Fin by Intercom vs. Rasa

Fin works best for handling routine questions like account issues, billing inquiries, onboarding guidance, and linking users to relevant help center articles, providing fast, consistent support without human intervention. It’s less suited for super complex troubleshooting, more sensitive complaints centered around billing, or highly personalized requests and product feedback that require human judgment and deeper product knowledge.

Incentivized

Rasa Pro is well suited for corporate use and for chatbots which require backend connections. Smaller chatbots with a few flows might be better served with a simple dialogue engine and custom AI agents, or Rasa Open Source. Rasa does not come with its own complex vector database, just in-memory FAISS and connectors to external vector DB's such as Milvus and Qdrant. It provides only a basic document parser and embedder for FAISS. If you need to build a RAG focused chatbot around a large knowledge base with complex documents, e.g. lots of MS Word or PDF files, you'll have to build a separate document parser and embedder, as well as your own semantic search engine

Incentivized

• Serves as the first point of interaction.
• Answers questions based on the knowledge base.
• Tries to suggest a solution for reported issues (in some cases).
• Gives the option to improve its answer.
• Learns from other conversations and replies by humans.
• Understands other languages.
• Interprets images (somewhat).

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

• Sometimes Fin can provide incorrect information when using previous conversations as a source; this is one of the few downsides, as teammates can sometimes make mistakes.
• We also sometimes see that Fin does not pass to a human as quickly as we would like, but this could also be a training improvement our business needs to implement.

Incentivized

• No-code apps could be improved
• Online docs can be messy
• Steep learning curve

Incentivized

We have been and will be continuing our journey with Intercom and nothing too concerning has happened that I have experienced or heard of that has us on the edge yet. If it ever happens it will be something along the lines of "Outgrowing" the use of need of the platform.

Incentivized

The Intercom plattform is amazingly well and this allows us to use FIN to its fullest potential. You have various ways of customizing your agent (from name, voice, guidance, escalation rules) and you have various built-in ways of understanding your performance and where you can improve (optimizer, topic explorer, etc.). And of course you can use FIN to ask questions about FIN! And FIN from Intercom is very well trained on itself, helping with most setup questions easily.

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

always there

Incentivized

works perfect

Incentivized

Intercom is the premier customer support/engagement model and it definitely has one of the top tier customer support teams as well. I don't think I have ever waited more than 5 minutes to get the information I need or get help with an issue. They are incredible and I aim to model our customer service department after them.

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

Easy to know the learning path

Incentivized

The implementation was surprisingly easy but we are having to adapt from our old process to work well with Intercom.

Incentivized

We used it a few years ago, and it was not as feature-rich for our needs. It lacked true AI capabilities, was hard for users to understand, and created workaround issues. The internal ticket system was difficult to use and led to many missed issues and calls.

Incentivized

Incentivized

• Greater customer satisfaction: Implementing Fin by Intercom AI and Intercom in general has definitely improved our CSATs from our customers. We are now consistently getting high 90s (in percentage) from our CSATs, both for Fin by Intercom and teammates. So yes, our customers are really happy with how Intercom is working.
• Reduced speed and responses: Since implementing Fin by Intercom AI and Intercom, our speed and resolution has increased massively. Resolution times have gone from days to hours with Fin by Intercom AI included. And now, with AI, customers are getting instant answers around the clock, rather than having to wait for a person.
• New role opportunities: Fin by Intercom AI have lead to many new roles created, including mine. Which has expanded overtime.

Incentivized

• Cost Savings & Efficiency
• Increased Conversion Rates
• Improved Customer Satisfaction
• Operational ROI

Incentivized