Rasa vs. Agentforce

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

Agentforce has a lot of applications. We are using it in consulting to benchmark other clients, what they're doing, where we stand, how can we have better efficiencies coming in, et cetera. Those are the areas where it is doing exceptionally well. The area where we feel it can do much more better is maybe a market benchmark because it's been used across by so many players and it's a connected ecosystem. If Salesforce can have something where it gives me the market view of things, I can then benchmark rather than in my own universe to the broader university Salesforce and I know where I exactly stand and what more can I achieve, what's my final goalpost. So that would be something really great.

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

• Which helps in creation of Autonomous AI agents to operate
• Multi-System Integration with "Zero-Copy" Data Access
• To built chatbots and copilot tools by utilizing the Atlas Reasoning Engine to function as an autonomous digital workforce
• Order and Transactional Management

Incentivized

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

Incentivized

• It is complex too, more help documentation or videos will help
• AI assistance doesn’t work well for specific or detailed questions
• So much configuration available it can put off new users

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

The platform offers an intuitive overall experience and the expected strong integration with other Salesforce existent tools. It has a low learning curve for new users on the commom use cases, such as intent classification, routing and knowledge-based answers. It could be improved with more transparency regarding to the AI decision logic.

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

Incentivized

We did evaluate the EVA bots, which are coming in market for Salesforce effectiveness. Those bots are good, but they're based out of very traditional use cases in the life sciences space. Agentforce is very, very advanced, right? Eva can talk about a typical sales rep coming in, logging in the day, log their entire day, and then probably having a simple text to reporting kind of a view. And that's it. Agentforce gives me a lot of insights, it gives me a lot of actionable insights. It uses its own brain. That's where Salesforce is an AI company. So we trust the Salesforce banner for it to innovate more and more, more and more. And that's where we chose Agentforce over.

Incentivized

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

Incentivized

• We were able to assist customers with the self service option, without wasting effort from a real CS advisor

Incentivized