Rasa vs. Yellow.ai

I have been using the platform for over 3 years and I have noticed a very good evolution, in an attempt to reinvent themselves. The support team is amazing, always available to work out with us in achieving the best results. About the technology, the algorithms available in the platform suits most of the cases. Being language agnostic is a very positive point for us, because some big tech platforms have little support for PT-PT language.

Incentivized

We are very happy how yellow.ai helped us through our customer journey. All the use cases are well met and fully automated. Our customers also found it very easier to get into the basic FAQs before getting into direct customer care agents. Needed a few more advancements in integrating catalog with chat so users can shop directly from WhatsApp or chat messages than going to our app/website. Overall I recommend it very much.

Incentivized

• Rasa team has Top notch AI knowledge
• Greate customer support, by listening towards the clients needs.
• And building future proof solutions around client Business Requirements within dazzling timeframes

Incentivized

• Web integrated chat bot
• WhatsApp bot
• Good support from YM team
• Transparent dashboard for analysis

Incentivized

• Rasa CALM flows and Rasa domain could be made fully independent of the Rasa training process and dynamically retrievable from e.g. a graph DB. This would make the chatbot more flexible.
• Prompt templates, or at least paths could be referenced in Rasa config. Different policies in the Rasa config could then be configured without code change to use different prompt templates
• LLM configuration should rather be part of the endpoints, than model configuration.
• Rasa Studio could support all the functionality of Rasa Pro.

Incentivized

• Shopping features in bot
• pricing
• app integration

Incentivized

With the help of dedicated team - documentation and video resources it is relatively easier to build. We prioritized pro-code usage to begin with launch.

Incentivized

Rasa support has been very responsive, trying to fix any reported issues ASAP. They've also listened to many requests for improvement. The Rasa features and changelog are well documented

Incentivized

Glean - proprietary semantic search algorithms, no backend actions integration IBM Watsonx - complicated dialogue builder, poor separation of no-code and pro-code interfaces ELMOS (agent based) - all logic in code, no dialogue logic in no-code interface possible Rasa - transparent and simple sharing of objects between no-code and pro-code interfaces. Transparent LLM usage and restrictions. Simple backend integration via Rasa SDK

Incentivized

The main factor was use cases implemented elsewhere in the BFSI domain besides competitive cost & implementation timelines.

Incentivized

• Reduced Human Connected Calls Per active User
• Improved Calls disposed by Voice Agent
• Reduced call wait times

Incentivized

• Chatbot is another touch point for customer to do servicing of their loan.
• The following are the benefits for the customers.
• Avoid long wait times to reach agent.
• Get quick and reliable and up to date information.
• Easy and guided self-service journey.
• Post-launch on 04-Jan-20, in one month we had around 28000 unique customers visiting the bot.
• 24 X 7 availability.
• Increased customer satisfaction.
• Reduction in customer support manpower.

Incentivized