Dialogflow is the natural language understanding platform of Google that you can use to create omnichannel chatbots.
But should you use Dialogflow to create your chatbots?
Find it out in this in-depth Dialogflow review!
Our Verdict
Our Verdict
I wouldn’t recommend using Dialogflow as a standalone chatbot platform, because you cannot create chatbot flows easily, store user information and personalize conversations (you need to code for that).
But Dialogflow is really good at one thing: understand the intent of the user based on training phrases you provide.
Therefore, I recommend creating a chatbot with another bot builder and integrating it with Dialogflow. Then, you can use the AI-engine of Dialogflow (where it’s good at), and don’t have the disadvantages of it.
Pros
- Built-in AI & NLP: Understand Intent & Entities
- Publish chatbot on 14 channels
- Very good free plan
- Improve chatbot easily with User Input Analytics
Cons
- Cannot collect user information
- Not possible to personalize conversations
- Limited chatbot elements
- Publishing chatbot on most channels is technical
- No Live chat integration
Table of Contents
What is Dialogflow?
Dialogflow is the natural language understanding platform of Google that allows you to understand language with your chatbot.
What Dialogflow tries to, is understand the intent of the user based on training sentences that you give.
Based on those training sentences, Dialogflow knows how to automatically respond to questions of your users.
Additionally, Dialogflow can also extract specific information in a sentence, which are called Entities. For example, if you say “Can I order a veggie pizza”, Dialogflow can understand that “veggie” is the flavour of the pizza.
How to Create a Dialogflow Chatbot: the Interface
Dialogflow has two types of editions: Dialogflow Essentials (ES) and Dialogflow Customer Experience (CX).
Both types of editions come with different interfaces and can be used for different purposes.
Dialogflow Essentials (ES)
Dialogflow Essentials is the standard edition of Dialogflow and most people are familiar with this one.
Within Dialogflow ES, you can understand the intent of the user by providing training sentences to your agent. The agent is then trained to understand these sentences:
And create a reply for it:
Also, you can use Entities with Dialogflow. With Entities, your chatbot can understand the difference between a “veggie pizza” and a “pizza”. In this example, the entity part is “veggie” that relate to a topping of a pizza:
If you want more information on how you can use intents and entities in Dialogflow, check this video for intents and this video for entities.
Moreover, you can test your chatbot in the Dialogflow interface:
Dialogflow Customer Experience (CX)
Dialogflow CX is a relatively new version of Dialogflow and is not yet used by many people.
In general, Dialogflow CX is not recommended for many use cases, unless you have a very sophisticated chatbot.
The benefit of Dialogflow CX is that you have a visual flow builder that provides a better overview of the conversation:
But at the same time, I wouldn’t recommend using Dialogflow CX if you are a beginner with chatbots. The interface is much harder to use than the simple interface of Dialogflow ES.
In general, I think the interface of Dialogflow ES is easy to use and it is easy to set up your chatbot. Dialogflow CX provides a better overview, but also has a steeper learning curve (and you probably don’t need to use it).
Flow Builder Create chatbot dialogs with a visual flow builder. | |
Ease of use How easy is it to use the platform? On a scale of 1 to 5. | 3.5 |
Ease of setup How easy is it to set up your chatbot? On a scale of 1 to 5. | 2 |
Test chatbot Is it possible to test the chatbot before putting your new flows or changes live? |
Chatbot elements
Dialogflow provides basic elements to create your chatbot. Depending on the channel, you can reply with Text, Images, Cards and Quick Replies. I think this is enough if you want to create a simple question/answering chatbot.
But I think Dialogflow lacks some important elements, such as:
- Collecting User Input and storing it in fields
- Using conditions to personalize conversations
- Starting other automations in Dialogflow (good for the scalability of your chatbot)
Image Can you send images via your chatbot? | |
Video Can you send video via your chatbot? | |
Audio Can you send audio via your chatbot? | |
Attachment Can you send attachments via your chatbot? | |
Gallery (Horizontal List) Show a gallery of cards inside your chatbot. A card consists of an image, title, subtitle and button. | |
Quick reply Can you add quick replies to your chatbot where users can click on? | |
Button Can you add buttons to your chatbot where users can click on? | |
Collect User Input Can you collect input from users and store it in fields? | |
Condition Make checks in your chatbot flow based on if-then logic. For example, if the user has not given their email, ask for their email. | |
Delay Use delays between messages in your chatbot | |
Start automation Can you refer from one automation to another and thereby reuse your automations? | |
Split traffic Can you split your trafic inside a chatbot flow? Often used for A/B testing. |
Users
In Dialogflow, you cannot see a complete user overview of all the people who talked with your chatbot.
In fact, if you want to store user information, you need to create a custom integration with Google Datastore or any other type of database.
Contacts overview Can you see all the contacts that talked to your chatbot in one overview? | |
Custom field Store information from your chatbot users inside fields. For example, you can ask for someone's email and store it inside the "email" custom field. | |
Tags Add tags to users in your chatbot flows to organize and categorize contacts. | |
User Segments Can you create user segments based on custom fields and tags? |
Dialogflow AI & NLP
One of the reasons so many people use Dialogflow is because of their AI & NLP, which is really good.
As described above, you can train your Dialogflow agent to understand the intent of the user by providing training phrases.
Also, you can use Entities so your chatbot can understand useful information that your users say.
Keyword recognition Trigger chatbot flow based on certain words or phrases a user says to the chatbot. | |
Intents Trigger a chatbot flow by understanding the intent of the user. | |
Entities Capture specific information from sentences. For example, if a user says "veggie pizza", the chatbot can understand it's not a regular pizza, but a veggie pizza. | |
AI Knowledge Base Can you train your chatbot on a knowledge base (like your website or articles) and then your chatbot automatically answer questions about it? | |
NLP integrations Does it have a direct integration with NLP platforms, such as Dialogflow? | |
LLM integrations Does it have a direct integration with LLM platforms, such as ChatGPT and Claude? |
Live Chat
Unfortunately, Dialogflow doesn’t have a built-in live chat or live chat integration, so it’s not possible to hand over the conversation to a human agent.
Gladly, some companies provide a combination of live chat and Dialogflow, such as Botcopy.
Built-in live chat Does it have a built-in live chat, so you can hand over a conversation to a support agent? | |
Live chat integration Does it have a direct integration with a third-party livechat application? | |
Auto-Assignment Rules Can you set up rules so that conversations get automatically assigned to agents in livechat? |
Channels
With Dialogflow, you can put your chatbot on 14 channels:
- Your website
- Facebook Messenger
- WhatsApp (using Twilio)
- Telegram
- SMS (using Twilio)
- Slack
- Skype
- Viber
- Workplace from Facebook
- Hangouts
- Line
- Kik
- Spark
And you can even use Dialogflow to handle one-click telephony:
Next to the AI of Dialogflow, this is one of the greatest benefits. You can create a chatbot on almost any channel.
While Dialogflow provides many channels, often you need to code to connect your chatbot to a channel (and Dialogflow already gives you the code you need to use). This is good to know when considering Dialogflow as your chatbot platform.
Website Can you publish your chatbot on your website? | |
Facebook Can you publish your chatbot on Facebook? | |
Instagram Can you publish your chatbot on Instagram? | |
Whatsapp Can you publish your chatbot on WhatsApp? | |
Telegram Can you publish your chatbot on Telegram? | |
SMS Can you publish your chatbot on SMS? | |
Slack Can you publish your chatbot on Slack? | |
Email Can you publish your chatbot on email? | |
Voice Can you publish your chatbot on a telephone line (Voice)? | |
Line Can you publish your chatbot on Line? | |
Viber Can you publish your chatbot on Viber? | |
Merge contacts across channels Can you merge contacts across channels, when the same person contacts you over multiple channels? |
Marketing
The marketing possibilities of Dialogflow are pretty limited.
With Dialogflow, you cannot send broadcasts and sequences. In essence, Dialogflow is user-triggered, which means that it responds when the user asks something, but the chatbot cannot initiate conversations (or you need to code this yourself).
Likewise, you can only use Dialogflow Messenger to create a native widget and put it on your website.
With this native widget, you can change the appearance (such as the title and colors) by editing some CSS (mark up language for websites). Also, you can trigger different intents.
Moreover, you can send pro-active messages to website visitors when the page of your website loads.
Broadcasts Send a message to all or a part of your chatbot users at a specific date and time | |
Sequences Send messages on a pre-defined schedule with a certain time interval between those messages | |
Rules Trigger events based on if-then logic. For example, if email is given by the user, send it to your CRM. | |
Website widget Embed your chatbot as a widget on your website (with your own branding & colors). | |
Send proactive messages on website Can you send pro-active messages on your website with your chatbot? | |
Facebook Ref URL Can you create a URL that goes to a specific flow inside your Facebook chatbot? | |
Auto-Reply to Facebook Comments Automatically reply with your chatbot to users who comment on your Facebook Posts | |
One-Time Notification Send one-time notifications via Facebook Messenger for a topic that a chatbot user has opted-in for | |
Recurring Notifications Send recurring notifications via Facebook Messenger for a topic that a chatbot user has opted-in for | |
Facebook Ads Start a conversation with your chatbot when someone clicks on a Facebook Ad | |
Sponsored messages Send paid messages via Facebook Messenger outside the 24-hour window | |
Auto-Reply to Instagram Comments Automatically reply with your chatbot to users who comment on your Instagram Posts | |
Instagram Story Mention Reply Send auto replies to Instagram users who mention your Instagram handle in their Instagram Stories | |
WhatsApp Message Templates Can you initiate conversations with Message Templates on WhatsApp? |
Integrations
Dialogflow doesn’t have any direct integrations with other applications.
So if you want to connect Dialogflow to other systems, you need to use Fulfillment. With Fulfillment, you can make API calls and code your own webhooks so you can integrate Dialogflow with other systems.
Direct integrations How many direct integrations does it have with other applications? | 0 |
Zapier Direct integration with Zapier, one of the largest integration platforms in the world. | |
Make Direct integration with Make (formerly Integromat), one of the largest integration platforms in the world. | |
Make API Calls Can you call an API inside your chatbot flow to send or get data from other applications? | |
Webhooks Can the platform send automatic notifications of all the messages and events going on in your chatbot? |
Dialogflow Pricing
Dialogflow has a Free Plan and paid plans that scales as you go, already starting at $1/month.
Dialogflow ES Pricing
Dialogflow ES is free if you stay under 180 text requests per minute. This means that you can send 7,5 million text messages per month and don’t have to pay a dime.
If you go above the 180 requests per minute, you need to pay $0.002 per request. Also, if you want audio input or output, you need to pay extra:
Dialogflow CX Pricing
When you use Dialogflow CX, new customers get a $600 charge for a no charge trial, that can be cancelled at any time.
After that, it costs $0.007 per Text Request. So this costs $7 if you want to send a 1,000 messages, which is pretty cheap. Also, if you wanto to use audio input or output, you pay $.001 per second:
In my opinion, Dialogflow is really cheap. For most chatbots, you don’t have to pay anything, you can just use Dialogflow ES for free. Only when your chatbot is really advanced or when you handle a large amount of messages, you need to pay. And these prices are still very low.
Free trial Does the chatbot platform provide a free trial? | |
Free plan Does the chatbot platform provide a free plan? | |
Price per month What is the lowest price per month to create a chatbot with this platform? In US Dollars. | $0 |
Monthly pricing available? Is it possible to pay monthly? | |
Money back guarantee Is there a money-back guarantee in case you are not satisfied with the platform? |
Analytics
In Dialogflow ES, you have a dashboard that shows the number of sessions and the number of interactions:
Moreover, Dialogflow has a “Training” feature that shows the messages your chatbot did (not) understand, so you can easily improve the answers of your chatbot:
If you want more advanced analytics, you can use Dialogflow CX, which also provides analytics on Engagement and the different conversation paths users follow:
In general, Dialogflow provides enough analytics to improve the answers of your chatbot.
Dashboard Dashboard that provides general analytics of your chatbot. | |
Flow analytics Can you analyze how users are going through your chatbot flows? | |
User input Get the input from users that your chatbot didn't understand. | |
Sent messages The number of messages that were sent by your chatbot. | |
Open rate The percentage of chatbot users that opened a message inside your chatbot. | |
Click rate The percentage of chatbot users that click on a button inside your chatbot. | |
Conversion rate The percentage of users that converted through your chatbot. For example, the percentage of users that gave their email address | |
Fall back rate The percentage of interactions where the chatbot did not know an answer to a question. | |
Agent analytics Can you analyze the performance of live chat agents? | |
Custom event tracking Can you create custom events and analyze how many times these happened? | |
Custom dashboards/reports Can you create your own dashboard or reports? |
Templates
Dialogflow provides 45 pre-built agents that you can use to get started with your chatbot.
Also, you can export each agent and share the ZIP with others (which is basically the same as using templates).
Number of templates How many pre-built templates does the chatbot platform provide? | 45 |
Make template Can you make templates yourself? | |
Share template Can you share self-created templates with others? |
Support
Dialogflow has extensive documentation on how you can use their platform.
NOTE: I also have some Dialogflow tutorial videos on my Youtube channel, which I definitely recommend you to check out!
Moreover, Dialogflow provides support via email.
Tutorials Does the chatbot platform provide tutorials on how to use its platform? | |
Documentation Does the chatbot platform provide documentation on how to use its platform? | |
Customer support Does the chatbot platform provide customer support? |
Conclusion
So, should you use Dialogflow to create your chatbots?
Yes, you should.
I wouldn’t recommend using Dialogflow as a standalone chatbot platform, because you cannot create chatbot flows easily, store user information and personalize conversations (you need to code for that).
But Dialogflow is really good at one thing: understand the intent of the user based on training phrases you provide.
Therefore, I recommend creating a chatbot with another bot builder and integrating it with Dialogflow. Then, you can use the AI-engine of Dialogflow (where it’s good at), and don’t have the disadvantages of it.
In the past, I have created chatbots with other chatbot platforms (such as ManyChat) and integrated it with Dialogflow, so you can understand the intent of the user with Google’s AI. That way, you have the best of both worlds. Manychat for creating the chatbot flows and storing user information, and Dialogflow for AI. By the way, here is a post on how you can integrate ManyChat with Dialogflow.
Related Posts
Frequently Asked Questions
Is Dialogflow free?
Both Dialogflow ES and CX have a free plan. With Dialogflow ES, you can send up to 7,5 million messages per month without paying a dime.
With Dialogflow CX, new customers get a $600 charge for a no charge trial, that can be cancelled at any time.