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 Google’s platform for creating chatbots.
With Dialogflow, you can understand the user’s intent by training a bot on sentences.
Based on those training sentences, Dialogflow knows how to automatically respond to questions of your users.
Dialogflow can also extract specific information from a sentence. These are known as 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)
- 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 | |
Ease of use | 3.5 |
Ease of setup | 2 |
Test chatbot |
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 | |
Video | |
Audio | |
Attachment | |
Gallery (Horizontal List) | |
Quick reply | |
Button | |
Collect User Input | |
Condition | |
Delay | |
Start automation | |
Split traffic |
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 | |
Custom field | |
Tags | |
User Segments |
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 | |
Intents | |
Entities | |
AI Knowledge Base | |
NLP integrations | |
LLM integrations |
Live Chat
Unfortunately, Dialogflow lacks built-in live chat or a live chat integration. So, you can’t transfer the conversation to a human agent.
Gladly, some companies provide a combination of live chat and Dialogflow, such as Botcopy.
Built-in live chat | |
Live chat integration | |
Auto-Assignment Rules |
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.
Dialogflow offers many channels, but you often need to code to connect your chatbot to them. Luckily, Dialogflow provides the necessary code. This is good to know when considering Dialogflow as your chatbot platform.
Website | |
Facebook | |
Instagram | |
Whatsapp | |
Telegram | |
SMS | |
Slack | |
Email | |
Voice | |
Line | |
Viber | |
Merge contacts across channels |
Marketing
The marketing possibilities of Dialogflow are pretty limited.
With Dialogflow, you cannot send broadcasts and sequences. Dialogflow is user-triggered. This means it only responds when a user asks a question. The chatbot cannot start conversations on its own, unless you code that feature.
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 | |
Sequences | |
Rules | |
Website widget | |
Send proactive messages on website | |
Facebook Ref URL | |
Auto-Reply to Facebook Comments | |
One-Time Notification | |
Recurring Notifications | |
Facebook Ads | |
Auto-Reply to Instagram Comments | |
Instagram Story Mention Reply | |
WhatsApp Message Templates |
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 | 0 |
Zapier | |
Make | |
Make API Calls | |
Webhooks |
Google Dialogflow Pricing
Dialogflow has a Free Plan and paid plans that scale 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 | |
Free plan | |
Price per month | $0 |
Monthly pricing available? | |
Money back guarantee |
Analytics
In Dialogflow ES, you have a dashboard that shows the number of sessions and the number of interactions:
Dialogflow also has a “Training” feature. It shows which messages your chatbot understood and which it did not. This makes it easy to improve your chatbot’s responses:
For better analytics, try Dialogflow CX. It offers insights on Engagement and the various conversation paths users take:
In general, Dialogflow provides enough analytics to improve the answers of your chatbot.
Dashboard | |
Flow analytics | |
User input | |
Sent messages | |
Open rate | |
Click rate | |
Conversion rate | |
Fall back rate | |
Agent analytics | |
Custom event tracking | |
Custom dashboards/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 | 45 |
Make template | |
Share template |
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 | |
Documentation | |
Customer support |
Is Dialogflow worth it?
So, should you use Dialogflow to create your chatbots?
After this Dialogflow review, I can confidently say – yes, you should.
I don’t recommend using Dialogflow as a standalone chatbot platform. It makes creating chatbot flows hard. You also can’t easily store user information or personalize chats. You need to code for those features.
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 or paid?
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.
Is Google Dialogflow open source?
No, Dialogflow is not open source. It’s a proprietary AI-powered chatbot development platform owned by Google.
Is Dialogflow easy to use?
Dialogflow ES is relatively easy to use for beginners, but Dialogflow CX has a steeper learning curve due to its advanced flow builder.
What are the limitations of Dialogflow?
Dialogflow lacks built-in chatbot flow creation, user data storage, and personalization options. It also requires coding for many advanced features and integrations.
Should I use Dialogflow ES or CX?
Use Dialogflow ES if you need a simple, free, and easy-to-set-up chatbot. Use Dialogflow CX if you need advanced conversation flows and have technical expertise.
What is Dialogflow used for?
Dialogflow is used to create AI chatbots. These chatbots understand what users want and answer questions on various platforms. These includes websites, messaging apps, and voice assistants.