Azure AI Bot Service vs. Google Cloud Dataflow vs. Fin by Intercom

From personal experience, I can recommend the Azure AI service to reduce the burden on your customer service team, as we did. We created a customer service bot and automated our Frequently Asked Questions section, as well as an interactive platform for registering other complaints that the bot cannot handle, which are later addressed by our customer service team.

Incentivized

It is best in cases where you have batch as well as streaming data. Also in some cases where you have batch data right now and in future you will get streaming data. In those cases Dataflow is very good. Also in cases where most of your infra is on GCP. It might not be good when you already are on AWS or Azure. And also you want in-depth control over security and management. Then you can directly use Apache beam over Dataflow.

Incentivized

Fin was very easy to train and implement. We had previously used Intercom, so we already had a lot of content available there, and Fin was able to leverage it and immediately provide users with meaningful answers. It was ready and working successfully within a single day, and we have been improving on it ever since.

Incentivized

• Assembles conversational AI encounters for our clients
• Adds regular language, discourse, and vision
• Sends to well known channels with insignificant code changes

• Streaming, Real time work load
• Batch processing
• Auto scaling
• flexible pricing

• 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

• Limited Natural Language Understanding, especially in entertainment contexts where slang, humor
• Works only with Azure platform only not compatible with other platforms
• Complex customization as per organization need

Incentivized

• More templates for Bigquery and App Engine. There is only limited options for templates so the things we use can limit.
• I would like native connectors for Excel (XLSX) to reduce the need for custom wrappers in financial pipelines.
• Debugging Google Cloud Dataflow using only logs in Cloud Logging can be overwhelming sometimes, and it’s not always obvious which specific element in the flow caused a failure. IT uses a lot of time.

Incentivized

• It seems some users really struggle to figure out how to escalate to a human (especially through email).
• Not excited about how "soft" resolutions still count as resolutions and are paid for. Though some abandoned cases appear to be able to be concluded as "the user got the answer they needed", there are others where they clearly didn't, because they just open up another chat (or even more), trying to get more info. This pads the resolution stats and makes it seem more effective than it actually is.
• Cost -- Fin is quite expensive. It helps us with scaling coverage, but we're not really saving money.

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

Azure AI Bot Service comes with an Integrated Development Environment and Bot Framework SDK that simplifies development. Having a single codebase for multiple channels, such as MS Teams, Facebook, and Slack, makes it easier to target multiple platforms without requiring redevelopment. LUIS and OpenAI can be easily integrated with your Chatbot to provide a seammless chat bot expereince to customers.

Incentivized

It really saved a lot of time and it's flexibility really can give you infra which is future-proof for most of the use cases may it be streaming or batch data. And with this you can avoid use of resource-heavy big data offerings.

Incentivized

Fin is extremely user friendly and was very easy to set up, and this is coming from someone who has never used any technology like this before. Fin was easy to customise to the way we wanted this to be, set up specific messages to our customers through Fin, customise the tone and content used as well as configure Fin's handovers to a human when required

Incentivized

always there

Incentivized

works perfect

Incentivized

Microsoft's customer service staff is friendly and extremely knowledgeable. They are always available to assist you with bot framework-related issues that you may be experiencing. They provide training sessions, manuals, and support personnel, among other things. Bugs were easily spotted and patched, which was one of my pet peeves about patching.

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

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

Microsoft Bot Framework is much better and well more established without a lot of proprietary software/coding language. Lex is very limited with integration with standard hardware and network configurations. Lex has performance issues and was too slow to meet near real-time collaboration requirements. Bot Framework complements many other Microsoft communication products and this was key to implementing without a lot of new training required.

Incentivized

Google Cloud Dataproc Cloud Datafusion

I've tried several AI chatbots before when using Zendesk. We found that the native Zendesk AI was expensive, but the best compared to "alternatives" such as Chatbase, My AskAI, and Macha. Then, we decided to switch over to Intercom for the startup program. WOW!!! Fin blows away any other AI bot on the market. Even if you're not using Intercom as a platform (you should), I highly recommend you use Fin. We've never had this high of CSAT or resolution with an AI bot before; our customers love Fin

Incentivized

• Azure Bot will only deliver according to the granularity of the FAQ it is feed. Otherwise, it has been a cost optimization tool for our organization.

• cost saving from managing our own data center for ETL servers
• consumption based pricing
• with auto scaling feature, we were able to expand components to support work load

• New role opportunities — Using the “Fin-first” approach has reduced the workload for our Tier 1 team, giving them more time to focus on their own career growth. It’s also opened the door to a dedicated, AI-focused role, where a team member regularly reviews Fin’s answers and makes updates to help it perform even better.
• Enabling Fin has also reduced our response time and allowed us to meet SLA's.

Incentivized