How to make your Manychat bot smarter with Dialogflow AI
For the complete guide on how to build AI-enhanced Manychat bots click here
No technical experience is required to enhance your Manychat bot with conversational AI from Google, so you can answer FAQ to reduce your customer support costs, close more leads and boost revenue, and delight your customers 24x7.
You’ll connect a Dialogflow AI agent to Manychat in a few simple steps. Dialogflow is AI from Google used by the biggest brands in the world. Janis makes this technology accessible to every small business in the world.
Janis works in Slack a virtual workspace used by millions of businesses. If you ever wondered how the Manychat team is able to output amazing new features add a rapid pace, it’s because the Manychat team collaborates in Slack. You can collaborate with your team, your clients, partners, and other bots. Collaborate With Janis in Slack and you can manage your AI and achieve your marketing and customer service automation goals.
How does Dialogflow work?
Dialogflow’s strength lies in it’s Natural Language Processing (NLP), AI technology which enables your business to better understand the messages your users send. With Dialogflow, your bot can learn to respond to phrases and understand the meaning of words inside of phrases.
You’ll need to train your bot to learn how to respond and that takes time, so Janis has created pre-trained AI that enables your business to experience the benefits of AI immediately.
Putting Natural Language Processing To Work
- Intents enable you to understand messages and their context and trigger responses. Think of an Intent as a Flow, but for AI.
- Training phrases are messages your users will send your bot and which you’ll use to train AI to learn how to respond.
- Entities enable you to understand that a word inside of a phrase can have different values. Parameters are created when Entities are triggered in training phrases and a Parameter value can be automatically stored in a Custom User Field in Manychat if it matches the Parameter name in Dialogflow.
- Context enables your bot to know the context of a message you receive. You can add or remove a Manychat tag in a Flow to enable or disable context in Dialogflow.
- Events are alternatives to training phrases. For example, the Messsenger “thumbs up” is an event that can trigger a response from a Dialogflow Intent.
- Dialogflow supports multiple languages, and you can use a Custom User Field to tell Dialogflow which language to respond with.
How do I get started?
Step 1: Get AI
The first step to adding AI to Manychat is to get a Dialogflow AI agent. Head over to Dialogflow.com, sign-in with your Google login and click Create new agent.
You just need to give your AI agent a name and click Create to save your AI agent. It’s a good idea to give your AI agent a name that is similar to your ManyChat bot so it’s easy to manage.
Step 2: Connect your AI to Janis
You’ll need a free Slack workspace. You’ll want to add Janis to Slack and chat with Janis to connect a Dialogflow agent.
You can connect an unlimited number of Dialogflow agents and Manychat bots to Janis in one workspace. Any time you want to connect a new bot, just say Add a bot.
Step 3: Connect your Manychat bot to Janis
You can use our Artifiicial Intelligence template for Manychat, or you can do a custom integration in a few simple steps. If you’re new to AI, the template makes it quick and easy to start benefiting from AI immediately. The main difference between the template integration and the custom integration is that the template comes with pre-trained AI you can install to Dialogflow so you can understand common things users say to bots and a Manychat template that you can use to edit your responses in Flows. AI training takes time, but the template option gets you much further ahead in the training process.
When you choose the template integration, Janis will give you a key. You’ll want to copy the key to your clipboard, install the Artificial Intelligence template to Manychat and paste in the key and you’ve got a Manychat bot responsive to user input immediately.
If you don’t want the template, you can do a custom integration and Janis will give you a URL that you can paste into a dynamic input card in your Default Reply which will forward all user input to Dialogflow so any message a user sends your bot will be processed with AI.
Step 4: Connect Facebook
When you connect Janis to your Facebook page you’ll unlock powerful AI management capabilities. Janis will monitor your bot, alert you of problems and help you fix problems fast. You can also pause your AI and take over live and train your AI to learn from your Messenger conversations.
Step 5: Start working with Janis
If you send your bot messages and you get back responses, you know your AI integration is working properly. You’ll start to get alerts in Slack for messages your bot can’t understand, and you’ll start to see those responses triggered by Dialoglow appear in Messenger.
You’ll want to understand some basic AI concepts that will help you boost revenue and reduce your customer costs and you’ll want to learn how to benefit from the AI tools so you can manage your AI and delight your customers 24x7. Janis is a complete toolkit that makes it easy. AI templates will help you experience the benefits of AI immediately, while an AI assistant will help you integrate AI and retain your users through that process.
Build smarter automated customer experiences with Dialogflow + Manychat.
🤖 Need an easy way to connect Dialogflow to Manychat?
🤖 Training Dialogflow NLP takes time. Need a Dialogflow template?
👉 https://janis.ai/dialogflow-templates/
🤖 Learn more how to build chatbots with Manychat and Dialogflow
