How To Build An AI With No Code

1. Introduction

No code machine learning refers to the ability of users to build machine learning based solutions without the need for writing code. It is a way for knowledge workers to build solutions for their own challenges on a no code AI platform. We show how anyone can build their own Intelligent Virtual Assistant that is capable of chatting with them and answering questions in any language. 

At the end you have your own Intelligent Virtual Assistant (or IVA for short) on a custom URL that you can share with your friends and colleagues. IVA is a smart chatbot capable of understanding natural language and built with Conversational AI tools.

There has been plenty of talk around AI and machine learning in countless articles, blog posts and news items. While much of it is hype, much of it is also true. How so? It will fundamentally enable machines to learn and as a result become more intelligent. This brings about a major shift in the way information gets processed and one should not turn a blind eye to this.

Want to use AI? Well, not so fast. In most cases you need to know how to program. Or at least have a certain set of technical skills to work with AI and create things for your own benefit. No surprise that data scientists and machine learning specialists are one of the most highly sought-after positions in the industry. And this applies not just in the IT industry but all across the board whether it be pharmaceuticals, automotive, food processing, forestry etc. Wherever data is collected, data scientists are in demand. 

2. Can’t code? No Problem.

But what about those of us that don't know how to program? What about if you don't possess the technical skills but still want to create AI that will help solve your problems? One could take online courses on machine learning but not all of us have the time and the willingness. And the truth is that learning a technical skill at a beginner’s level takes a few months at minimum to get started. To get good one can easily spend years on it. So does this mean that you should just give up and find those who have the technical skills to carry out your vision?

Well, no. While it is true that artificial intelligence is something that requires technical skills, there's an increasing part of the industry that is making it available for anyone. It should be made clear that if you really want to have an AI solution that is tailored to your exact needs and customized, then you need to have people that possess the technical skills. That being said, there is a growing cadre of companies offering no code machine learning tools for non-technical people to get started. 

3. What is Minimum Viable AI?

In lean startup methodology the focus is on creating a Minimum Viable Product. In machine learning projects the initial aim should be the same - create a Minimum Viable Artificial Intelligence with no code AI. Whether it is a machine vision, language processing or a data categorization project, start something small (a proof of concept) that you can accomplish in 3-4 weeks and see the results. Minimum Viable AI creates quick proof whether the project is working and gives insight into what to focus on.

Amassing a team of data scientists for a short proof of concept project is a bit of an overkill. So there is a growing number of companies giving non-technical knowledge workers the tools to build their own AI proof of concept project. These can be tools that require no coding skills or tools that are so-called low code platforms that require minimal programming skills.

This makes a lot of sense because people are curious and creative. Thus far software creativity has been bound by the need for technical skills. However, this should not be a limitation. People want to learn things, to create things, to be able to express their thoughts and ideas. Machine learning has so much power and so much potential to expand on any human creativity so it is necessary for people to have access to the tools to express their creativity. 

If you do not know how to code but have interest in artificial intelligence, then most likely you have ideas for things you want to build with no code machine learning tools. You could either be a manager and notice flaws in your processes that you wish to automate. Or you could be a knowledge worker that is performing tedious tasks that should be automated. Or you are a marketer and are looking for automated communication channels with your audience. No matter the role, building solutions for our own problems gives inherent satisfaction. And building solutions should not be bound by knowledge of technical skills. 

4. Your first AI project in 15 minutes.

Our company has been building Conversational AI solutions for large companies for several years. And one of the things that we advise is that if you have interest in machine learning then the best thing is just to build something. To get started, build a no code or a c AI solution, measure the results and improve your solution on that. 

If you want to build AI then you can get started by building your own Intelligent Virtual Assistant. Essentially it is your own “Siri” - an artificial intelligence-based machine running on deep learning algorithms and trained with phrases and utterance making it capable of chatting with you and your customers and answering questions. And you can build it without knowing any code. Suffice it to say it is not perfect all-knowing general AI. And that is fine because one, you want something quick to start with. And two, well … general AI does not exist yet.

So if you're looking for a machine learning project that would take you 15 minutes to complete then please read on.

Here we have outlined how to build your own AI without coding. Without writing a single line of code on the Alphachat no code machine learning platform. 

It is a Conversational AI based Intelligent Virtual Assistant. An intelligent chatbot that you can train and share the website URL with your friends and colleagues who can also chat with it. Conversational AI means that it is capable of answering your chat based questions. 

Here’s how to do it in 15 minutes.

5. Step-by-step guide to building your own AI with no code.

1. Go to and click Sign-Up. Enter your email and choose a password. Go back to your inbox and click on the verification link. Now you have verified your account.

Sign up for no code machine learning platform. no code maching learning platform website.

We also have an AI-based Virtual Assistant embedded right on the front page that you can chat with. The best part? You can chat with it in any language. English? For sure. Spanish? Of course. Swahili? We got it covered. 

Intelligent Virtual Assistant built with
Intelligent Virtual Assistant built with

2. You can use the product with all its features for free for 10 days. During the first 10 days you have access to all the features and can build your own Intelligent Virtual Assistant.

Signing up does not require a credit card. So if you just want to build something quickly and try out for free, you can do that. If you do not wish to pay for the product after the 10 day free trial, no problem. You don’t have to do anything. After 10 days your account will close and unless you enter your credit card and pay the €399 monthly fee, we will delete the account in 30 days. 

3. After signing up you will first see the Floweditor. This is the heart of the no code machine learning tool where you can build the content of the Virtual Assistant. For the sake of simplicity we have built a demo IVA for you already. 

The blue items are actions. Each action is a topic that your no code AI knows. In the welcome action you will see the greeting. It is polite for your IVA to say something nice to the person in the beginning. 

Floweditor - the heart of the no code machine learing tool for building Conversational AI.
Add topics that your AI can chat about.

You can change the text in the action by simply clicking on it and adding your answer.

Change the content of the Intelligent Virtual Assistant.
Change the text of the answer.

You can add pictures, carousels or gifs as well.

Add pictures to the Intelligent Virtual Assistant.
Add pictures to the answers.

Add links to the IVA.
Add links to the answers.

If you want then you can also add links at the end of each action. The link can be to any URL. Simply click the button titled “Button” and add the text that the user will see and the URL in https:// format.

4. Next is the menu. In the menu your IVA will present the user with a few popular topics that they can select. If you are a company then for example these can be your Products, Pricing and Value. We have provided these by default. You can change the content by simply clicking on the topic and then editing the text area.

Menu provides quick navigation links to topics in the IVA.
Menu provides quick navigation links to topics in the IVA.

5. Topics in the menu can be easily changed by adding new ones through buttons on the top or deleting old ones. Each topic is linked to a topic in the main folder system. For example Product is linked as Main.Product where Main is the root folder and Product is the name of the topic in the Main root folder.

Change topics in the Conversational AI menu.
Change topics in the menu.

6. If the Intelligent Virtual Assistant is unable to help the user you have two options. You can log into the chat panel in Alphachat and toggle on the live chat button. Now when users do not get an answer they like they can choose to be connected to a human agent (i.e. you). 

Human-in-the-loop AI
See incoming chats from the VCA in the chat panel.

If you are online the IVA will direct the conversation to you and you can see it in your chat panel. If you are offline, then the IVA will take a message from the user and send it to your email. You can set the email where you wish to forward your conversations from the forms panel.

7. Now, let’s turn to training the no code AI. No technical skills needed here as the no code machine learning interface makes it easy. Users will have all kinds of questions for your Intelligent Virtual Assistant. So let’s train it. First, you should add a few topics that the AI should know. As an example we have added topics like Product, Pricing and Value. If you are a company then you might want to edit those and specify what product you offer, how much they cost and why customers should buy them. 

Add topics underneath the menu in the Conversational AI
Adding topics underneath the menu.

If you want to build the Intelligent Virtual Assistant to talk about things you care about or your hobbies or you, then simply add a new topic by clicking the + button on the top left. Add the text and you have another thing that the IVA knows. 

Add new topics to the Virtual Customer Assistant.
Add new topics to the Virtual Customer Assistant.

To train the AI, go to the Train tab on top of the action editor. Add here phrases that you think your users might ask if they want the IVA to answer with the action you have just created. For example, if the action is Product then you might add phrases such as “what products do you offer”, “what do you sell”, “what kind of product you provide”. Add a minimum of 5 phrases, 10-15 is good, 20 is optimal for starting out. 

Adding training phrases to the topics of the Conversational AI.
Add training phrases to each topic.

Once you have added the phrases for all your actions, click Train. This will train your AI. It is using a combination of neural networks and machine learning algorithms to train the Intelligent Virtual Assistant to understand user questions. There is no way to write down all the ways in which your users will talk to your bot. And you do not have to. It will learn from the training data that you just entered and make its own guess when users will come and talk to it. You can read more here about how to train your AI after you have put it live.

Training the AI.
Training the AI.

8. Now that you have trained the no code AI, give it a shot. If you have the AI panel open, you see the chat icon on the bottom right corner. Click that icon and ask away. This is what your IVA looks like.

Test your Conversational AI.
Click the bottom right corner in Alphachat to test your AI.

Also you can click on the URL in the AI panel. It is a unique URL for your AI where you can test it. You can also share the URL with your friends and colleagues so that they can also try out the IVA you have built. 

9. All the questions that the AI gets are visible in the Inbox. From here you can easily see how the IVA recommends to train itself. You can confirm the choice for an action for a phrase that the user has said by clicking confirm.

Inbox for training the AI on actual customer data.
Click Validate in Inbox to train the customer phrase to a topic.

Or you can change the action by selecting a different action from the dropdown menu and click confirm. Press Train, wait a bit and the IVA is trained based on the new information.

Training the AI with AlphaChat.
Choose the correct topic from the dropdown menu and then click Validate.

10. To deploy the IVA live simply go to the Widget panel on the left. Copy the code and paste it on the website you wish to deploy the bot. It can be copied to Wordpress, Wix, Hubspot and other website builders. 

Sample code to deploy chat widget with the AI to a website.
Code for copying the AI onto a website.

11. That’s it. You have built your AI. Without a single line of code. Needless to say there are more features in the Alphachat product (e.g. APIs and customizable actions with custom code). But the steps described above are enough for you to get started with your own AI with the no code machine learning tool.

Feel free to play around with Alphachat no code AI and build your own Intelligent Virtual Assistant for your own needs. If you have any questions, feel free to reach out to us or chat with our virtual assistant on our website.