Finally, Tiledesk integrates
Posted: Sun Dec 15, 2024 4:35 am
A powerful automation engine that can interpret and implement complex logic through the use of no-code tools, based on generative AI. This allows for flexible and accessible design of automated workflows, which leads to greater support service efficiency, reduced response times and personalized interactions based on specific user needs.
Conclusions
Speaking of numbers. We actually exchange an average italy phone number whatsapp of 200 messages/second, with peaks of only 500 messages/second leveraging our instant messaging engine. Choosing market-proven protocols and platforms like MQTT and RabbitMQ was the right choice. Thanks to flexible standards (MQTT) we can evolve the messaging engine very quickly, following all upcoming Tiledesk needs.
And we have a lot of future needs. Thanks to the penetration of AI in Tiledesk, the messaging engine was the first to be involved in the AI wave. For example, we are adding the ability to broadcast text messages , something that is mandatory for generative AI when aiming to reduce long delays in generating LLM responses by returning the message text (or a part of it) to users as soon as it is generated. With XMPP this had been an impossible progress, while MQTT/RabbitMQ allows a lot of flexibility. Big messaging players have already switched to MQTT for messaging (e.g. Facebook Messenger ) and there will likely be more. We have released our Chat21 engine open-source to give everyone the opportunity to work on it or use it as a prototype for their own messaging engine. It is MIT licensed, for maximum flexibility.
Conclusions
Speaking of numbers. We actually exchange an average italy phone number whatsapp of 200 messages/second, with peaks of only 500 messages/second leveraging our instant messaging engine. Choosing market-proven protocols and platforms like MQTT and RabbitMQ was the right choice. Thanks to flexible standards (MQTT) we can evolve the messaging engine very quickly, following all upcoming Tiledesk needs.
And we have a lot of future needs. Thanks to the penetration of AI in Tiledesk, the messaging engine was the first to be involved in the AI wave. For example, we are adding the ability to broadcast text messages , something that is mandatory for generative AI when aiming to reduce long delays in generating LLM responses by returning the message text (or a part of it) to users as soon as it is generated. With XMPP this had been an impossible progress, while MQTT/RabbitMQ allows a lot of flexibility. Big messaging players have already switched to MQTT for messaging (e.g. Facebook Messenger ) and there will likely be more. We have released our Chat21 engine open-source to give everyone the opportunity to work on it or use it as a prototype for their own messaging engine. It is MIT licensed, for maximum flexibility.