown.</p><h3>Making it conversational</h3><p>Now that you have created a welcome intent, it’s time to get into the core of the app.</p><h4>Create the ‘findRestaurant’ intent</h4><p>Let’s start with find my food intent. The one which is responsible for extracting the dish and finding the best restaurant for that particular dish!</p><p>Once you have created an intent, you can name it and start adding training phrases as shown below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xuzFUDtEdTx_h8bv7ubMnw.jpeg" /></figure><p>Try to form questions which user might ask for finding his food and rephrase them to come up with multiple sentences. Now you can notice that rosogulla, bhalla, italian, naan, daal makhani etc are all types of food the user might say therefore we have to club them in some way for the assistant to understand.</p><p>We can create an <strong>Entity </strong>which represents a category of things, which in our case is a category of food<strong>.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tA1mvyHZULsLxJ8pL_6Z4g.png" /></figure><p>We have created an entity names cuisine where we have entered some common names for the types of food. Notice the ‘Allow automated expansion’ checkbox, this will help dialogflow understand the terms that are not mentioned in the cuisine list and might be related to food.</p><p>Once this is done, in the intent, you need to enable Webhook for our intent</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*i6P_Eg-y2nNEeLtZegA6vA.png" /></figure><p>Dialogflow will automatically extract parameters it recognizes from user speech which triggers this intent; in this case, the cuisine parameter. Once it obtains this information, Dialogflow makes it available to your fulfillment.</p><h4>That’s it for this part of the tutorial. In <a href="https://medium.com/espresso-labs/part-2-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-157879711d6b">part 2</a>, we’ll be finishing code for the webhook and complete the application.</h4><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=36fb5e9c2631" width="1" height="1" alt=""><hr><p><a href="https://medium.com/espresso-labs/part-1-build-actions-app-in-10-mins-to-make-google-assistant-find-your-favorite-food-36fb5e9c2631">Part 1: Build an Action to make Google Assistant find the food you are craving for.</a> was originally published in <a href="https://medium.com/espresso-labs">Espresso Labs</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>