Find similar content

Hey guys, it’s time for #botoftheweek. Our bot today is kinda usual - it has no task or problem to solve. It’s a multiplayer strategy game on Telegram called Idle Town. And these guys already have more than 60k users with about 2k of them playing daily. Read my review below to find out more. Or you can test the bot here: @IdleTownBot https://docs.google.com/document/d/1-5wPfzEI-qHH6UsZEVF9XAlLc3yvha1Y8pk1XbBGXi0

Do you remember a homework tracking bot built by 14-year old kid? Yep, it was #botoftheweek once. And it’s again here. It’s... been acquired 😲 Yep, a chatbot built by 14-year old has been acquired. Full story is below, it’s insane. https://chatbotsmagazine.com/the-story-of-getting-acquired-at-age-14-a0171247d991

Hey Telegram folks, Today’s #botoftheweek shows a great example of solving a very clear problem via messenger interface. Lenny is a bot that helps you to learn 10 new English words every day in order to increase your vocabulary. It has been launched only 2 months ago but already has about 3k daily active users and 36 paid ones. Sound interesting, right? Read the full review here: https://docs.google.com/document/d/1Nl5p5TaqgjTd8uNQwhqiUsiyETg6v77KFfTK9WPI1yk/edit

Hey folks, I’m a little bit late, but #botoftheweek is here! Today’s bot works on Slack and helps you as a business owner to set goals, track performance and reward excellence. The name is pretty straight-forward by the way, it’s called KarmaBot. It has a plenty of features to boost your company performance and improve culture, such as setting monthly monetary bonuses based on Karma points, encouraging team members to share some Karma between each other, giving extra points to the teams for faster shipping and much more. My favorite feature here is an ability to share some karma points with my team members to reward them for doing a great job. It really works, and feels great too. I really advise you try it: http://karmabot.chat

Zendesk has just released their new #botoftheweek for customer support automation. Boom! I’ve seen a lot of startups trying to do the same thing, but it was only a matter of time before the big players made it a feature. What’s interesting here is that both Intercom and Zendesk position their bots less as bots or conversational assistants and more like a knowledge base products. That makes a lot of sense — there’s so much value in the content assets that customers have already created and sometimes it's just about helping connect the dots. Top 4 features of Zendesk bot: 1. It works wherever your customers are: Answer Bot already works across several channels including email and API which typically don’t have great automated self service experiences. They’re also extending Answer Bot to create new in-channel experiences for web form, web widget, chat, and our SDKs in the near future. 2. Activate and go: They’ve removed the complexity to make it as easy as possible for anyone to start using Answer Bot straight away. No training time or massive data sets needed. (You’re wondering how? Because it’s trained on over 12 million customer service interactions to deliver accurate and reliable responses. And it’ll continue to learn and grow.) 3. Learns from customers and agents: Interactions between Answer Bot and your customers are clearly presented to your support team, allowing them to see the actions customers have taken to avoid suggesting the same content again. Your support team can also provide pointers to Answer Bot to help it learn over time. 4. Optimize performance with reporting: Generate amazing insights into where Answer Bot performs well and where you may need to create or improve your self-service content. Let the automation battle begin! 🤖 https://www.zendesk.com/answer-bot

Intercom has launched Operator, which is a #botoftheweek for customer experience. Why do they need a chatbot? Intercom makes products that help businesses to communicate with their customers. The bot’s goal here is to automate some extremely simple tasks around this communication, which the bot can handle better/faster than live operators. For example, if someone is texting business on a website, and that business is now overnight, nobody will pick up the chat. In this case, the bot could clarify the situation and ask for the best channel to follow up when the team will be back in the office. Just like Amazon Alexa, Operator has a growing set of skills, including: - Set expectations based on your team’s availability - Collect contact information - Intelligently suggest help articles to answer questions - Automatically close answered conversations for you - Measure customer satisfaction It’s just the beginning, the next step is to add some kind of SDK/framework available for teams to build their own skills 🤖 https://www.intercom.com/operator-bot

Hey Telegram community, Today’s #botoftheweek shows the perfect example of how to create a captivating product on Messenger. Forksy is a bot that keeps a food diary, tracks calories, and provides basic nutritional tips based on your eating habits. “But there are dozens of similar products for nutrition, why the hell did you choose this bot?” They are not good enough. Why? Read the full review here: https://docs.google.com/document/d/1IgETqbjM39bSxqdGkqYxVBU-UzFAb2n8-EX_ARwE-qU/edit

Oh, sh*t. That’s the Hook Model! Have you ever spotted a popular framework in action? It’s a strange yet reassuring feeling! Realising someone has implemented a strategy, textbook perfect. Nir Eyal would be proud. Well that happened to me yesterday when I was reviewing Champ for our #botoftheweek series. Champ has stormed to success in the last couple of months, processing over 25 million messages on Messenger, here's my review as to why. Full review here, made by Matthew, one of our BDDM community admins: https://docs.google.com/document/d/1E1FPlwEF4ZBFFe8NonVbiPPySM0rZne4E4fsggeV1pg/edit?usp=sharing

I haven’t found any compelling bots for today’s #botoftheweek. But I want to share with you a trick we use to improve our bots onboarding & engagement 5x. It works 🙂 It’s based on a habit creation model called HOOK, described by Nir Eyal in his book “Hooked: How to Build Habit-Forming Products” (highly recommend to read). Let’s say we are building a community manager bot, which helps to engage community members in Slack. To implement the HOOK model, we need to activate a habit-forming process, which consists of 4 steps: 1. Trigger The trigger is an activator of a behavior. It could be either internal or external, and usually, in bots, internal triggers (such as boredom or curiosity) are activated by external triggers (such as a direct message from the bot). The goal of the trigger is to drive the user to take action using the product. In our case, the trigger is hidden in an onboarding message: “Greetings, @flreln! Welcome to BotCube, the top Slack community for bot designers.” ”My name is Botty, and I’m a bot, designed to help show you around and get the most out of your membership.” ”Say “help” to get started or “tip” to get today’s tip about bots.” The last message here is an example of a good trigger because it has 2 key things: - Shows that the reward is variable (“today’s tip”); - Is actionable and provides the user with a choice. 2. Action The action is a simple thing user needs to do to get a reward. Like hitting “Show me” button or opening a notification. Once the user has done the intended action (in this case, typing the “tip”), he’s dazzled by what he sees next. 3. Variable reward The reward is the realization of the value from the action. Feedback loops are all around us, but predictable ones don’t create desire and don’t surge the level of dopamine in the brain. In our case, the reward is a random useful tip about bots that user gets after he typed “tip” message to the bot. Variability and reduced accessibility here multiplies the effect, creating a frenzied hunting state, activating the parts associated with wanting and desire. 4. Investment The last phase of the HOOK is where the user is asked to do a bit of work. Here we can benefit from the reward we just gave him and ask him to take action that makes the service better with use and generates future triggering opportunities. In our community bot example, we can promote a survey or explain any other feature we want the user to proceed to. These investments can be leveraged to make the trigger more engaging, the action easier, and the reward more exciting with every pass through the HOOK loop. That’s it. I highly recommend you to implement this approach in your bots and just see what happens next. You will be surprised :)

Hey botmakers, anyone would like to submit their bot for review in our #botoftheweek series? The offer lasts for an hour. Send me (@flreln) a message with your bot’s description, and I’ll choose the best one to write a post about 🙂

Today's #botoftheweek is kinda special. Why is that? Because it's not just one bot. It's 1000 bots. Last year Joshua Browder launched DoNotPay, which is a bot that helps people fight their parking tickets. He got big media coverage because the service already saved people $9.3 million disputing 375,000 parking tickets. Could you imagine? Now he's pushing out 1,000 new bots that can assist people in filling out transactional legal forms in all 50 U.S. states and the U.K. That's huge. Why did he do this? As Joshua added new capabilities to his DoNotPay bot, many early users started to become confused about what the bot could actually be used for. That’s the main reason he decided to release as many legal assistance features as possible, branding them as a full-service consumer legal tool. I personally think this is a brilliant idea because people are not struggling to find the right tool anymore. And the bot itself is a fantastic case study for why people should care about AI, even if it’s not revolutionary on the tech side. P.S this one is not a Medium post as I told you a week ago because at the moment I have no access to the bot to test it. Looking forward to getting it very soon 🙂 https://techcrunch.com/2017/07/12/donotpay-launches-1000-new-bots-to-help-you-with-your-legal-problems/

I thought a lot about our #botoftheweek section. Then it hit me. I need to make a guide out of every successful case we go through at #botoftheweek. Why? Because there are dozens of unique approaches and features hidden in products I share every week, and it would be not fair if I keep that golden chest away from you. Starting today, every #botoftheweek post is a Medium publication with highlighted insights and key features of every bot, explained in details. I’m sure it will bring a lot more value to this community to get what’s under the hood of these products. And the first one is right here 🙂 https://medium.com/@flreln/emily-bot-review-botoftheweek-28-a2f82124fb52