My main use case for Kore.ai is customer support automation, where I have been using it to fetch customer details and to add or update customer details. For example, I receive a call from a customer requesting his current details that are present in the system, and if the customer provides his phone number, I can retrieve that information efficiently. Using Kore.ai, I initiate the task through the chatbot, and then based on the response, I can proceed with the needed actions.

The best feature Kore.ai offers, in my experience, is the AI assistant, which allows me to query user details in any way so that it gets fed into the system effectively. The AI feature in Kore.ai stands out for me because it is particularly useful in a specific chatbot context; for simpler cases, querying and getting details is fine, but for complex tasks where a user feeds data into the system in any format, AI is very helpful in retrieving and inputting those details. Compared to other tools, Kore.ai provides a well-organized chatbot experience that others do not offer.

If Kore.ai can implement UI automations and similar features, it will be very helpful. I rated Kore.ai eight out of ten because of the potential for these additional improvements.

In my current field, I have been working for around seven years.

My advice to others looking into using Kore.ai is that if you are looking for chatbot solutions that are easily configurable by drag and drop and you are ready with your business scenario, then you can easily use Kore.ai to configure your chatbot effortlessly. I rate this product an 8 out of 10.

The main use case for Kore.ai was building a chatbot for one of our insurance clients who required a chatbot to allow agents to directly ask about documents uploaded for verification. The chatbot checks if documents exist at a particular link that contains the personal documents of clients and then sends the status back to users or agents. If the document is present, agents may request to read it and check if certain conditions are fulfilled in the document. This is essentially a document validation agent created using Kore.ai as the front end, coupled with Teams channels for the agents.

Kore.ai helped our team specifically in building the document validation chatbot by serving as the front end of the entire development. Using Kore.ai, we connected with the Teams channel and leveraged features such as API connections and API calls to easily retrieve the status of documents.

The best features Kore.ai offers include a very user-friendly interface, making it easy for agents who are not comfortable with technology to navigate it. This is the main aspect I would highlight.

The user interface of Kore.ai is so user-friendly because it is a no-code platform that provides drag-and-drop tools for building chatbots or agents without needing to write code. Kore.ai also offers excellent connectors with different services, and in our case, we built a microservice that was called directly from Kore.ai through API calls. Additionally, it offers popular application integrations such as SAP, ServiceNow, and Salesforce. These features have significantly improved the customer experience and made it scalable enough to manage millions of interactions, which suits large enterprises.

Kore.ai has positively impacted our organization by reducing error rates from around fifteen to twenty percent to just two to three percent after implementation. This significant reduction in errors means that fraud detection is not negatively impacted. It has also helped reduce the time agents spend on document validation, thereby increasing efficiency and accuracy. These are the main two metrics that have contributed to our success.

In terms of time saved, the accuracy has dramatically increased, with error rates decreasing from fifteen to twenty percent down to two to three percent. We have saved almost two hours of daily work per agent. With more than twenty agents working on this document validation task, we are saving a total of around forty hours per day.

To improve Kore.ai, I suggest focusing on more agentic automation, such as offering MCP kind of features with an orchestration layer for use cases. This would allow us to implement business logic in the orchestration layer. With the ability to build our own MCP servers and plug-and-play with the MCP client, we could have more scalable options for deploying multiple agents on one platform, enabling them to work simultaneously across different use cases.

I have been using Kore.ai for around eight or more months in my previous company, where I worked on a proof of concept for that particular engagement.

Kore.ai is stable.

Kore.ai's scalability is good, and it is indeed scalable.

The customer support for Kore.ai is really good.

Before Kore.ai, we used InteliX, which was one of the vendor products we explored but switched to Kore.ai due to its superior connectors and more affordable licensing compared to InteliX. Additionally, the user experience in Kore.ai is much more user-friendly, unlike the complex user interface of InteliX.

My experience with pricing, setup cost, and licensing has been good. Although I was not directly involved in the pricing discussions, the setup costs and licensing were straightforward, and we received excellent support from the Kore.ai product team. Their training sessions were effective, and we also achieved certifications through mini-projects alongside the training, making the transition and onboarding process quite smooth.

We have seen a return on investment, particularly in full-time equivalent count saved.

We did not evaluate any other options besides InteliX, but we also tried Copilot. Unfortunately, Copilot did not deliver good accuracy during the proof of concept, and its licensing costs were higher than those of Kore.ai, which is why we ultimately chose Kore.ai.

Kore.ai has impressive features, such as effective connectors and a very good user interface. It is a no-code platform where drag-and-drop functionality is sufficient to build logic without needing to write code. It is easy to deploy agents and much more scalable than other tools I have explored so far.

My advice for others considering Kore.ai is that it is really easy to use for beginners. People will quickly learn how to use it and deploy their own use cases. Kore.ai is a good product, and I would rate it an eight out of ten.

We created a chatbot using Kore.ai that integrates the AI services it allows. For the travel insurance system, I created a chatbot where we read insurance policies using our AI system that we integrated into it, or we recommend insurance options. This serves as a user interface where people can type their questions to the chatbot, such as their age, income, or the type of insurance they want, including travel, car, or health insurance. The main focus we explored was reading insurance policies and providing AI suggestions on what users can do with these insurance policies. It simplifies how people read insurance policies by allowing them to upload it to our chatbot, and Kore.ai processes it in such a way that it prompts questions such as "Give me a question that would define how much money you can get from your insurance when you get into an accident or about life insurance." It tells users which part of the document pertains to how much they can receive and other factors. Users can also summarize the document as a whole, including the provider, details, and other specialized features that Kore.ai offers for insurance options.

Kore.ai positively impacted our organization through integration with Power BI for reporting, such as user numbers and automation. We observed how it integrated with our data analyst side, allowing us to automate reports. Kore.ai's main benefit was identifying the chatbot's potential to integrate into our processes and help us land more projects in the future. Although our industry has not extensively adopted it yet, it provided a clear pitch of how it could enhance operations, helping users navigate without relying on outdated documentation, providing summaries, and interactive queries.

Kore.ai was straightforward once we got to know it. Since it was new technology for us at the time, it took some learning because our team of four did not have any experience initially with Kore.ai. We only had experience with Microsoft Copilot chatbot or something similar. The first time we experienced this, it was great because the interface was drag and drop, and we could review the documentation. There was a learning curve, but it took us about a week to get started, and then we proceeded to create systems that read insurance policies using Kore.ai's AI system. By the second week, we were also recommending to our customers how they would approach their existing or non-existing insurance policies. Kore.ai helped us integrate a lot through documentation and trial and error, making it straightforward to integrate overall, resulting in a very good experience for first-timers.

Something that stood out to me was Kore.ai helping us integrate many other applications. The bot builder showed a similar feature with API integrations, proving we are not limited to interacting solely within the application. We can use API calls during development, integrating our API with OpenAI ChatGPT LLM. For example, we utilized a post request to send data to Power BI and sent emails to test the user experience for the chatbot's logs. There is much we can do with API definitions, allowing us to define several APIs that process information for us. I enjoy developing with Kore.ai because it enables integration with many tools.

We did extra investigation on Kore.ai's bot builder. One standout feature includes digital forms, digital views, and the task definition. We created around six tasks, including reading the document itself, which is straightforward. The dialogue tasks can be called from the APIs from the bot's interface. We refined tasks such as recommending travel insurance by diving into them with an intuitive drag and drop interface that provides excellent visibility into the flow. We also tried knowledge AI, which is beneficial for answering user queries although it was not the main focus of our project. We leveraged many features of Kore.ai, including natural language processing, and even though we ended up using an external API, it has good integration potential, especially with generative AI and LLMs facilitating various integrations.

Another feature I found valuable was the deployment channels we used, such as the web client. We integrated it directly into a website, which was significant help. We plugged in the URL and HTML code, managing domain access through whitelisting. It worked exceptionally well, and I was impressed by how easy it was to integrate the chatbot into our services. I have high expectations if we integrate it into platforms such as Telegram or Instagram, and I genuinely enjoyed setting up the web and mobile client.

I see opportunities for improvement, especially regarding integrations. It is positive that there are many channels, including Facebook Messenger and enterprise platforms such as Zoom or Slack, yet I think more could be done in chatbot deployment integrations. I am looking for further advancements between generative AI structures, allowing different LLMs to be utilized, and enhancing the intuitive interface. I believe an interface showing a sub-workflow could be valuable, as cluttered screens may hinder usability in complex industry flows, allowing a dialogue within a dialogue feature.

Regarding documentation, I believe it is sufficient, although there is space to improve the interface's appearance. Kore.ai's bot builder presents a vast white screen with build and deploy options, while the cluttered sidebar can be overwhelming upon expansion. Enhancements in presenting facts and utilizing white space would significantly improve user navigation.

The two points I deduct relate to the integrations, which were not as extensive as I initially expected. However, integrating using API calls in the bot builder is positive, and there is a need for better compatibility with other integrations. For instance, the knowledge base limits the capability if using an external LLM or vector database. While there is a small talk feature, it feels more gimmicky, focusing on predetermined responses rather than providing genuine chatbot interaction.

I have been using Kore.ai for only a few months at our organization. This was a feasibility project in which we were supposed to deploy our product. Our project at that time was a travel insurance system, and we had been developing the system for about half a year. We showed our product for evaluation to stakeholders.

Kore.ai shows impressive uptime, and we have not encountered any downtime during development. All four of us can access the development environment without issues, contributing to an overall great experience.

This is not a robust part of our production systems yet, but during our trials, we operate on the public cloud. We presented our proof of concept to stakeholders to demonstrate its potential. They are now discussing how to transition it to a private setup, but I am not privy to those details.

We have not reached out to customer support since we have not experienced any problems, which indicates good reliability.

Before choosing Kore.ai, we used Microsoft Copilot's chatbot, a virtual agent, among other options such as Azure AI Studio, as we have Microsoft integrations. We wanted to explore Kore.ai due to its intuitive use, clean interface, and great integration potential. After presenting Kore.ai, our higher-ups were pleased and are exploring integration, as we faced few issues with Microsoft's Copilot agents, but their lack of AI-interactive responses did not meet our needs, making Kore.ai a significant upgrade.

Kore.ai's bot builder is hosted on its own self-service SaaS platform. It is not dependent on any public cloud provider; we navigate inside the bot builder and deploy using their software, which handles all user interface matters. To deploy the bot on the web client, we went directly to the Deploy tab, configured our whitelisting for the website, and it functioned perfectly without needing to privatize our infrastructure.

This setup is not currently part of our production, so I can only relay feedback from our higher-ups regarding Kore.ai's potential to replace Microsoft's agents. They are looking into integration possibilities, so while I do not have specific numbers, the general sentiment is positive, suggesting substantial future investment.

My advice for potential Kore.ai users is to thoroughly read the documentation and follow tutorials while exploring the environment. It is an excellent tool for integrating chatbots into systems and has an intuitive interface that is easy to navigate, boasting high potential for usage in larger companies. I would rate this product an eight out of ten.

My main use case for Kore.ai was creating an outbound calling generative AI-powered chatbot, which is useful for insurance and healthcare companies.

Kore.ai is a low-code platform, and you do not necessarily have to be an expert in artificial intelligence or generative AI to use this platform. However, if you have that experience, it will be a valuable add-on. The main advantage is that it has almost every kind of plugin available to use, whether for live agents or if you want to use it as a call center. You have real-time capabilities and the most useful plugins available, with almost every kind of model available with configurations. We can configure the ML models and train them. The platform is very user-friendly with explanatory features and a great UI.

One significant feature is the live testing platform with Kore.ai. When you are creating a workflow, you have an interactive, real-time testing platform that reflects every change you make. This makes it easy to debug errors or add new features. Additionally, Kore.ai has many different tools and platforms that cater to different needs, whether for a call center, normal workflow, or machine learning workflow, which is really useful.

Because of Kore.ai, it was much easier than creating something manually. A low-code platform always helps, and when that platform has this much capability, it provides far more value than manual development. It was particularly helpful for our team that we could create a POC and get that project into production. Kore.ai helped our team build a generative AI outbound calling chatbot, and it truly helped our customers.

If you have a hospital with a thousand employees in a call center, you might consider outsourcing. However, with Kore.ai's outbound calling capabilities, you can eliminate the outsourcing part. You do not need a thousand call center employees. You can accomplish this through automation with just one or two employees if people need to switch to agents. This represented a significant cost reduction.

Kore.ai can be improved by enhancing their documentation, which is currently a bit disorganized. They should include detailed videos or workshops. There are not many videos or community resources available, so adding more would be beneficial.

Integrations with real-time models with Kore.ai would be great. Advanced models like Claude or Anthropic models would be valuable additions.

Regarding the rating of 8 instead of 10, the missing comprehensive documentation, tutorial videos, workshops, and community services are factors that reduced the score. Additionally, the unavailability of real-time advanced models from Anthropic or Grok also contributed to deducting one point.

I have been using Kore.ai for nearly one and a half years.

Kore.ai's scalability is pretty much scalable both vertically and horizontally.

The customer support is top-notch, and they respond promptly. I have been in direct contact with the team, and they typically reply with respect.

We used different solutions, including manual calling.

For my project or workflow, I collaborated directly with the Kore.ai team. It was an intra-team project, and it was really useful that their UI was very well-designed so that you do not necessarily have to go to the documentation to find anything. You can look at the name of the icons and understand what they do. For my workflow, I had to connect this with a live call center system. There were plugins that helped me dial and call real customers. The plugins available were really good and useful.

As I mentioned, if you have a call center for 1,000 people, you can reduce that to two.

My experience with pricing, setup cost, and licensing is comparatively lower than other companies and tools available.

We evaluated other options like Emma and Elsa, as well as other platforms, Python-based automations, and n8n-based automations.

Really refine your use case, gather your requirements, and talk with the team to confirm if that is something possible before proceeding. I rated this solution an 8 out of 10.