AI For Work

I used Kore.ai  to make dashboards, widget creation, and I tagged some columns. I wanted to create dashboards to get all the details for policy, specifically to understand who are the legacy policy users and who are the Guidewire policy users.

The widget in our system was for the policy product. In that product, users were not able to see on a page how many users logged in today, whether a legacy person or Guidewire user logged in, or what changes or modifications they made. I created dashboard widgets so that legacy users and Guidewire users could track the changes they made in their policies.

I used Kore.ai  for this purpose. Before that, I migrated from Kore.ai 10 to 11. I trained the model by adding utterances as training data and achieved almost 97% accuracy. After that, I started working on widget creation.

The best feature I have worked on is widget creation. I went through the entire chatbot workflow to create it, so I have a good understanding of that part. I appreciate the process of adding tags and fetching data by creating a dashboard.

For the admin side, they will get an audit that shows who logged in—legacy or Guidewire users—and what modifications they made. This helps them by seeing that dashboard rather than viewing each policy individually.

It impacted my organization by helping us move into being AI-native. Our organization is proving themselves that they are AI-native, and it helped a lot to show other clients that we have worked in AI.

I have worked only for six months on Kore.ai. While working on it, I haven't seen any area that needs improvement because I need to explore more in voice chat. I don't think there may be any improvement needed for that part as of my knowledge.

I want to work on voice AI chat, but I have not yet been involved in that. For that project, I was working on widget creation, training the model, and migrating from Kore.ai 10 to 11. Then I moved to a different project, so I couldn't explore that. This is a regret for me. In the future, if I get an opportunity with Kore.ai, I will definitely work on voice AI chat.

I have used Kore.ai for six months.

Kore.ai is stable.

Kore.ai is a scalable product. I think they can add more features, but right now I'm unable to recall something specific for improvement. Definitely, it's a scalable product.

The customer support was good. We connected two or three times and received full support from the customer support team.

I haven't switched to any other solution. I got Kore.ai first and worked on that only. It is a good product.

It is definitely a money saver and time saver.

I haven't evaluated other tools. Kore.ai was the first one, so our organization went with it.

For the process of adding tags and fetching data for dashboards on the admin side, admins will get an audit that shows who logged in—legacy or Guidewire users—and what modifications they made. This will help them by seeing that dashboard rather than viewing each policy individually.

I give a nine for the customer support. I will recommend Kore.ai to others. If anyone is looking for tools similar to Kore.ai, I will definitely recommend it. I will recommend it to someone if they are having issues or problems with other tools. I definitely want to explore more of this product. I gave this review a rating of seven.

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.