<?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[Smartloop - Medium]]></title>
        <description><![CDATA[Simplicity and automation. Sell more by using conversational AI to collect leads, nurture and engage with better insights. Enjoy improved CTR by elevating your email marketing. - Medium]]></description>
        <link>https://medium.com/smartloopai?source=rss----9fec2c2f8196---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Smartloop - Medium</title>
            <link>https://medium.com/smartloopai?source=rss----9fec2c2f8196---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 10:10:50 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/smartloopai" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Natural Language Understanding with Smartloop NLP]]></title>
            <link>https://medium.com/smartloopai/natural-language-understanding-with-smartloop-nlp-42b0b92f56f6?source=rss----9fec2c2f8196---4</link>
            <guid isPermaLink="false">https://medium.com/p/42b0b92f56f6</guid>
            <category><![CDATA[tensorflow]]></category>
            <category><![CDATA[bidirectional-lstm]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[nlp]]></category>
            <category><![CDATA[smartloop]]></category>
            <dc:creator><![CDATA[Mehfuz Hossain]]></dc:creator>
            <pubDate>Sun, 30 Jul 2023 17:56:42 GMT</pubDate>
            <atom:updated>2023-09-26T16:57:44.203Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*XWoiZt9KF1P8Oqtza1UCww.png" /></figure><p>Smartloop NLP framework powers the <a href="https://dashboard.smartloop.ai/">platform</a> for processing natural language inputs. Smartloop, over the years, has become a community-driven platform; it is used by hotels, healthcare providers, and name brands worldwide with little or no intervention.</p><p>In that direction, we are open-sourcing the NLP framework that powers most of our platform, which you can fork or contribute using the following link:</p><p><a href="https://github.com/SmartloopAI/sl-core">GitHub - SmartloopAI/sl-core: Natural Language Understanding Framework</a></p><p>In this post, I will cover using Smartloop NLU to train and test natural language queries.</p><p>To use the NLP, you will need Tensorflow &gt;= 2.12.0 installed and configured in your local machine. If you are using <strong>M1</strong> mac then you will need the equivalent tensorflow-macos and metal plugin installed to take advantage of the GPU processing.</p><p>I have used miniconda to configure my system, once you have everything configured, you should see the following:</p><pre>➜  conda activate slp<br>(slp) ➜  nlu-demo python <br>Python 3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:12:31) [Clang 14.0.6 ] on darwin<br>Type &quot;help&quot;, &quot;copyright&quot;, &quot;credits&quot; or &quot;license&quot; for more information.<br>&gt;&gt;&gt; import tensorflow as tf<br>&gt;&gt;&gt; tf.__version__<br>&#39;2.12.0&#39;<br>&gt;&gt;&gt; tf.test.is_gpu_available()<br>WARNING:tensorflow:From &lt;stdin&gt;:1: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version.<br>Instructions for updating:<br>Use `tf.config.list_physical_devices(&#39;GPU&#39;)` instead.<br>Metal device set to: Apple M2 Max<br><br>systemMemory: 32.00 GB<br>maxCacheSize: 10.67 GB<br><br>True<br>&gt;&gt;&gt;</pre><p>I am using <strong>macOS</strong> for his post, but GPU training is much more accurate/efficient with nvidia + windows combination, I will cover more detail in the next post on how to optimize the RNN model using TensorRT.</p><p>Now that you have configured your environment, the next step is to install smarloop NLP using pip ,</p><pre>pip install smartloop==1.1.0</pre><p>The next step is to define the model. Copy and paste the following model.json to your root directory of main.py :</p><pre>{<br>    &quot;examples&quot;: {<br>        &quot;intents&quot;: [<br>            {<br>                &quot;text&quot;: &quot;about&quot;,<br>                &quot;intent&quot;: &quot;about&quot;<br>            },<br>            {<br>                &quot;text&quot;: &quot;about&quot;,<br>                &quot;intent&quot;: &quot;about&quot;<br>            },<br>            {<br>                &quot;text&quot;: &quot;learn more&quot;,<br>                &quot;intent&quot;: &quot;about&quot;<br>            },<br>            {<br>                &quot;text&quot;: &quot;more about the platform&quot;,<br>                &quot;intent&quot;: &quot;about&quot;<br>            },<br>            {<br>                &quot;text&quot;: &quot;hello&quot;,<br>                &quot;intent&quot;: &quot;start&quot;<br>            },<br>            {<br>                &quot;text&quot;: &quot;start&quot;,<br>                &quot;intent&quot;: &quot;start&quot;<br>            },<br>            {<br>                &quot;text&quot;: &quot;hi&quot;,<br>                &quot;intent&quot;: &quot;start&quot;<br>            }<br>        ]<br>    },<br>    &quot;lang&quot;: &quot;en&quot;<br>}</pre><p>Next, in your main.py import the following libraries:</p><pre>from smartloop.core import FileConfig<br>from smartloop.core import Project<br>from smartloop.core.text_classifier import TextClassifier</pre><p>Now, let&#39;s create a train Function:</p><pre>def train():<br>cfg = FileConfig()<br>  <br> model_id = int(time.time())<br><br> proj = Project(data_dir=data_dir, project_id=project_id, model_id=str(model_id))<br> cls = TextClassifier(proj=proj, cfg=cfg)<br><br> with open(&#39;model.json&#39;, &#39;r&#39;) as f:<br>  data = json.loads(f.read())<br><br> cls.fit(data)</pre><p>A few things are happening here:</p><ul><li>Loading the config (default config.yaml)</li><li>Creating the project with project_id , data_dir(where the model will be saved)</li><li>Using the model.json for training the model</li></ul><p>Copy and pasteconfig.yaml to your project:</p><pre># number of epochs<br>epochs: 100<br><br># Use tensorboard callback<br>logs: True<br><br># classifier parameters<br>embedded_intent_classifier:<br>    # base neurons to be used by LSTM model<br>    neurons: 64<br>    # length of input len(&quot;hello how are you&quot;) = 4<br>    input_length: 100<br>    # learning rate<br>    learning_rate: 1e-2<br>    # flatten<br>    flatten: False<br>    # number of hidden layer<br>    hidden_layers: 1<br>    # drop rate to avoid overfitting<br>    drop_rate: 0.5<br>    # early stop training in case of not improving<br>    early_stopping: False</pre><p>If you are into machine learning, you can tweak this configuration to fine tune the model, but this should be good enough for our use case and this post.</p><p>One last step before you can train the model is to install nltk corpus:</p><pre>python -m nltk.downloader stopwords  </pre><p>Now, let&#39;s train the model:</p><pre>(misc) ➜  nlu-demo python main.py train<br>Metal device set to: Apple M2 Max<br><br>systemMemory: 32.00 GB<br>maxCacheSize: 10.67 GB<br><br>WARNING:absl:At this time, the v2.11+ optimizer `tf.keras.optimizers.RMSprop` runs slowly on M1/M2 Macs, please use the legacy Keras optimizer instead, located at `tf.keras.optimizers.legacy.RMSprop`.<br>WARNING:absl:There is a known slowdown when using v2.11+ Keras optimizers on M1/M2 Macs. Falling back to the legacy Keras optimizer, i.e., `tf.keras.optimizers.legacy.RMSprop`.<br>Model: &quot;sequential&quot;<br>_________________________________________________________________<br> Layer (type)                Output Shape              Param #   <br>=================================================================<br> embedding (Embedding)       (None, 32, 2)             14        <br>                                                                 <br> bidirectional (Bidirectiona  (None, 64)               8960      <br> l)                                                              <br>                                                                 <br> dropout (Dropout)           (None, 64)                0         <br>                                                                 <br> dense (Dense)               (None, 64)                4160      <br>                                                                 <br> dense_1 (Dense)             (None, 2)                 130       <br>                                                                 <br>=================================================================<br>Total params: 13,264<br>Trainable params: 13,264<br>Non-trainable params: 0<br>_________________________________________________________________<br>2023-07-29 19:57:37.610164: W tensorflow/tsl/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz<br>Epoch: 0, accuracy:0.0000, loss:0.8271, val_accuracy:0.0000, val_loss:1.1254, <br>########## Epoch: 10, accuracy:0.7500, loss:0.6238, val_accuracy:0.0000, val_loss:1.4519, <br>########## Epoch: 20, accuracy:1.0000, loss:0.1624, val_accuracy:0.0000, val_loss:1.7909, <br>########## Epoch: 30, accuracy:1.0000, loss:0.0670, val_accuracy:0.0000, val_loss:1.1486, <br>########## Epoch: 40, accuracy:1.0000, loss:0.0441, val_accuracy:0.0000, val_loss:1.2058, <br>########## Epoch: 50, accuracy:1.0000, loss:0.0290, val_accuracy:0.0000, val_loss:1.1323, <br>########## Epoch: 60, accuracy:1.0000, loss:0.0249, val_accuracy:0.0000, val_loss:1.1935, <br>########## Epoch: 70, accuracy:1.0000, loss:0.0152, val_accuracy:0.0000, val_loss:1.2751, <br>########## Epoch: 80, accuracy:1.0000, loss:0.0079, val_accuracy:0.0000, val_loss:1.2548, <br>########## Epoch: 90, accuracy:1.0000, loss:0.0057, val_accuracy:0.0000, val_loss:1.5172, <br>########## Epoch: 99, accuracy:1.0000, loss:0.0029, val_accuracy:0.0000, val_loss:1.2377, <br><br>1690678657For this particular model, we may not need 100 epochs , in that case, it would be good enough just with 50 epochs in the config file, I leave it to the reader to tune it further.</pre><p>Here, around 50 epochs will be good enough for this model but I will leave that to the reader to fine-tune</p><p>Next, the step to parse and see that we are getting the correct response:</p><pre>def test(project_id, model_id, query):<br> cfg = FileConfig()<br><br> proj = Project(data_dir=data_dir, project_id=project_id, model_id=model_id)<br> cls = TextClassifier(proj=proj, cfg=cfg)<br><br> return cls.transform(query)</pre><p>Running test should give you the following response:</p><pre>(misc) ➜  nlu-demo python main.py test <br>Metal device set to: Apple M2 Max<br><br>systemMemory: 32.00 GB<br>maxCacheSize: 10.67 GB<br><br>2023-07-29 19:57:48.376778: W tensorflow/tsl/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz<br>1/1 [==============================] - 0s 293ms/step<br>{&#39;name&#39;: &#39;start&#39;, &#39;confidence&#39;: 0.9848259091377258}</pre><p>Putting it all together:</p><pre>import os<br>import time<br>import json<br>import argparse<br><br>from smartloop.core import FileConfig<br>from smartloop.core import Project<br>from smartloop.core.text_classifier import TextClassifier<br><br><br>data_dir = os.getenv(&#39;data_dir&#39;, &#39;data&#39;)<br><br>def train(project_id):<br> cfg = FileConfig()<br> <br> model_id = str(int(time.time()))<br><br> proj = Project(data_dir=data_dir, project_id=project_id, model_id=model_id)<br> cls = TextClassifier(proj=proj, cfg=cfg)<br><br> with open(&#39;model.json&#39;, &#39;r&#39;) as f:<br>  data = json.loads(f.read())<br><br> cls.fit(data)<br><br> return model_id<br><br>def test(project_id, model_id, query):<br> cfg = FileConfig()<br><br> proj = Project(data_dir=data_dir, project_id=project_id, model_id=model_id)<br> cls = TextClassifier(proj=proj, cfg=cfg)<br><br> return cls.transform(query)<br><br><br>if __name__ == &#39;__main__&#39;: <br> project_id = &#39;demo&#39;<br><br> parser = argparse.ArgumentParser(description=&quot;Smartloop NLP&quot;)<br> parser.add_argument(<br>  &quot;command&quot;,<br>  metavar=&quot;&lt;command&gt;&quot;,<br>  choices=[&quot;train&quot;, &quot;test&quot;],<br>  help=&quot;argument: train|parse&quot;,<br> )<br> parser.add_argument(&quot;-i&quot;, &quot;--id&quot;, dest=&quot;id&quot;)<br><br> args = parser.parse_args()<br><br> if args.command == &#39;train&#39;:<br>  print(train(project_id))<br> elif args.command == &#39;test&#39;:<br>  id = &#39;1&#39;<br><br>  if args.id is not None:<br>   id = args.id<br><br>  resp = test(project_id, id, [&#39;hello world&#39;])<br>  print(resp[&#39;topIntent&#39;])</pre><p>I have used a slightly different expression from what I used to train the chatbot to validate that it is processed by the NLP correctly</p><p>Finally, if you need help in trying to set up the NLP for your project or you want to contribute, drop me a line at <strong>mehfuz at smartloop.ai</strong></p><p>Happy Hacking!</p><h3>References</h3><ul><li><a href="https://pypi.org/project/smartloop/">https://pypi.org/project/smartloop/</a></li><li><a href="https://docs.conda.io/en/latest/miniconda.html">https://docs.conda.io/en/latest/miniconda.html</a></li><li><a href="https://github.com/SmartloopAI/sl-core">https://github.com/SmartloopAI/sl-core</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=42b0b92f56f6" width="1" height="1" alt=""><hr><p><a href="https://medium.com/smartloopai/natural-language-understanding-with-smartloop-nlp-42b0b92f56f6">Natural Language Understanding with Smartloop NLP</a> was originally published in <a href="https://medium.com/smartloopai">Smartloop</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Creating and configuring a GPU-enabled cluster in Microsoft Azure]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/smartloopai/creating-and-configuring-a-gpu-enabled-cluster-in-microsoft-azure-5441141c6ac9?source=rss----9fec2c2f8196---4"><img src="https://cdn-images-1.medium.com/max/1788/1*h0DXa-hSlRL-LGEqq9jpwg.png" width="1788"></a></p><p class="medium-feed-snippet">I have recently created a GPU-enabled cluster (Nvidia Tesla T4) to run a GPU-enabled workload on a k8s instance.</p><p class="medium-feed-link"><a href="https://medium.com/smartloopai/creating-and-configuring-a-gpu-enabled-cluster-in-microsoft-azure-5441141c6ac9?source=rss----9fec2c2f8196---4">Continue reading on Smartloop »</a></p></div>]]></description>
            <link>https://medium.com/smartloopai/creating-and-configuring-a-gpu-enabled-cluster-in-microsoft-azure-5441141c6ac9?source=rss----9fec2c2f8196---4</link>
            <guid isPermaLink="false">https://medium.com/p/5441141c6ac9</guid>
            <category><![CDATA[terraform]]></category>
            <category><![CDATA[k8s]]></category>
            <category><![CDATA[nvidia]]></category>
            <category><![CDATA[cluster]]></category>
            <category><![CDATA[azure]]></category>
            <dc:creator><![CDATA[Mehfuz Hossain]]></dc:creator>
            <pubDate>Sat, 22 Jul 2023 00:31:14 GMT</pubDate>
            <atom:updated>2023-07-22T00:22:04.122Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How the combination of Live Agents & Chatbot can transform customer service?]]></title>
            <link>https://medium.com/smartloopai/how-the-combination-of-live-agents-chatbot-can-transform-customer-service-5b0f8f733a3f?source=rss----9fec2c2f8196---4</link>
            <guid isPermaLink="false">https://medium.com/p/5b0f8f733a3f</guid>
            <category><![CDATA[contact-center-chatbot]]></category>
            <category><![CDATA[conversational-ai]]></category>
            <category><![CDATA[chatbots]]></category>
            <dc:creator><![CDATA[Priya B.]]></dc:creator>
            <pubDate>Fri, 09 Apr 2021 15:26:39 GMT</pubDate>
            <atom:updated>2021-04-09T15:24:09.815Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*GtEceNga6rg8MnT3JqhNHg.png" /></figure><p>As we all know, chat agents are a crucial part of the customer service department. People prefer to talk to brand representatives to get answers to their questions instantly. This experience leads brands to drive higher customer engagement rate, conversion rate and retention rate. As per research, Live chat agents can bring up to 27% extra sales in your bucket.</p><p>However, many businesses are still not using live chat agents to handle their customer conversations. There are many reasons behind this. Some find it a little confusing, some think that they can’t figure out the right channel to handle live conversations as they are getting inquiries from multiple channels, but most of the time, businesses think that live chat installment, maintenance and agents cost them more than the ROI they get.</p><p>If you are one of them, combining Chatbots with Live Chat agents can be the right solution to your all problems. Let me show you how live chat agents and chatbots can bridge the gap between customer expectation and your customer service to gain more sales.</p><ol><li><strong>Quick Query Resolution</strong></li></ol><p>More than 80% of customers expect to chat with company representatives to get their problems solved. But most customer problems and queries are the same.</p><p>Chatbots are great to address those repetitive queries instead of allocating all of them to live chat agents. Chatbots can answer these queries simultaneously, more quickly and deliver personalized experience instead of putting customers on hold.</p><p>According to Forrester Research, 50% of customers don’t complete a purchase if they don’t find quick answers to their questions during online shopping. So instead of making your agents answer each question personally and making a number of customers online, use the combination of chatbots &amp; live chat to stop losing sales.</p><p><strong>2. Automated Decision Making</strong></p><p>Customers seeking for live chat or any communication on channels are either about to buy a product/service or have already bought stuff and need help after service. And at both stages, they might have a lot of questions. Decent communication is very important here. If the visitor becomes a customer, or a customer going to come again or not depends on how you treat them on these initial stages.</p><p>Having these questions answered and transferring conversation to the agent at the right point is crucial in the buying process. A chatbot can effectively make this type of important decision quickly and improve the buying process for making more sales.</p><p><strong>3. Cost effective</strong></p><p>Customers are most likely to buy from a brand where they are treated well, and their queries are answered quickly. Businesses have found an effective solution as Live Chat Tools to achieve more customers. But the cost of live chat installment tools, devices, workplace and hiring employees exceed too much. Small businesses are unable to afford this costing.</p><p>The beauty of combining live chat with chatbot is that a chatbot can handle initial conversation of multiple customers at the same time and handover the conversation to agents only if needed to save you from unnecessary costs.</p><p><strong>4. Increase conversion rate &amp; boost sales</strong></p><p>More than 65% of customers think that having a conversation directly is informative and more helpful than emails or SMS. Combining live chat agents with chatbot can provide effective assistance when they are confused about your product or services. As a result, they will be more likely to be satisfied and buy products much faster without any hassle.</p><p>Live chat also improves customer satisfaction by quickly answering their queries in a personalized way. According to eMarketer, more than 60% of customers are likely to return to a website that offers live chat. Therefore, it becomes easy for businesses to improve sales conversion &amp; generate more ROI.</p><p>While the popularity of chatbots and live chat is on the top, be on the trend by building your AI-Powered contact center using Smartloop. The benefit of this combination can offer the values that you will not find anywhere else. Double your conversion rates and cut your costs using today <a href="http://www.smartloop.ai/">www.smartloop.ai</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5b0f8f733a3f" width="1" height="1" alt=""><hr><p><a href="https://medium.com/smartloopai/how-the-combination-of-live-agents-chatbot-can-transform-customer-service-5b0f8f733a3f">How the combination of Live Agents &amp; Chatbot can transform customer service?</a> was originally published in <a href="https://medium.com/smartloopai">Smartloop</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How to use low code platforms for creating engaging conversational experience?]]></title>
            <link>https://medium.com/smartloopai/how-to-use-low-code-platforms-for-creating-engaging-conversational-experience-9b5cec76f968?source=rss----9fec2c2f8196---4</link>
            <guid isPermaLink="false">https://medium.com/p/9b5cec76f968</guid>
            <category><![CDATA[chatbots]]></category>
            <dc:creator><![CDATA[Priya B.]]></dc:creator>
            <pubDate>Thu, 04 Mar 2021 16:34:05 GMT</pubDate>
            <atom:updated>2021-03-04T16:34:05.284Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gxYokhjupU_QGg2fHhtPMw.png" /></figure><p>Customer engagement and retention is one of the main areas where business put lots of efforts. To satisfy these needs, businesses has started adopting AI-powered chatbots to engage customers and offer them seamless experiences. Chatbots works great while attracting and engaging new customers. They are also great collect customers data and shorten sales life cycles. Chatbots adoption is at its highest pick due to the wide digital adoption caused by global pandemic in the year 2020. Hence, many businesses still think chatbots are still naive and they can’t afford to spend too much on this tool.</p><p>Chatbot development can be costly at a time but it can give you long term benefits. If you are a startup or a small business, and can’t afford chatbot development, low code chatbot development like smartloop.ai is the great way to be in a trend at lower rates.</p><p>With technology advancement and smart tools, businesses are moving towards low code and no code approaches to create software solutions. These approaches can reduce up to 60% development costs and time. And of the biggest benefit of using no code platform to create chatbot solution is that domain experts can create and refine these conversational flows without the friction of having to explain their ideas to others. This way they can deliver a high-quality product to market in a short time.</p><p>There are already so many low or no code platforms, although the functionalities are relatively different. These platforms make a lot of sense for simple chatbot use cases, like lead generation, product promotions and appointment booking. But in many cases chatbot needs some complex functionality that requires programmatic logic. The chatbot may need to manage or reset contexts depending on what users says at different stage of flows or need to store lead details in CRM systems. For that case tools like Dialogflow, Zapier and Wit.ai can be blessings.</p><p>Person without any knowledge of coding can create his own bots on different channels using these platforms. Generally, these platforms provide features like -</p><p>· Creating informative flows using drag and drop modules.</p><p>· Creating forms to take user’s details.</p><p>· Quick replies to give answers to frequently asked questions.</p><p>· Carousel and card to display content attractively.</p><p>· Buttons to simplify user’s selection and choice submission.</p><p>· NLP to train chatbots for natural language interactions.</p><p>· Dynamic blocks to display dynamic data using APIs.</p><p>· API integration to do certain backend operations.</p><p>· Emotion detection to personalize the user experience.</p><p>· Analytics dashboard to observe customer behavior.</p><p>And the list can still go on.</p><p>Most of these chatbot development platforms provide an end-to-end developer experience that allows users to build great bots. Users can build chatbots effortlessly, test the bot and can launch bots while leaving worries.</p><p>But creating these conversational experiences on low code platform may require a skill call conversation design. It’s a whole different skill and require a complete study. But if you are reading this article, you don’t have to worry about that. I’m going to list five tips which you can use to create chatbot using low code platforms.</p><p>1. <strong>Guide your users </strong>— When your customer visits your chatbot for the first time, it may happen that they are interacting with this technology for the first time and talking with a chat-robot can be little confusing for them. As specially if you are dealing with baby boomers. In this case you can create a chatbot with guided approach where the chatbot will tell the users what they have to do and what will be the next action required.</p><p>2. <strong>Ask Questions </strong>— Creating guided bot experience does not mean letting your customers speak or express their needs. This way they can feel connected with your brand. To understand their needs, it’s important to prepare set of questions to ask. You can customize this question at the later stage if you feel the need using the same platform with a minimal change.</p><p>3. <strong>Personalize recommendations </strong>— These low code platforms can have features like “tags” and “Custome variables” that you can use to store user preferences and previous purchases. So that when your customers come again you can make the personalized recommendations and increase the chances of purchasing.</p><p>4. <strong>Error handling — </strong>While talking with chatbots many people do not follow certain rules and they start talking like the way they talk with human. Untrained chatbots cannot answer these kinds of conversations and got stuck at certain point of flows. To handle this kind of situation by providing suggestions and ways to get out is called error handling. Many low code platforms allow prompt messages, so when user type something unexpected, chatbot can guide them to process with certain options or to end the flow.</p><p>5. <strong>Provide Options — </strong>When you have lot to offer, instead of bombarding sets of messages you can provide multiple options so that user can choose the option they are comfortable with and the chatbot won’t get confuse with user’s need. And don’t forget to give options like “back to menu” or “exit” to let your customer go out from the loop.</p><p>With these tips, you can create conversational experiences that will drive more engagement sales. To create such experiences, please visit <a href="http://www.smartloop.ai/">www.smartloop.ai</a> and start your free trial today!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9b5cec76f968" width="1" height="1" alt=""><hr><p><a href="https://medium.com/smartloopai/how-to-use-low-code-platforms-for-creating-engaging-conversational-experience-9b5cec76f968">How to use low code platforms for creating engaging conversational experience?</a> was originally published in <a href="https://medium.com/smartloopai">Smartloop</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>