Skip to main content
Skip table of contents

OCP® Overview

What is OCP®?

OCP®, or Omilia Cloud Platform®, is an innovative, no-code, enterprise-scale Conversational AI platform crafted for customer service automation. It operates efficiently across both voice and text channels and provides meticulously tuned, industry-specific models right out of the box. In addition, it offers seamless integration with several leading CCaaS platforms, such as Genesys Cloud, NICE CXone, Talkdesk, and RingCentral. With OCP, deploying a new bot can be accomplished in mere minutes, simplifying the process and saving time.

Moving from command-line interfaces (CLI) and graphical user interfaces (GUI) to conversational user interfaces (CUI) has been a significant leap in the world of technology. With the rise of CUIs, user interaction with machines has become much more natural and intuitive. However, creating efficient automated solutions requires more than just advanced technology; it demands establishing a level of trust with each client interacting with your automated system.

A Nielsen Norman Group report, "Intelligent Assistants Have Poor Usability," mentions that “observing users struggle with the AI interfaces felt like a return to the dark ages of the 1970s: the need to memorize cryptic commands, oppressive modes, confusing content, inflexible interactions — basically an unpleasant user experience.” Our goal at Omilia is to ensure that interactions with machines should be as seamless and engaging as human-to-human conversations.

Creating trust with your callers necessitates incorporating best practices rooted in years of industry experience. Trust is indeed the cornerstone of all conversations, even those involving machines. This is where the OCP® truly shines, aiding you in the creation of efficient and enjoyable conversational user interfaces. Omnichannel interactions can be designed with minimal or no training, eliminating the need for specialized expertise in Speech Recognition or Natural Language Processing. With OCP®, the development of robust conversational interfaces can be achieved by anyone, making it easier than ever to cultivate productive, engaging, and trustful interactions with your clients.

OCP® Tools

OCP® offers a range of visual instruments for the development of a Conversational AI system customized to your requirements. For ease of understanding, a short explanation of each OCP® tool is provided below.

OCP Console®

OCP Console® is a unified entry point for managing all OCP® services. It has an easy and intuitive interface and is designed for both advanced and novice users. Go to OCP Console® User Guide for more information.

OCP miniApps®

OCP miniApps® are the essential elements of your OCP®-based Conversational AI solution. The miniApps are designed to be user-friendly, requiring no coding knowledge, no maintenance, adaptable to your needs, and ready for instant deployment. They are natural language dialog units that manage one specific task, for example: asking for an address or credit card details, comprehending a call recipient's purpose, delivering information from a flexible knowledge base, or even arranging a meeting. More information on OCP miniApps® can be found here.

OCP Conversational Natural Language®

OCP Conversational Natural Language® OCP Conversational Natural Language® is a highly intuitive and user-friendly tool designed to construct, test, and launch Machine Learning-driven NLU models. These NLU models are vital for scrutinizing text and extracting significant entities, entity features, intents, and other key syntactic elements. We invite you to visit the OCP Conversational Natural Language® User Guide for a more detailed explanation and additional information.

OCP Orchestrator®

OCP Orchestrator® is the main development tool of OCP®. It allows combining the existing miniApps created in OCP miniApps® web application to build and run a complete Dialog Application. The Dialog Application can be further connected to a phone number or a chatbot to maintain a conversation. Go to the Orchestrator User GuideOrchestrator User Guidefor more information.

OCP® Voice Biometrics

OCP® Voice Biometrics is a feature for authenticating a caller's identity by comparing their active voice to stored voiceprints during calls. Voice Biometrics offers enrolment services, assigning identifiers to stored voice records for seamless, secure identification. Users can also opt-out if desired. Notably, Voice Biometrics includes speaker verification and identification systems, with verification comparing voiceprints from the same speaker for confirmation, and identification precisely discerning the speaker from a group. We encourage you to check out the OCP® Voice Biometrics User Guide for a comprehensive understanding and more details.

OCP Insights®

OCP Insights® is a comprehensive tool used for monitoring and analyzing calls, providing significant statistics about Orchestrator applications such as dialogues, flows, and miniApp invocations stemming from calls or web chats. It is segmented into three components:

  • OCP® Monitor is the heart of the system, providing an in-depth exploration of conversations within an OCP application. Essentially, it offers a clear and detailed view in the interaction between the system and the user. For more information, refer to the OCP® Monitor User Guide.

  • OCP® Reporting is an extensive reporting and analytics system providing graphical dashboards illustrating key performance metrics. Its purpose is to highlight opportunities for continuous improvement of the Virtual Assistant and offer profound insights into customer conversations. The generation of these reports is entirely system-driven and doesn't require human analysis. For more information, refer to the OCP® Reporting User Guide.

  • Export Service grants users access to their raw application data and provides an essential and unfiltered foundation for data analysis. For more information, refer to the Export Service User Guide.

OCP® Testing Studio

OCP Testing Studio® is an automated testing framework designed for Omilia's conversational applications. It supports test-driven development and various levels of functional testing, enabling evaluation of conversational scenarios. Suitable for both seasoned developers and non-technical users, it provides an intuitive, web-based platform to run pre-existing tests without download or installation. It also offers visual analysis of test data, showing trends in test results for insightful review.

For more information, refer to the Testing Studio User Guide.

Why use OCP®?

With OCP®, the process of developing and maintaining advanced, speech-enabled conversational voice interfaces is significantly simplified. There is no requirement for mastering intricate tools and algorithms or undergoing extensive training. You can effortlessly create top-tier conversational speech automation that greatly enhances customer experience and satisfaction. The reduced complexity makes it far easier to amend application flows with OCP®, especially when compared to traditional systems. Additionally, these advanced conversational virtual assistants can be launched much quicker than other solutions, thanks to the pre-packaged natural language dialog components of our OCP miniApps®. All you need to do is incorporate them into a CCaaS flow and set up accordingly.

Typical CCaaS Flow without OCP miniApps®

In a standard IVR system without the aid of OCP miniApps®, callers are often overwhelmed by a multitude of options to choose from. What counts as a user-friendly number of choices? Can we retain user friendliness with more than ten options? Regardless of your views on the optimization of these options, it's common knowledge that such interfaces are often subjects of user frustration. This becomes even more noticeable when the system requires users to enter specific information, such as ZIP codes or dates of birth. For instance, what if the ZIP code follows the Canadian format, like J4W1S6? How should the date of birth be formatted - is it MMDDYYYY or YYYYMMDD? Have you encountered these systems which require lengthy instructions just to enter letters or data properly? Consequently, it's unsurprising that users commonly choose to either get transferred to a live operator or abandon the call due to sheer frustration.

Enhanced CCaaS Flow with OCP miniApps®

In an IVR workflow that is augmented with OCP® services, callers can seamlessly convey their purpose for the call. For example, they might say, "I lost my card," and then provide the necessary numerical or alphanumeric information, such as a postal code or birth date, by using natural language. The system can understand this language with accuracy comparable to, or sometimes even better than, a human listener.

Requesting a caller’s postal code in a CCaaS flow, without the aid of OCP miniApps®, presents a complex task:

Yet, this task is easily transitioned to a sophisticated natural language interface facilitated by OCP miniApps®, which simplifies the flow considerably:

So, why opt for complex systems that are challenging to use for accomplishing simple tasks, when OCP® can offer a user-friendly system that effectively handles these tasks for you? Just remember this - OCP miniApps® are stand-alone, customizable natural language dialog components. They're designed to manage single tasks and pre-programmed to deliver precise, human-like interaction during a natural question-and-answer process. OCP miniApps® can be effortlessly tailored to your business rules without necessitating any coding, and they offer immediate deployment, eliminating the need for any maintenance.

What are OCP miniApps®?

OCP miniApps® are built to enable anyone to benefit from Omilia’s 10+ years of experience in deploying voice automation solutions. Each of the OCP miniApps® is designed to be a complete solution and encapsulates the translation of complex behaviors and processes into a conversational format. All the tools are aligned to solve a single problem with maximum accuracy and simplicity of execution.

With a few minutes of configuration work, not coding, you can create a conversational interface that captures intent or needed data from a client (let’s say, an address), converting naturally spoken words to text (including understanding all the various accents and ways people pronounce words, not to mention voice mannerisms such as saying “ummm” or maybe even coughing or clearing their throat) using disambiguation and error handling best practices with state of the art speech recognition accuracy and security. This is a mouthful but the bottom line is you spend a couple of minutes configuring OCP miniApps®, link to your Orchestrator flow application, and your problem is solved. Using a simple wizard, and no training, anyone can use OCP miniApps® to apply all the following capabilities to a problem:

  • Capture the caller’s naturally spoken words, and convert them to text

    The era of trying to figure out every possible way a caller could say something is over. We’ve learned over the years that the secret to good automation is to ask better questions of your callers. The use of OCP miniApps® naturally follows a strategy proven to work across years of automation best practices – ​asking a specific question while accepting an unstructured response. Being ready, in essence, for any response to that question.

    If you ask a caller to say their date of birth, you need to be prepared for “January first nineteen-hundred”, “one one one nine oh oh”, “January … uhhh…. one… I guess… nineteen aught… yeah that’s right… I think…​”…​ It’s not the caller’s job to figure out how to say their birthdate your way, it’s your job to understand the caller’s speech as any human would.

    Trust is built, and understanding enabled, by asking the right questions in the right order and learning to understand any response that comes back within the context of the question.

  • Context-based tuning for maximum accuracy

    Another outcome of Omilia’s experience is that aligning every element of the technology (speech recognition, language understanding, machine learning) to the context of the question enhances the accuracy of the results that meet or exceed human understanding.

    If I know I’m expecting a ZIP code, I can disregard any results that are not tied to ZIP codes. The natural structure of OCP miniApps® (built to capture a specific element in a specific way) enables the capture to be tuned for optimal accuracy and results.

  • Redaction of caller information via masking or AES-256 Encryption

    Another benefit of the natural structure of OCP miniApps® (built to capture a single data element, wrapped into a specific context) means that it’s easy for customers to control what data is masked or encrypted in OCP miniApps®.

    • Are you asking for Information that only the caller should know (for example, PIN number)?
      Then select “irreversible masking” in the OCP miniApps® User Interface. The data captured by the invocation of OCP miniApps® will be permanently masked and forever inaccessible to anyone.

    • Are you asking for information that is considered PII, PCI (credit card number)?
      Use AES-256 encryption. Only admins from your organization will be able to decrypt the information. Since each invocation of OCP miniApps® is separate from other OCP miniApps® invocations, you can carefully classify each element of data that the Omilia system captures for you.

  • Disambiguation and Incomplete responses

    If you ask a caller “How may I help you”, and they say “300”, you know you need to clarify that response. Maybe you didn’t hear them quite right. It might be good to say “do you want me to transfer you to extension 300?”.

    But if you ask a caller “How much money do you want to transfer”, and they say “300”, there is no need to ask additional clarifying questions – except, perhaps, to confirm whether it is “dollars” and not “euros”.
    Also if the caller says “I need some information in regards to my card”, the request is not complete and the miniApp can ask “What information do you need about your card” to make the request more specific.

    Humans ask clarifying questions all the time, “I’m not quite sure I heard you…”, “Did you mean __, or was it something else?”. This is a key element of building trust, which is a key element for getting callers to use an automated system.

    Think about trying to do all of this in your standard IVR flow editor. How many hours do you think you would need to spend trying to figure out how to implement this level of logic? OCP miniApps® use simple wizards and drag/drop menus to configure this. Read more about ambiguous intents.


    Intent Disambiguations

  • Validation
    You can choose the way the data provided by the caller is validated against the preset rules. You can add multiple validations and prioritize them accordingly.



  • Confirmation
    How confident are we in the result? Should we ask the caller to confirm? Maybe we should only ask if we’re less than 90% confident we got the answer? Maybe 80%? Control how you manage your confirmations.
    People do not always repeat back the answers to their questions… If your callers have to confirm literally every response, it can be frustrating. “You said __, right?” It takes time, and it’s something a human doesn’t always do.
    Being able to configure when you ask for confirmation, and when you don’t, is a very big element of building trust. Plus, think about trying to deal with this in the IVR.



    Think about all the additional programming work involved with trying to analyze when and how to confirm and validate. OCP miniApps® use a simple wizard that you can deploy in seconds.

  • Allow a caller to “pause capture” for a moment, if needed
    Did you just ask your caller something they didn’t expect? Do you ask “what is your member ID?”, but maybe they didn’t have it ready or memorized? If they were talking to a human they could say “uhhh… wait a moment… oh man… I never have this at hand….” They can ask for time because the human understands.
    Automation solutions can do this too. “If you need a moment to find your member ID, just say ‘wait’. Otherwise, if you have your member ID, please say it now.” Being able to request a “pause” or “more time” is a natural part of any OCP miniApps®.
    As with all OCP miniApps® features, you are just a few mouse clicks away from best practices that took years to develop.
    You can read more about hold functionality.


    Hold functionality

  • Retry and Error Handling properties
    What do we do if we don’t get a useful response the first time? How many times do we retry? You decide! Is no response considered an error? You decide! On maximum errors, do you want to transfer or hang up? You decide! How about custom messages per error case? You got it! Want to have different thresholds for continuous and global errors? You got it!
    IVRs have quite a lot of complexity around error handling and retry logic. OCP miniApps® eliminates the complexity and lets you configure the behavior with a few clicks, but offers a level of customization that is equivalent to something one could achieve with custom code. Adjust the miniApp behaviour to your liking and decide when and how the call ends depending on the type and number of errors that occurred in the dialog. All the error handling fields have built-in optimized default values, but allow you to fully configure them if needed.



  • Request for Agent Escalation
    Asking for a live agent became the standard reaction to anyone calling a virtual assistant. The reaction developed systematically and as a consequence of poor conversational experiences, remains today as a standard human-to-bot reaction/interaction. OCP miniApps® encapsulate an easily configurable way to mitigate this behavior and keep a caller comfortable with the conversational experience. You can decide if the system will transfer immediately on any agent request or try to continue the conversation to extract more information from the caller. If someone immediately asks for a live advisor you can provide a comprehensive response: “I understand you want to speak to an agent, but the fastest and safest way is for us to continue together. Should we continue together?” or even: “I will get you to an agent. However, to get you to the correct agent, I will first need you to tell me the reason for your call.”
    Not only do you build rapport with the caller by acknowledging the request, but you provide reasons to continue the call without an escalation.


    Agent handling

  • Flexible reactions to enhance the natural feeling of each conversation

    A conversation is never exactly the same. Even if you are performing the same task, a conversation should always flow naturally. That keeps users comfortable and enhances their trust in the interaction. Either by configuring acknowledgment of nice reactions towards the completion of a task or by having a selection of ways to express that you might have misheard or confused something, having a layer of fully customizable interaction features brings a natural feeling to your conversational experience on OCP miniApps®.


Nice Reactions

  • Speak over the IVR (or “Barge-In”)

    You can define if a user should be able to interrupt the prompt playback or not. Either to improve the recurrent customer experience (when someone is calling several times, being able to interrupt the prompt and speed up the conversation is a great help) or to enforce some specific prompts to be heard, with a click of a button you can enable or disable the ability for users to speak over the IVR.

  • Fail over to “touch-tone”

    Similar to the agent escalation, many people will try to interrupt the conversation by simply pressing zero or any other key. In other cases, you might be migrating from a legacy DTMF application and your users are not yet accustomed to the new conversational behavior. The ability to configure playback prompts to guide the user’s behavior is key in such cases. Regardless of the user pressing 0 to reach an advisor or just pressing the keys that previously would lead to the skillset they are looking for, you are now ready to maintain a fluid conversation. No disruption.

Types of OCP miniApps®

A variety of OCP miniApps® currently exist with more to be released in the near future. You can gather more information about each type by simply clicking on the provided links.

OCP miniApps® features

The principle behind the OCP miniApps® concept lies in incorporating a standard set of features. These miniApps are developed with a focus on consistency and ease of setup and maintenance. The aim is to significantly enhance the task completion rate (TCR) within the self-services in which they are integrated.

Delve further into the vast array of features that OCP miniApps® offer.

What is OCP Conversational Natural Language®?

OCP Conversational Natural Language® is ingeniously engineered to facilitate the creation and deployment of robust Natural Language Understanding (NLU) models.

What exactly is an NLU model? This high-tech tool comprehends textual information through intricate analysis, which allows it to efficiently extract varied components such as intents, entities, entity features, and other significant syntactic elements.

With OCP Conversational Natural Language®, experience an easy-to-use, intuitively designed interface that empowers you to curate your own NLU models. These models can be efficaciously employed in your dialogue applications. This compelling tool comes embedded with a suite of vital features for your convenience:

  • Creating NLU models

Effortlessly create an NLU model utilizing Omilia's pre-tuned xPacks. All you need to do is select from an array of readily available domains and utilize the built-in understanding of both intents and entities.

Moreover, the convenient usage of Machine Learning is an added advantage. Allowing you to insert your own intents and entities, it helps magnify your NLU model's comprehension to the preferred scale. It’s crucial to remember that the final output is largely dependent on the depth of understanding you aim to attain as well as the time and effort you're willing to dedicate to the model’s refinement.

As of now, the following domains are available with a pledge of introducing newer domains in the future: Universal, Insurance, Energy, Telecommunication, Car Retail, Banking, and COVID. The Custom domain, however, doesn't come with pre-set understanding. Instead, it empowers you with the ability to fully tailor-make it by inputting your own specific data.

  • Training an NLU model

The training process makes your model adept at understanding your unique data via Machine Learning. Suppose you construct a banking model using Banking deepNLU® xPack. Your model comprehends the packaged intents and entities, eliminating additional training.

However, if you choose to enhance this model with your personal data, it's imperative to instruct your model to comprehend this new information. Likewise, creating a custom domain model with your data requires training.

This training is administered automatically by our advanced system. All you need to do is initiate the process by simply hitting the Train button. Your AI domain model will begin to learn and understand your data, growing smarter with every interaction. No complex coding or technical expertise is needed. It's as simple as clicking a button!

  • Evaluating a model

Evaluating a model provides an in-depth analysis of the performance of the machine learning component within your model. This essentially reveals the level of proficiency your model has attained through training. It's worth noting that, this evaluation process is only feasible for models that have been augmented with bespoke training data.

  • Deploy NLU models

Once your NLU model has been adjusted and optimized, the next step is deploying it. With just few clicks, you can effortlessly integrate the deployed model into your application. This ease of implementation facilitates the smooth usage of your NLU model, ensuring a seamless interaction with your application.

  • Test NLU models

Challenge your deployed model under various conditions and ascertain its efficiency as per your expectations. Feel confident to conduct an exploration trial on it!

Put your deployed model to the test and confirm its functionality matches your expectations. Feel free forward to dive in and explore its capabilities! The testing feature is at your disposal and ready for a trial run. Don't hesitate, go for it!

What is Orchestrator?

What do you do when you have created and prepared the miniApps bots for a real conversation? How do you create and manage that exact conversation with your first caller? Take it up with Orchestrator!

Orchestrator User Guide allows creating a logically completed conversation that represents a dialog between the application and the caller. It combines the existing OCP miniApps® and other building blocks (for example, Flows, Transfer block, Set Field block and so on) in a way that describes the steps and possible paths a conversation can take. Use a simple UI that allows you to drag and drop OCP miniApps® and connect them to create dialog logic!

But first and foremost - let’s talk about the basics.
OCP® features the concept of miniApps. Each miniApp that is created within OCP® is a bot with intelligence and expertise around a specific type of information that is able to share what it knows with other bots using OCP Orchestrator® application. Orchestrator synthesizes a fluid conversational experience by assimilating the expertise of each task-specific bot into a single unified intelligence. This process of assimilation is unique to OCP® and is a revolutionary technology of bot orchestration.

Orchestrator provides various simple and user-friendly features which help to maintain a complete, clear, and coherent conversation between a caller and an application:

  • Authentication via OCP®: The user authentication should be performed with the same tokens used for any other OCP® service.

  • Manage OCP miniApps®: While working on the dialog application, you can create OCP miniApps® directly in Orchestrator with further viewing and editing all the available OCP miniApps® and use them when building the dialogs.

  • Create and edit Flows: It is extremely convenient that you can split parts of dialog logic into reusable components called Flows.

  • Conditional dialog flow: You can add and configure Condition building blocks so that they can control and guide the conversation based on the values of available information.

  • Event Handling:Orchestrator provides the following functions of Event Handling:

    • Error function (allows channeling a conversation to a preconfigured Flow that will be played once the predefined error happens)

    • Repeat function (provides the ability to repeat or start over the conversation by identifying specific phrases that indicate the caller wants to start over or go back).

  • Transfer a conversation: It is possible to create Flows that allow the deferral of the conversation to a real agent, a chatbot, or any other conversational system.

  • Automatic dialog deployment: When a dialog is ready for testing/production, you can deploy it with the click of a button.

  • Collect Flow’s statistics with Custom Logging: Gather different types of information or Flow’s status by configuring Custom Logging building block and pass this data to Analytics for statistical purposes.

  • Voice Biometrics in Orchestrator: Use Voice Biometrics as a mean to optimize actions within a conversation by setting a process of voice identification and storing your voiceprints for further use.

  • Managing deployed dialogs: You are able to view a simple dashboard-like page where it is possible to manage Dialog Applications and Flows.

  • Simulator: Orchestrator allows creating a chat with your Dialog Applications and Flows through an integrated web-chat simulator in real-time without leaving the application.

How to use OCP miniApps® within Orchestrator?

Let’s assume you want to ask a customer to provide you with his card number. Just follow the simple steps below to see how Orchestrator works.

1. Create and configure a welcoming miniApp that contains a “How can I help you?” prompt. Don’t forget to save your changes when finished.

2. Switch to the Orchestrator by clicking the button on the left, so you will be navigated to the Orchestrator board with the prepared miniApp in the list.

3. Drag and drop the miniApp you’ve created onto the canvas - this is a working area where you orchestrate the bots and other building blocks in order to build a complete conversation.

4. Even with only one miniApp bot placed on the canvas you can already try Orchestrator because you have a fully functional conversational AI bot that is able to pass and receive information from a customer. Click the Deploy button on the right, and then hit the Chat button on the lower right. You can easily notice in the dialog window that the conversation has begun!

5. The conversation is on, but how do you really ask for the card number? Just create and configure another miniApp bot that asks for the card number, and connect it with the first miniApp, so it represents a logical conversation.

6. Try to run the dialog by clicking the Chat button.

The miniApp bot asks the exact same thing you’ve configured it to ask!

In the same way, we can continue adding logically structured miniApps and conditions to drive a natural conversation that will allow the caller to get the desirable outcome from the call.

Besides miniApps, there are several other blocks used in Orchestrator that will help build more complex logic to include conditions, transfers, re-ask intents, and more as described in Orchestrator User Guide.

What does OCP Insights® offer?

OCP Insights® is a comprehensive tool used for monitoring and analyzing calls, providing significant statistics about Orchestrator applications such as dialogues, flows, and miniApp invocations stemming from calls or web chats. It is segmented into three components:

  • OCP® Monitor is the heart of the system, providing an in-depth exploration of conversations within an OCP application. Essentially, it offers a clear and detailed view in the interaction between the system and the user. For more information, refer to the OCP® Monitor User Guide.

  • OCP® Reporting is an extensive reporting and analytics system providing graphical dashboards illustrating key performance metrics. Its purpose is to highlight opportunities for continuous improvement of the Virtual Assistant and offer profound insights into customer conversations. The generation of these reports is entirely system-driven and doesn't require human analysis. For more information, refer to the OCP® Reporting User Guide.

  • Export Service grants users access to their raw application data and provides an essential and unfiltered foundation for data analysis. For more information, refer to the Export Service User Guide.

OCP® Monitor

The OCP® Monitor is a comprehensive tool designed for tracking system-user interactions. With this tool, users can dive into conversational details within an OCP® application, examining Orchestrator application dialogues, Flow interactions, and miniApp invocations originating from calls or web chats.

  • Search filter
    OCP® Monitor comes with a powerful search filter that lets users refine dialog search using filters like dialog ID, session ID, and connection ID. Live monitoring of ongoing sessions is also a feature via the Show Live toggle. Additionally, the Advanced Search provides more granular control over queries.

  • Dialog Review
    The search results, displayed in a dialog list, offer vital dialog specifics. A click on a dialog opens up the Dialog Review that provides in-depth details about the selected dialog.

  • Application Layer
    Application Layer can be enabled to give a high-level perspective of each dialog in OCP® without subcomponent details. The Application Layer also allows application dialog structures to remain visible during dialog list searches with applied filters.

  • Path View
    Path View is a feature in OCP® Monitor that visually displays the sequence of dialog steps in a session. It provides a structured, hierarchical view of interactions, and users can expand/collapse branches and click items for detailed information. This tool offers a clear and concise way of analyzing session components.

  • Monitoring Voice Biometrics
    Monitoring of Voice Biometrics offers the users tools for assessing caller identification. Users can evaluate results of voice database searches, verification labels, and comparisons of voiceprint similarity. This aids in validating voice identification.

To access more comprehensive details, refer to the OCP® Monitor User Guide.

OCP® Reporting

OCP Reporting® is a comprehensive analytics and reporting platform which delivers real-time and conversational insights into customer interactions. It provides graphs and tables of key performance metrics, offering opportunities for continual improvements and deeper understanding of customer needs. Additionally, the Reporting tool also allows for customizable and detailed search filters for specific applications or miniApps.

The tool is divided into two components:

  • Real-time Data
    Real-time Data gives instantaneous updates on the current situation of miniApps, including Sessions, Dialogs, miniApp Invocations, miniApp Events, End Type Reports and miniApp Success Rate. This data can be filtered and downloaded for further analysis.

  • Conversational Insights
    Conversational Insights offers a more analytical approach, providing historical performance metrics presented in a number of interactive dashboards, including Total Sessions, Avg Invocations, Conversational Outcome, miniApps Invocations and miniApps Results.

Export Service

Export Service allows OCP users to access their raw application data securely in compliance with GDPR requirements. With special privileges, users can create new exports or download data.

The main features of Export Service include:

  • Archive that provides a summary of export requests per OCP group,

  • Subscriptions that allow users to receive real-time data streams, and the ability to create new export requests.

The data is available for download for only 24 hours after the export request is successfully completed. If the data is not available for export, users will receive a notification.

To ensure the highest security standards, access to these features is controlled and requires special access permissions from the Customer Support team.

To explore more details, refer to the OCP® Export Service User Guide.

OCP® Integration

OCP® is fully pre-integrated with the key CCaaS providers, and accessible via their respective marketplaces, such as Nice CXone, Genesys Cloud, Amazon Connect, and Lifesize CXengage.

Moreover, we offer a range of direct integrations:

  • IVR providers: Such as Avaya, Cisco, and Genesys Engage

  • Mobile App integration: Executable through our iOS and Android SDKs

  • Messaging Platforms: These include Messenger, Skype, Slack, Telegram, Viber, WhatsApp, ZenDesk

  • Smart Speakers: Featuring Amazon Alexa and Google Home

  • Live Chat integration: Such as Genesys Chat Bot Gateway, LivePerson, Freshdesk, Talkdesk, NICE CXOne, Zendesk

The scalability and adaptability of OCP® enable us at Omilia to swiftly deploy OCP miniApps® with minimal modifications to your existing Contact Center and/or Telephony platform. All you need to do is integrate your CCaaS application with OCP® as outlined in the Integration guides and transfer the call from your call center to OCP®. In doing so, OCP® will manage the dialogue and transfer it back to your call center, along with valuable data that can be used for analytics. This data includes:

  • The user’s intent

  • The number of times the user requested an agent

  • Whether the user was authenticated

  • The reason for the call transfer

  • The user’s date of birth, and more.

Simply drag and drop the miniApps® to your workflow, insert the miniApps® ID you wish to use, the pseudo number to connect to Omilia, and provide the host URL for your OCP® miniApps. This streamlined process ensures integration is seamless and efficient.

NICE CXone Integration

OCP® by Omilia can be seamlessly integrated into NICE CXone, offering advanced capabilities like voice recognition and conversational AI, within a familiar system. This efficient blend of two high-end products enables vastly improved customer communication. The end result of this integration is an improved customer experience and efficient handling of customer care tasks.

For more intricate details on the integration process and its benefits, refer to our detailed NICE CXone Integration webpage.

Genesys Integration

OCP® offers seamless integration with Genesys, providing a configurable and easily deployable miniApps® that can dynamically handle various parts of conversational applications. This blend enables Genesys systems to have natural language processing capabilities, guided with the artificial intelligence provided by OCP®.

The benefits of this integration include enhanced customer experience through AI-driven dialogue, quicker processing times, and the ability to handle more complex customer inquiries. By integrating the OCP® miniApps into a Genesys-based system, businesses can push the boundaries of their customer service capabilities, exploiting the potential of artificial intelligence in their dialogue workflows.

For additional and comprehensive information, please proceed to our Genesys Integration section.

WebChat Integration

WebChat can be easily integrated into your website by pasting an automatically created JavaScript code to your website’s HTML code. WebChat interface is fully customizable to match your brand and visual identity. It can adapt to both design and functionality preferences to suit your website’s look, feel, and user experience.

WebChat offers a number of useful features, such as automatic chat bubble expansion, a typing indicator, an option to resend messages, a view of the entire conversation, configurable timeout messages, an exit chat button, the option to play audio, and even capture users' clicks outside of the chat area.

The live chat feature allows the user to communicate in real time. If an agent is offline, the system continues with the virtual assistant. It also allows the chatbot to pass on complex queries or needs to a human agent for further assistance. The live chat feature can be integrated with different live chat platforms.

Integration to other chat platforms works through a series of APIs with such platforms as Facebook, Viber, and WhatsApp as well as telephony channels and web chat. This cross-channel capability enables you to offer your customers a seamless user interaction experience.

For more information, go to WebChat Integration Guide and Chat Tab configuration in miniApps.

Talkdesk Integration

Talkdesk integration with OCP® offers a unique, blended environment for managing customer interactions across chat and voice channels. This integration combines Omilia's Natural Language Understanding and Machine Learning technologies with Talkdesk's cloud contact center solution, offering a more personalized and engaging customer experience.

For chat integration, OCP® uses Omilia's miniApps architecture, where each miniApp is designed to handle a specific task in the user's conversational flow. OCP® chat platform can send and receive messages from Talkdesk, allowing seamless bi-directional communication.

Similarly, in voice integration, OCP® utilizes its Dialog Manager for session control and the routing of customer calls. This setup ensures a smooth transition between actual human customer service agents and automated or digital agents, based on preset rules.

Overall, the integration of Talkdesk with OCP® enables an AI-powered, effortless, and personalized experience for Talkdesk's users to handle customer interactions more effectively and efficiently.

Custom Integration

Interested in custom integration with an IVR provider? At Omilia, we make that possible. For detailed information, we kindly request you to connect with your assigned sales representative. Our Omilia sales team stands prepared to assist with insights into the practicality of custom integrations with your chosen IVR provider.

JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.