Welcome to ORAI Docs

Welcome to your one-stop repository for all documents on ORAI. Here’s wishing you a successful engaging experience with ORAI.

Please feel free to reach out to connect@orai-robotics.com for any feedback or addition request.





Welcome to ORAI Docs


 Conversational Automation

  • Smart Response

  • Conversation Flow – Paths

  • Nodes

 Advanced Conversations

  • Train

  • Multi-lingual Bots

  • Conversational Context

  • Related Matches

  • Small Talk

  • Programmable Delay

  • Voice

  • User Feedback

  • NLP Debug Mode Channels

  • Facebook Messenger

  • WhatsApp

  • Telegram

  • Twitter

  • Line

  • Slack

  • Skype

  • Website

 Live Chat

  • Conversations

  • Configurations


  • Human Takeover

  • General Configurations

  • Users

  • Formatting Controls

  • Broadcast

  • Campaigns

  • User Attributes

 Analytics Dashboards

  • Live Chat

  • Bot Platform

 Account Management

  • Billing

  • Plans and Upgrades

  • Portal User

  • Support ( Channels and Processes. )

  • Passwords and Security

  • Get Professional Help

ORAI is available to its customers as 2 valued offerings – chatbots and live chat. If the need is to build and manage automated chatbots alone to engage users, then the recommended offering to use is chatbots. If the need is to engage users in real time conversations with a human agent or support a mix mode of self-service conversational automation with real-time human conversations, then the recommended offering to use is live chat.

ORAI allows you to build chatbots of varying complexities & scale with ease. With 150+ chatbot templates to help you get started, a best-in-class Conversation Flow builder, robust integration capabilities and ability to deploy the bot on Website, Facebook Messenger or one of 14+ channels, ORAI has made Chatbot building easier than never before. 

ORAI live chat allows business to engage with its customers, employees and prospects over real-time human conversations across 14+ channels. Other key features include native self-service automation, skill based routing, one-view inbox, real-time administration and supervision, in-depth analytics and dashboards, queue management amongst others.

The platform and it’s capabilities also includes sections to help build, deploy, train, look at analytics as well as other associated capabilities such as Broadcast, Campaigns, Portal Users, Visitor information, etc. 

In the following sections we will try to understand what is the functionality of each of these sections and how they can help you in building your perfect chatbot.


As the name suggests, this section is what you would use the most while building your chatbot. It is further subdivided into FAQs, Paths, Entities, and Data sources.

2.1 Smart Responses


This section is what primarily drives the automated responses and is powered by ORAI’s proprietary NLP engine. Adding FAQs is fairly straightforward, you just click on Add FAQ, add the query, add any variations of the primary query and then add the appropriate response. The response can be a simple text message as well as can be used to trigger paths. The FAQs can get more complex by adding and tagging entities in the query. The intent determination from the user query  is made by the NLP engine based on the training provided. 

There is also an option to upload all the FAQs at once via the CSV upload utility. This is the quickest way to train the chatbot if you have data already available in a FAQ format. FAQs/Intents can be categorized as well to manage them better as well as be tagged to a language while building multilingual bots. For Business plan users, you can also add and manage custom synonyms and stopwords from this workflow.

2.2 Paths

Paths are complex conversational flows which would involve more interactive elements than what the FAQ module can provide. The entire conversation design/structure of the chatbot can be modeled using the conversation modeler. Each specific aspect of the chatbot or a workflow can be built as its own path and then linked appropriately to put in place the entire chatbot. This modular design can be very helpful for triggering certain chatbot functionality from various entry points which may include FAQs as well.


Each path is composed of interlinked nodes. Each node is meant to perform a particular function. Some of the nodes are – Sending a simple message, carousel nodes for displaying rich menus or item listings, sending a message with quick responses/options, various multimedia nodes like send image, video and audio, faq filters, setting attributes, identity and many more.

There are a number of nodes focused around integration as well. JSON API node to quickly link to any standard REST API which supports various authentication modes as well as quick, easy ways to use the response values. The chatbot can also be linked to Zapier which can be used to connect to various other third-party services. Other than the above, there are a lot of GUI driven native integrations provided by the platform which include – Salesforce, Google Sheets, Google Calendar, SMS providers and more which will be added to the list. 


2.3 Entities

Entities are critical data points or values which are extracted from a user query/input. The system provides inherent capabilities to determine entities and isolate them from the actual user intent. There are a number of system defined entities which are provided like – Date, Time, Date and Time, Amount, Cities, Countries and many others. Also, along with these system defined entities you can also define your own custom entities which could be list of products or services or anything else which can be an important data point for taking a particular action or understanding of the user intent.


2.4 Tabular Input

Data sources are provided as a capability to facilitate loading of information to help the chatbot respond to certain queries. A data source is typically a two-dimensional data table which could be a list of entities along with the values of their corresponding attributes. File formats supported are CSV and Excel. Once the file is uploaded, intents and entities are automatically generated from the file and are consumed by the chatbot for training. The chatbot will now automatically start responding to queries around the attributes of any of the entities which are present in the tabular data. 

The Intents and Entities can also be independently modified to probably add more variations to them or changing the response language to make it more meaningful.

3.Processing Information

We understand that during the course of your conversation with a user, you will need to process a lot of information. ORAI provides you the use of Attributes to make it easy to collect, process, persist and even report on information collected.


Some of the key capabilities include:

3.1 Collecting Information in Attributes

There are various means of collecting information from your bot user and saving it as an attribute. These include the use of nodes like Request User Data, Identity and JSON API in your conversation flow. You can also initialize the web chatbot with attributes to set the initial context. Once you set an attribute value using one of these Nodes, it is automatically persisted for use in the conversation flow as well as for reporting & viewing later.

3.2 Processing Attributes

Nodes like Script Node and Set Attribute allow you to set & process values stored in an attribute. Script Node in particular is a powerful means to do various kinds of processing on the attribute values including string manipulation to mathematical operations.

Besides the above, all Display Nodes like Send Message, Send Message with Options, Send Carousel etc allow you to use the attributes as a placeholder within the display text.

3.3 Reporting on Attributes

ORAI provides two key mechanisms to let you view & analyze the information being collected.

This includes:–

User Report: You can configure the available columns on this report to include specific attributes

User Details: For an individual user, ORAI automatically displays the entire list of available attributes and information collected against those for that user.

4. Deploy

4.1 Test the Chatbot

Once you have started building the chatbot, you would want to test out the conversation flow structure as well as the NLP responses.

This can be easily done from the home page of your account, clicking on the three-dot menu icon for a bot and selecting the option “Test Bot”.

4.2 Channels

Once the chatbot is built and trained to satisfaction, it needs to be deployed on any of the multiple messaging channels which are supported. The same chatbot can be associated with multiple channels without any additional efforts.

The platform does the part of normalizing the conversational experience for the channels configured and providing a consistent experience tied to what was built as part of the FAQ training and the conversational paths.

There are 14+ channels on which the chatbot can be set up which include Whatsapp, Messenger, website widget as well as standalone web link, mobile SDKs for Android and iOS, Telegram, LINE, Slack, Skype and many more..

The steps for configuring the chatbot for each of these channels are different and are amply documented in the user assistance guides for the channel setups. 

5. Analytics

Once the chatbot is built and deployed on the channels, there are various statistical data points which are collected for the chatbot usage and are made available via the multiple Dashboards as well as the Users section which particularly focuses on the chatbot users. The Dashboards cater to a specific aspect of the chatbot and highlights such metrics :– 

5.1 Engage

The Engage dashboard primarily provides stats around the chatbot engagement. Some of the key elements here are the number of user interactions, new user growth and usage trends, and some metrics around the conversation type which include average messages per conversation and conversation duration. It also common button actions and frequent messages data. 

5.2 Responses

The Responses dashboard primarily focuses on the NLP aspects for the automated responses to user queries. You get to see trends of total questions asked to the bot and the split between answered and unanswered questions. You can also drill down to see the individual questions also with details of the chatbot response, NLP engine’s score determination for the match and you can also train the chatbot from there.

5.3 Retain

The Retain dashboard helps you with data and insights around user retention. You get a clear depiction of the repeat usage patterns of the chatbot users with time and can understand when they drop off post-joining.

5.4 Support

The Support dashboard primarily contains statistics around the live chat aspects and agent performance. Some key metrics are average time to respond, the average time for a user to wait for an agent, inbound and resolved query trends, etc. Also, these data points can be grouped by days, agents or agent category to provide more meaningful insights. 

6. Other capabilities

There are a number of other capabilities which can enrich your chatbot outside what is provided in the build section. Below is a brief description of these :– 

6.1 Live Chat

Live Chat capability for the chatbot also comes as a pre-packaged solution without dependency on a third-party service. This capability augments the automated responses capability of the chatbot to handle cases which the chatbot is not currently trained for or for cases where a human intervention is necessary to perform a certain task. Chats can be seamlessly handed over to an agent, live chat agents can be assigned to categories/groups, chats can also be transferred between agents and chat context is maintained and can be exported/downloaded.


6.2 Broadcast

Broadcast capability helps you to proactively reach out to your users for certain announcements as well as send any promotional activities you might have for your chatbot users. Broadcasts can be sent to all users or users can be segmented as well to allow for more targeted and relevant marketing messages. Various stats can also be viewed around the broadcasts which are sent out. You can also set up periodic broadcasts or broadcasts which trigger a certain path/flow. It is to be noted that broadcasts are channel dependent and there could be restrictions on promotional content as well as the timing of the broadcasts which are channel-specific.


6.3 Campaigns

Automated campaigns can be designed to re-engage the users or to nudge them to complete a particular action if they have dropped out of it. Each campaign can have a sequence of steps which can send out a message to a user or trigger a path. Each of these steps can have a particular delay between that step and the one prior to it.
Users’ subscription to campaigns can be managed via the nodes for subscribe as well as unsubscribe.

6.4 Portal Users

For a complex chatbot, more than one users might be required to manage the bot. The platform provides the ability to invite multiple users to the chatbot in various capacities. You can add chatbot administrators, live chat support agents, or bot builders. The access to the various workflows would be controlled depending on what role the particular user is provided. It is to be noted that a user who already has another account on the platform cannot be invited to a different account’s chatbot.

7. Account 

The Account section helps you manage your ORAI account, it shows the total number of interactions you have consumed, the number of bots you have as well as plan and billing information, including current plan details, any associated trials, payment history, etc. You can upgrade your plan based on your requirements from this section.

Patform Registration



ORAI is the leading digital customer experience platform that allows you to leverage the power of automation and conversational AI to acquire, grow and serve your customers. This platform allows you to 

  • Initiate your Bot creation journey using one of the 150+ templates

  • Deploy the bot on Website, Facebook Messenger or one of the any 14+ web, social & mobile channels

  • Design the conversation flow for your bot, using the Conversation Flow Builder

  • Set up and manage live chat on Website, Facebook Messenger or one of the any 14+ web, social & mobile

  • Easily train your bot and allow agents to have conversations with end users leveraging FAQs, Intents & Entities 

  • Build Integrations with various systems using one of the many integration options available 

2. What ORAI can do for you 

Customers are engaging with businesses across multiple channels and businesses are struggling to provide a seamless, consistent experience to its customers. Imagine a customer reaching out to a business via multiple channels (Web, Facebook, WhatsApp, Email) over an urgent issue and having to speak to 4 different representatives where one is not cognisant of the other’s conversation. In such scenarios, customer experience suffers thereby reducing the chances of retention. On the other hand, if we could empower support agents or self-service chatbots to understand a customer’s need quickly and personalise the buying or resolution experience for them, then CSAT and NPS would be at all-time high. As we move into the post-COVID era, customer experience is increasingly important for businesses to engage with their customers, internal or external.

Some of the key use cases that businesses today can use ORAI chatbots and live chat for include:

  • Comprehensive Customer Support: Chatbots can cost-effectively streamline your customer support process. ORAI allows you to train the bot for giving automated replies to your end-users and seamlessly transition to live chat agents when needed.

  • Automated Sales & Marketing: Chatbots enable an instant & interactive way for users to interact with your brands, get 24×7 recommendations & guide users to complete transactions. ORAI allows you to broadcast messages to your users and build successful step-by-step campaigns for user segments.

  • Human Resources: Chatbots help embraces the future of people management helping automate hiring & onboarding and offering instant responses to employee queries. 

  • Services Management (ITSM)Chatbots can help increase service level satisfaction for your internal customers by providing a 24×7 service to address IT service support queries and a range of simple tasks.

With its simple user interface and no coding philosophy to building chatbots and setting up live chat, ORAI makes it easy to build chatbots for your own specific use case along with managing customer experience.

Our Support Team is always available to help answer your queries on email. Simply write to connect@orai-robotics.com and you could also look to use the services of our ‘ORAI’s Genius’ experts to have us do the heavy lifting of designing and building the bot or for any other customisation that you may need.

3. How to Build a Chatbot using ORAI 


You can get started on your chatbot journey, by simply opting to create a new chatbot from the ORAI Home Page. ORAI offers you 100s of templates across use-cases that can further accelerate the bot creation and setup steps.



A chatbot is a sum total of the NLP Training to you provide for the bot to be able to have conversations, the Conversation flows you design including menus & Integrations. 

In ORAI, these functions are easily available under the section “Build” in the navigation.



The world of chatbots can be a little daunting at times. No need to worry at all. We have put together a bunch of articles to help you navigate through your chatbot journey with ORAI.


1. Introduction

A chatbot is the core element in the platform around which other entities and functionalities are built. A chatbot can be defined as an encapsulation of the responses and the conversational flows. It would be also inclusive of associated capabilities of broadcasts, live chat, campaigns, etc.

2. Chatbot Components


The core building components of a chatbot include :

  1. FAQs – Each FAQ represents a set of query variations and expected response for those. This is the building block for you training the Chatbot for NLP intelligence.

  2. Paths – ORAI’s best in class conversation flow modeler allows you to build conversation flows easily using a drag & drop UI.

  3. Intents and Entities – For advanced intelligence, you can create FAQs with intents that handle system entities like dates, location etc as well as custom entities.

  4. To aid with the conversation intelligence, capabilities to handle Synonyms, Stopwords are also available for you to configure and manage.

Besides the core build components, there are a number of features available to aid you with your marketing, customer support, HR and service management requirements. The key ones here include

  1. Live Chat: ORAI allows the conversation to be transferred to your support agents if the bot is not able to help your users during a conversation.

  2. Campaigns & Broadcast: Use push messaging via your bot to keep your users engaged.

  3. Integrations: Integrate with a variety of Cloud or internal apps using ORAI’s strong integration capabilities.

  4. Analytics & Reporting: Get various reports on users interacting with your Chatbot. Understand aggregate patterns as well as look at individual user interactions to make better decisions on continued utilization & training of your chatbot. 

3. Deployment

A single chatbot can be deployed or set up in multiple channels. The platform is designed keeping build once – deploy anywhere philosophy at the core. The choice of channels would be dependent on the user base for which it is intended.

4. Multiple Chatbots

Cases where multiple chatbots would be needed are where the chatbots are expected to serve completely different use-cases or cater to varied audience sets. For example – A company might have multiple products and would in that case require different chatbots for each of them. They would then reside on the respective product websites or social media channels.

You can create multiple chatbots from the platform, as per the plan limitations and they can be connected independently to the various channels. You can view and manage all your chatbots under your account from the home screen. You can also use the chatbot switcher at the top right to change the context from one chatbot to another.

5. References

  1. Channels – A Chatbot designed & developed once can be deployed on multiple channels including your website, Facebook Messenger, Whatsapp, Twitter & more

  2. FAQs – Learn more about FAQs and how to use them to train your bot

  3. Paths – Learn more about building conversation flows

  4. Intent & Entities – Learn more about Intents & Entities

  5. Synonyms & Stopwords – Learn more about Synonyms & Stopwords

  6. Dashboards Engage, Responses, Retain & Support – Learn more about Analytics on ORAI.

  7. Integrations – ORAI makes it easy to enable various integrations on 

  8. Document Lookup – Learn more about our Smart response features



1. What is a Chatbot Template

A chatbot template is a pre built chatbot structure that comes ready with:-

  • NLP/NLU Training: A chatbot template would typically include a minimal listing of FAQs with which the bot has been trained to have conversations around the purpose of this chatbot.

  • Conversation Flows/Paths: A chatbot template comes with well defined conversation flows including display constructs like messages, carousel cards & more as well as some Integration & Process touchpoints.

ORAI has a collection of 150+ chatbot templates available in our Bot Marketplace and users can select any one of them to get started on your Bot building Journey.

Bot Marketplace is easily available on https://botstore.app.ORAI.com/. Alternatively, you can also access it from under the Profile Menu on top right of your ORAI Account.  

2. Bot Marketplace 

ORAI’s Bot Marketplace is an extensive library of chatbot templates for a wide range of use cases across a number of categories.
Key Categories include :-
HR, Customer Support, ECommerce, Education, Marketing, Travel, Finance and more. 

3. Using a Chatbot Template 


While creating a new Chatbot, ORAI gives you an option to create it using a template. Simply select the option to “Build from Template” 


And then Click on “Select a Template” to be redirected to the Bot Marketplace.


Once in the Bot Marketplace, you can select from the 150+ template available.

Narrow down to what you’re looking for by clicking on one of the categories in the left navigation panel. Alternatively, simply search for what you are looking for by starting to type in the “Search…” box in the top right of the portal. 

Once you have located the Chatbot Template that you’re interested in, you have a range of options available to learn more about the Chatbot Template.


These include – 

  1. View Details  Allows you to review the detailed description of the functionality handled by the Chatbot Template. This text is typically written by the Bot Developer 

  2. T ry  Allows you to see the chatbot in action. This is an excellent way to let you understand the functionality better and then make an informed decision about your interest in the specific chatbot template. 

  3. Unlock – Select a template that suits your use case & requirements the most, by clicking on Unlock from the View Details page




Once you have clicked on Unlock, the selected chatbot template will be added to your Templates and you would be redirected back to the Create Screen with the selected template showing prefilled.

Click on PREVIEW to continue to the next step and then click CREATE after the REVIEW. 


Once a chatbot has been created using a Chatbot Template, it will be available on your Home Working Space. You would notice that the FAQs for training and Conversation flows (Paths) have been copied over from the Chatbot template for you to give a start to your bot. 




From this point onwards you would be able to work on this bot like any other bot, and go on to :– 

  1. Train the Bot further – BUILD > FAQs

  2. Update Conversation Flows – BUILD > Paths 

  3. Configure the Bot – Give it a new name, update theming and more – CONFIGURE 



1. Introduction

Interaction is an important term to understand since the platform usage is determined in terms of interactions. The number of interactions gives a good understanding of the activity for a particular chatbot.

2. Definition

An interaction can be defined as a user action (a query or a message sent or an action taken in terms of a button/option-click) leading to a single or multiple responses from the chatbot. An individual conversation or session of a user with a bot will typically consist of multiple back and forth interactions.

In the above example, a user query and the two subsequent bot responses comprise of a single interaction.

3. Additional Cases & Types

While the interactions explained above typically cover all kinds of text, multimedia exchanges between a user and the Chatbot, there are a few other cases to consider: 

3.1 Human takeover

With respect to Human takeover responses as well, the above holds true just that the response would be from the human agent and not the chatbot.

3.2 Broadcast

Outside of the above, each outbound message per user sent as part of a broadcast a campaign would be treated as a single interaction.

3.3 File Uploads

File Uploads are tracked separately and besides the regular Chatbot interactions and include the scenarios where the end-user has had to upload a file to continue with the flow. 

3.4 Voice Interactions

Voice interactions – Voice to Text and Text to Voice is handled using Google Voice and would be tracked/charged separately by your Google Voice account. For more details on how to set up Voice on ORAI, connect to us on connect@orai-robotics.com.



1. Introduction

The ORAI platform comes pre-packaged with it’s own proprietary NLU engine for making the chatbots built on the platform respond most accurately to the user’s queries.

While there are a lot of complex computations which happen for determining each response, we have made great efforts to keep the platform simple for building and training the chatbots. The following sections will help to throw light on what goes on behind the scenes from an NLP/NLU perspective for resolving each query.

2. NLP Pipeline

The NLP pipeline can be defined as a series of steps which happen in perfect synchronization to process the query and terms and provide the best response. Each step or component of the pipeline is focused on performing a particular objective and then all these results are consolidated, reconciled and the best match is returned by the chatbot.This pipeline is what orchestrates all the individual aspects.

Let us look at each of the components in more detail:-

2.1 Normalization

To reduce bias in the pattern recognition algorithm tokens transformed into a consistent format which is lower case. This is also necessary since many users prefer lower case text for chatting.

Also noisy characters e.g. punctuation can also be removed for better downstream processing.

2.2 Tokenization

Input messages are split into sentences, and then sentences are split into tokens/words. Tokens are the lowest common denominator for further processing.

2.3 Stop Words Removal

Stop words are frequently occurring words like ‘the’, ‘and’, ‘a’, etc. that do not contribute greatly to understanding text and are thus removed from the input message. This helps in reducing noise and improves the accuracy.

Custom Stopwords can also be added to enhance the training of the NLP engine.

2.4 Spell Check

The platform includes capability to correct misspelled words in user messages.The spell check models continuously learns new words based on the training data added by Bot Administrator. It computes and keeps track of frequencies of words in the system to identify misspelled words. It is based on a word distance algorithm called “Levenshtein Distance”. 

For every user query if we detect any word as a misspelled word we choose the best suggestion based on the above mentioned word distance algorithm. The spell check dictionary automatically rebuilds itself on every new statement being added to the system.


Let’s say the user message is  “rechagre offers for prepiad with 10GB data and unlimted national calls”.  This user message is converted to “recharge offers for prepaid with 10GB data and unlimited national calls” before any further processing.

2.5 Stemming/Lemmatization

The root of each word is determined to eliminate affixes from words. The approach is different for different languages as well. In some cases the system would perform lemmatization to get to the root word whereas in others it would use the stemming approach. These are fundamentally different in their approaches but are used for the same intent of distilling the terms to their base form.

For Example:

The word stem of liking, liked is determined as like. This helps in better semantic understanding.

2.6 Conversational Context

NLU capabilities of the chatbot allows it to maintain conversational context while conversing with a user, by keeping track of the entities. This makes the conversation easier and quicker so that user need not mention the entity in subsequent query carrying the same context.

The NLU engine remembers the entities used in a session by saving them as conversation context history. Conversational context is also detailed in it’s own section.

2.7 Named Entity Recognition

Entities are very important for identifying and extracting useful data from natural language input.While intents allow us to understand the motivation behind a particular user input, entities are used to pick out specific pieces of information that users have mentioned. Any important data to get from a user’s request is an entity.

There are built in entities like Day/Date/TimeQuantity/Country and many more. Specific Custom Entities can be added for a use case, for Telecom plans the possible values can be “unlimited national calls”, “unlimited data plan”, “Fixed call plan” etc. 

The Bot Administrator gets to specify the entities expected in user queries and the extraction engine extracts these entities from the user query.


“What are pre-paid plans with 10GB data and unlimited national calls?” 

The entity extraction engine can figure out the user is talking about “10GB” data and a plan of type “unlimited national calls”.

2.8 Figures of Speech Determination

The tokens/words are tagged into various figures of speech like nouns, verbs, adjectives, adverbs, etc.These data points are used to tag the query and then give appropriate weightage for these parts of speech in the final representation. This influences the responses determined by the NLP engine to result in more relevant matches.

2.9 Synonyms

Synonyms are alternate words to denote the same object or action. From a bot and context relevancy, typical use cases involve your domain-specific synonyms. It could also be used for cases of common misspellings, abbreviations, and similar uses.

You can add more than one synonym by pressing tab/enter key after each entry. The system finds matching synonyms and adds to your list, you can remove these if you don’t find it relevant.

2.10 FAQ Disambiguation

Related Matches is a capability which lets the bot provide not just the best response from the training data set but also other options which were under consideration and were close to the top match.

The number of options which are shown to the user is dependent on how many trained responses matched the query and the distribution pattern of their scores. The system also makes a determination of the most well formed statement/phrase from the set of variations and uses that to present as the variation. 



1. What is a Path 

1.1 Introduction

“Path” is a Conversation Flow design for the Chatbot. You would at times, see the terms Conversation Flow and Path being used interchangeably. A conversation flow typically consists of one of more steps for a specific purpose. As an example see a very simplistic conversation flow below that consists of a single step of sending a message via the chatbot to the end user. 

2. Conversation Flow Modeler

2.1 Introduction

Conversation Flow or Path design is a critical aspect of any chatbot and covers end-to-end scenarios of chatbot actions and responses. With the increased complexity of the business logic for the chatbot, the flow path design also may get complicated to visualize and build as a whole.

ORAI’s Conversation Flow Modeler is a best in classpath designer allowing for Paths to be edited and visualized on a single canvas with the ease of working on a mind map.

Conversation Flow Modeler can be accessed from the Navigation in the Build Section. You can further navigate between paths by either choosing a path on the Path Selector available on the left-hand side of the canvas or by creating a new path.

On the top left-hand side of the canvas, the user has the option to toggle the presence of the path selector. 

The menu in the top left of the canvas also provides options to – 


  • Delete the Path

  • Test the Path 

  • Edit the Path Name (Path Key)

  • Copy the Path

  • Zoom-in/Zoom-out of the Path

2.2 Standard Canned Paths

All new Bots created in ORAI come with standard paths that you need to be aware of :– 

  • Welcome New User – This is the Flow that any new user starts from when they interact with the Chatbot for the very first time.

  • Greet Returning User On the Website Bot, if a user returns to the Chatbot, they start with this Path as against the Welcome New User.

  • Default Message This is another very important Path to be aware of. This is triggered when the Chatbot is not able to comprehend the user’s query. You could include a simple message apologizing to the end-user for not being able to answer their query.
    Alternatively, a lot of customers use this flow to collect more user from the information to be able to create a ticket with their query.


  • Live Chat This is a notional Path that is to be triggered if you want the user query to be redirected to your team of Live Chat Agents on ORAI.

  • Post Resolution – Once a Live Chat Agent on your team, marks a query as resolved, this is the flow that is triggered. 

Note: Whatsapp doesn’t allow messages to be triggered by the Bot to its user, to initiate a conversation the end-user has to start a conversation with the bot first, the end-user can enter any text and the bot will start. 

The following behaviors are common for all platforms. 

If the user enters any term such as ‘Hi’, ‘Hello’ the bot will start from the ‘Greet returning User path’, you can redirect them to your desired path via ‘Trigger a path node’.

Any term entered by the end-user that has an FAQ will display the response associated with it. 

3. Nodes

3.1 Introduction

Each node is a logical step in the path flow and is represented on the canvas by a different color and consists of additional elements depending on the type. For example, a Send Message will show a preview of the message on the canvas whereas a Carousel will show the various cards as part of the Carousel.

Nodes are a building block of the conversation flow being designed as per the intended user journey for the chatbot’s end user.


The various types of Nodes provided include :– 

  • Display Information Nodes: ORAI provides a number of options to present information to the end user via the chatbot. These range from simple messages, images, carousel cards & more.

  • Data Input NodesCollecting information from engaging users is a key function of most chatbots. ORAI makes it easy to do the same by providing a number of options to collect data using nodes like Request User Data, Identity Node & more.

  • Processing NodesORAI also provides a number of ways to handle & process information within the chatbot and to make conversation flow branching decisions.

  • Integration Nodes: A large number of Integration focused nodes are available ranging from JSON API Integration to standard nodes for out-of-box integration for Salesforce, Google Sheets & Calendar. 


3.2 Adding a Node

A node can be added by clicking on the “+” available on the bottom right. Alternatively, a node can also be added by clicking on “+” available at the bottom section of the node.

3.3 Editing a Node

A node can be edited by clicking on the edit icon next to the node. The option appears when the cursor hovers over the node. Alternatively, the node can be edited by double clicking the node which opens up the dialog box.


3.4 Building Connections

A connection between two nodes can be created by clicking on “+” available at the bottom of the first node and dragging the connection to the second node that it needs to be connected to. This option is also available from nodes that support branching.

This includes the “Send Message with Options”, “Carousel” and “Decision” nodes. Each such option to build connections to existing paths or to add a new node at that point, is represented by a “+” icon.

3.5 Deleting a Node

A node can be deleted by clicking on the delete icon next to the node. The option appears when the cursor hovers over the node.

3.6 Branching off to another Path

To redirect the flow to a different path, use the “Trigger Path” node and select the path that you would want the flow to be redirected to.



1 Introduction

Users in the platform terminology would mean the end users of the chatbot who would interact with the bot over the various supported messaging channels the bot is set up for. These users are not to be confused with the users who would log into the ORAI platform to build, deploy, manage, train or analyse the bot. Those groups of users are referred to as Portal Users.

2 Behaviour and fields

A user record is automatically created by the platform when a bot user interacts with the bot for the first time. There are some core attributes or fields which are associated with a user like – their associated channel, date/time which they started using the bot, date/time of their last interaction. 

Additionally, based on the channel of communication of the user, more fields can be populated for a user based on availability and access of data. Some examples of this are – For Facebook Messenger, the profile picture and name of the user are retrieved for every user record. Similarly, for Telegram users, the username or handle of the user is obtained and displayed.


For every user, based on their interaction, various state elements are maintained to manage their conversations with the bot. This could be a particular step in the path or context terms stored in the bot’s memory.

There might be multiple records for a single end user if they use the bot via multiple channels. User records are not automatically merged and synced due to lack of a primary field for association. For web bot users, a user would mean a unique combination of a device and browser. 

2. Mechanisms for setting attributes

User attributes can be associated or managed via various means. Listing down the various ways how the attribute values can be added, updated or reset :– 

  • Set Attribute Node can be used to set an attribute value for a user. While setting the value, it even allows selecting from one of the three types as listed below: 

    • Text

    • Number

    • Date

These types, further allow appropriate search options for the attributes in the Users workflow. 



  • Send Message with Options Node can be set up to store the option selected as an attribute value for the user. To be able to do that – specify the attribute against which you want selected value to be saved in.

  • Request User Data Node can be used to request information from the user and store it as an attribute.

  • JSON API Node  - The response fields from an API call can be fetched and stored as an attribute which can be utilized later. This can be a really helpful way to load more contextual and relevant information about a user or an activity via an API call.

    To store a response from an API as an attribute:

  1. Click on the key from the response whose value you want to use in the flow

  2. The attribute is created right below the response box

  3. You can change the name of these attributes as per your desire

Note:  This is only available for the customers on the professional plan & higher

  • Script Node – The output of a script node execution can also be returned to add or update a user attribute value. 

You can set up an attribute by using the attributes field which takes in an array of attribute objects. Each attribute object is a very simple object with name and value fields. This field can be used in conjunction with the other sections as well.

process({“data”: { },”attributes”: [{“name”: “dob”,”value”: “03/06/1988”}]});

Note:  The script node is only available in the Business plan and higher

  • During website bot initialization – For both the widget mode and the standalone mode, attributes can be set up for a user to initialize the bot.

    This can be helpful for cases where contextual information is available for the user during the chat initiation. 

  • Standalone Mode: While launching the bot using the direct URL, you can specify a Path/flow to be launched as well as specify the values for a set of attributes. 


  • These have to be added to the bot’s direct URL 


  • Website Widget: You can add an additional parameter for user_attributes as is highlighted in an example of the initialization script below: 

    !function(e,t,a){varc=e.head||e.getElementsByTagName(“head”)              [0],n=e.createElement(“script”);n.async=!0,n.defer=!0,n.type=”text/javascript”,n.src=t+”/static/js/chat_widget.js?config=”+JSON.stringify(a),c.appendChild(n)}(document,”https://app.ORAI.com”,{bot_key:”7b61ede44c1c4928″,welcome_msg:true,branding_key:”default”,“user_attributes”:[{“name”:”user_id”,”value”:”340490123″}, {“name”: “user_email”, “value”: “test@ORAI.com”}]});


  • Identity Node: – The identity node can also be used as a simple form to collect data from the user and persist them as attributes.

  • Other means for example Google Calendar node utilizes attributes to store the date and time values selected for the appointment/event.

3. System-defined attributes
Outside of the explicitly set up user attributes, there are some system defined attributes which are provided based on the details available in the system about the user.


These are namely – 

  • user.user_id The unique identifier of a user in the ORAI system.

  • First Name – User first name, detects from channel (Facebook).

  • Last Name – User last name, detects from channel (Facebook).

  • user.channel_user_id The identifier provided by a particular channel where the user is interacting from.

  • user.channel The channel from where the particular user is interacting.

  • user.last_query The latest text input by the user.

  • user.username – The username of the user as provided by the channel. Not applicable for all the supported channels. Would be blank where the channel does not provide the data.

  • user.fileUpload.url – URL of uploaded file.

  • user.fileUpload.type – Uploaded file type.

4. Viewing Attribute Values

All the attributes which are associated with a user are displayed in the User Details section. Here is an example of the same – 

5. Using Attribute Values

All user attributes including the system provided ones can be accessed in the relevant nodes by using the double curly braces notation {{attribute}}.


For Example – To access the value stored in email_address attribute, use {{email_address}} in the node.

An autocomplete list will start showing up to ease the access to the user attributes. The double curly braces notation is to be only used while accessing the variables. While defining them there is no need to specify braces.

6. Standard Attribute Length

The attributes are limited in size by design. The constraint is due to performance factors.

Here are the standard limits:

1. Up to 25K characters for in flow usage
2. Up to 1000 characters for also persisting this information in DB for reporting and segmentation.

Note : For double byte characters, these limits may be halved.

In order to deal with larger data, it is a standard practice for any development to split the data or use paginated responses.


1. Introduction

User Attributes are data points associated with a user or relevant for the conversation. These attributes are persistent in nature unless they are cleared or overridden explicitly.

User attributes can also be used as variables for storing data related to a path execution.


For example – email or username of a chatbot user, items ordered, quantity and delivery address for a pizza ordering bot and so on.




1. Introduction to Hosting Flexibility

At ORAI, we understand the value of flexibility for your business. We understand that every organization wants choice and has unique needs and requirements in terms of performance, security, and scalability – and meeting them all can be a tricky task.

Cloud solutions have certainly grown in popularity and come with advantages ranging from time & money savings to more flexibility, agility & scalability. On the other hand, on-premise software that has been around for a long time has certainly proven to provide security and control to enterprises.

So, we offer open and flexible deployment options that can be custom-tailored to suit your requirements. This approach & philosophy has allowed us to build a unique platform that supports cloud, on-premise and hybrid deployment options.

1.1. Terms & Definitions

  1. Cloud Solution: A subscription-based licensing of software that is centrally hosted on a public cloud infrastructure.

  2. On-Premise Solution: On-premises software (or “on-prem”) is installed and runs on computers on the premises of the person or organization using the software.

  3. Hybrid Solution: Hybrid solution is a deployment solution that involves a mix of both Cloud software as well as on-prem solutions.

  4. Socket IO: Used in Cloud-2-Enterprise solution to enable real time, bi-directional communication between the C2E Bridge deployed on on-premise and the ORAI Cloud.

2. Deployment Options

2.1. Cloud

ORAI offers a best in class multi-tenant cloud solution. You can get started with our cloud offering and get up and running in no time. No time is lost in setup and deployment aspects. Some of the advantages of going for the cloud solution will be as below: 

  • Cost Effective: Our predictable, value oriented cloud subscription is designed to make it easy to get you started with minimal upfront & reasonable regular investment. 

  • Secure: ORAI Cloud is hosted on best in class cloud infrastructure from leading cloud vendors with utmost focus on security. And our own strict security measures add to the overall security of the platform. All data transmission is encrypted and access to customer’s data has strict controls. 

  • Scale: The multi-tenant cloud platform is designed to scale for millions of interactions. Makes it easy for you to manage the increasing interactions without so much as needing to change anything other than automatically subscribing to the right plans.

  • Data Control: ORAI makes it very easy to manage data or train your chatbot on our cloud and at the same time gives you complete control over your data. We are GDPR compliant and customers can request for information about their data as well as removal of the same from our servers. 


2.2. On Premise & Private Cloud

If you require more control over your data, stricter compliance requirements or there is a need for integration with on-premise systems, we have that covered as well with our on-premise offering. The entire platform can be set up on your infrastructure with no dependencies since our proprietary NLP engine which powers the conversations is also packaged along with it. 

Also, the platform can be deployed in a private cloud set up. All the standard PaaS providers are supported – AWS, Azure, GCP, etc.

Key advantages include: 

  • Control: ORAI’s on-premise or private cloud deployment gives you the same capabilities as our cloud but with complete control over your deployment and data collected within it .

  • Utilization: For our customers that have on-premise and / or private cloud capacity, on-premise deployment is an excellent means of utilization of available resources.

  • Privacy & Compliance: With all data contained within own servers, privacy & compliance is significantly easier to achieve.

  • Internal / Intranet Deployment: With its own proprietary NLP engine, ORAI can be deployed on your intranet and not need internet access for any services. 


2.3. Hybrid Deployment

If you are looking for the best of both worlds, we have hybrid options as well. Our C2E offering provides a deployable set up which can integrate with on-premise systems and services and relay it back to the cloud where the rest of the conversation resolution and management happens.

Including some details below on how it works:

  • You register for an account on our Cloud.

  • Deploy our proprietary Cloud-2-Enterprise (C2E) Bridge utility on premise. Installation is done in a secure manner with a secure token based authentication between the C2E Bridge and ORAI Cloud.

  • Build & deploy modules on the C2E Bridge to get access to data on your internal apps.

  • Our proprietary use of Socket IO technology, further allows ORAI Cloud to then communicate with the on Premise C2E Bridge without needing direct access from Cloud to the C2E Bridge.

All the above then bring in significant advantages to ORAI’s Hybrid model including :– 

  • Best of both worlds, Cost Effectiveness of the ORAI Cloud and retained control over internal Data.

  • Cost Effective: Our predictable, value oriented cloud subscription is designed to make it easy to get you started with minimal upfront & reasonable regular investment. Hybrid allows you to continue using the cost effective cloud model.

  • Control: Nothing better than retaining full control over internal data and Hybrid allows you to continue doing that even as you use the power of Cloud in so far as the heavy lifting of conversational modeling for Chatbots is concerned.


ORAI Cloud is easily available for self-registration and trial from our website at www.orai-robotics.com.

On Premise, Private Cloud, and the Cloud-2-Enterprise Bridge are all available upon request. Contact us at connect@orai-robotics.com.


1. Introduction


Each attribute has its own identity and stores values that have been mapped to them, the release of an option to copy and create new attributes during a copy function enables you to manage your attributes.

2. Functioning

Once you copy a path that has any node containing attributes such as Request User Data node, Set User attributes node, Identity node, Send Message with Options node with an attribute then a modal will be shown as below  :

The copied node is referring to an attribute ‘name’ – This will display the current attribute for which the changes are going to be made. 

The following are the options that can be selected: 

2.1 Create a Copy 

When this option is selected, the attribute created in the copied path will have a new identity and will not be mapped to the original one, the name of the attribute create would have ‘_copy’ added as an appendix for easy identification. 

For Example:

If the original attribute was {{name}}, and Create a Copy is selected, the new attribute will be {{name_copy}} 


2.2 Link with Original 

When the option has been enabled then both the attributes the original and the copied one will have the same identity and any changes in either of them will be reflected in the other one too.

2.3 Select this to perform the same action for other attributes

This option simplifies the work if you have multiple attributes present in your path, you can select either of the options and the changes will be applied to all the attributes.  


Feel free to reach out to connect@orai-robotics.com in case of any issues.


ORAI for Facebook

ORAI for Instagram

ORAI for WhatsApp

ORAI for Website

ORAI for Google Assistant

ORAI for Alexa

Contact Us

+91 8660 16 13 19

  • Facebook
  • Twitter
  • LinkedIn - Grey Circle
  • Instagram - Grey Circle
  • YouTube

© 2019 -20 ORAI-ROBOTICS