Intro To Dialogflow Cx and ES
Dialogflow was introduced by Google, a platform on which users easily use their agents in a customized way, as they want. Google Dialogflow created two versions of this platform and versions like CX and ES(Essentials). We can see the amplification and constraints in this article.
DialogflowCX gives you a user-friendly interface for creating virtual design and a machine approach to agent design. This gives you buttons, choices, and suggestions that are wonderful because they allow users to know what the options are, and make it easier for them to pick what they want. This is an advanced agent type that is suitable for large and complex agents.
Functions :
The most impressive new capability of DialogFlow CX is that Google integrated new interactive flow visualizations that allow conversation builders to quickly see, understand, and edit their work.
Page and Flows:
In a single virtual agent, separate flows let multiple teams work simultaneously.In simple words, it increases bot management efficiency and mitigates risks of breaking the bot.
For example: If you want to see the doctor, then you can go straight to the doctor’s flow and can also switch to the symptoms as the path is defined,the specific flow related to its own intent.
It can be configured statically in fulfillment of a static condition for a route or with a webhook call, and there is Advanced NLU in cx. which can easily relate to user input. There are also some pre-build agents in it.
Intents:
An intent categorizes an end-user’s intention for one conversation turn. Compared to ES intents, CX intents have been simplified to make them a more reusable resource. The parameters are defined as to extract values from specific parts of the end-user input.
Testing:
In Dialogflow Es the testing is a little bit complex because of reading one intent at a time, but in a Dialogflow Cx the intent pages, parameters, routes, flow can be changed at any moment
Actions and Parameters
Some parameters are defined in the CX version for example name and color and the catchy part is that you can define your parameters which is flexible. When you define a parameter For Example — I am feeling cold today and the parameter goes around like @symptoms is defined as a parameter and takes straight away to the next flow.
As per some limitation count in cx:
. It only accepts English language
.In Dialogflow Knowledge connectors are not supported
.The history in not available, you can’t check the recent activities
Dialogflow ES
This is the standard agent type that is suitable for small to medium and simple to moderately complex agents.I really want to highlight this point that DIalogflow ES will not be blown off course because of the introduction of Dialogflow CX.
For smaller or less complex agents, DialogFlow ES will still remain the right solution and does an incredible job.
As we discussed above, the new version of Dialoglow, then this version of dialoglow is more concerned by developers for doing small projects and small text files .
In this, ES(Essential), it is mostly conversational in text form . Hence on there is no testing on this platform. The agent that are provided is 1.ES checks
But the core features remain the same: the NLP (Natural Language Processing) & entity recognition system.
Cost:
DialogflowCX has some price for their service prices like, it includes all DetectIntent, StreamingDetectIntent 12000 per minute, $0.007 per request. And as per audio input/output 600 per minute, $0.06 per minute, and in the another box DialogflowES it is like all DetectIntent, StreamingDetectIntent Production per Quota $0.002 per request,audio input per ready quota $0.0065 per 15 seconds of audio, and for output $4 to $16 per million characters.
Wrapping up : This article gives you an idea of DialogflowCX and ES,Also tells you about the ease of creating chatbot on this kind of platform.As above mentioned the cost , Functions and Advantages.
You can contact me through : Linked in: www.linkedin.com/in/parth-chaudhary-1415b01b6
Note: We at Techsalo Infotech is a team of engineers solving complex Data engineering and Machine learning problems. Please reach out to us at sales@techsalo.com for any query on How to build these systems at scale and in cloud.
