I had an online conversation with someone recently and they referred to Chatfuel as a "lesser" platform for Dialogflow bots. This got me thinking, and I have created a video to explain my views on this topic.
- Yes, I agree that it is a poor choice for NLU/AI bots (but great for pure rules-based bots)
- You can do the same integration without Chatfuel, but it requires more effort to get feature parity (obviously)
- Designing NLU conversation flows is harder
- You need to learn a second UI specification
- You have less control over your bot
- There is a problem of lock in
I don't have the same experience with integrating ManyChat, but I have seen tutorials on how to build the integration. Based on what I have seen, you will face the same issue with ManyChat also.
Here is what I think: If you have the resources to build a custom Dialogflow+Facebook integration, your final bot will be a lot more flexible and it will also be a lot easier to analyze the behavior of its NLU portion.
Said another way, the more "intelligence" you wish to add to your bot, the more important it is that you build out your own integration.
- Dialogflow vs RASA NLU
- Dialogflow vs Lex vs LUIS vs Watson vs Chatfuel
- Machine Learning vs non-Machine Learning algorithm
- BotFlo update
- Learn Dialogflow basics for free (till May 31)
- 10+ practical projects to learn spaCy in depth
- An Epidemiology Glossary for Programmers
- All my mini-courses are free this week
- Reader Question: What if a specific system entity isn’t available in all languages in a multi-lingual bot?
- How much can Machine Learning ACTUALLY help with answering free-form questions?