ManyChat vs. Rasa

ManyChat is extremely easy to set up on your Facebook business page and Instagram account. Even if you just want to try it out, the free plan is great to get started. If you want to provide a freebie or 24/7 customer support, you can get it done with ManyChat.

Incentivized

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

• ManyChat has a Facebook comment feature that when your audience comments on a particular post on your Facebook page then send them the information you have promised them. Once set up, is all on autopilot.
• We have the ManyChat plugin on our website to act as a customer service chat feature for those looking for help and engage with us.
• Have some great integrations on the pro account with payment gateways such as Stripe that allows you to charge your clients and receive money.

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

• Better one way communication once explicit consent from recipient is acquired.
• Ability to see in one place where any automations are live.
• Alerts or notifications when an automation fails.

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

ManyChat is a great tool, provides loads of features, integrations and just saves you a whole load of time once all set up. If you aren't tech-savvy or used to how digital marketing tools work, it can appear complicated. That's how I felt initially 2 years ago, and after watching tutorials online I had a better understanding of it. This is why I rated it a 7, as it's not a tool that you can just play around with and guess how it works. There's definitely a learning curve with it so I recommend doing the free training and watching video tutorials.

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

There is room for improvement but frankly, we haven't had the need to request for support. Everything is pretty easy to setup and there are very useful video explanation guides and walkthroughs on ManyChat's YouTube channel. The only challenge we have had was to integrate it with Zapier, it's a bit tricky because you need to do a setup workaround first, but nothing too complicated.

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

For the initial purpose of getting ManyChat, none of the alternatives worked either. We ended up creating a mobile app to meet the need. For incoming support automation, using the native features within Facebook has been effective as well as using GoHighLevel and Continual.ly. ManyChat was considerably more effective, but with the price increase and the non-necessity of carrying another subscription for incoming message support, it wasn't a logical choice to keep the service.

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

• We have a very positive ROI for our business. We have been generating about 10 leads a month. We are currently closing on 10% of those, so 1 new client a month. We are working on ways to improve that conversion percentage.
• We generate around 50 leads a month for a client of ours. Their conversion is about 25% Their average ticket is 1,500.00 which puts them to about 15-20 thousand a month.

Incentivized

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

Incentivized