Lessons learned from Building Callbot

Last June we booked a 3 days trip to attend the Chatbot Summit in Tel-Aviv. We were used to the various AI events in Paris as exhibitors, but it was our first event outside Europe, and one of the rare we were not exhibiting at. We were pretty excited to attend, to meet our peers, and it has been great. First time I really got to speak to other chatbot software CTOs, (in particular it was great meeting Alan Nicole from Rasa and Yi Zhang from Rul.ai, both CTO and co-founders of two other interesting players) to openly discuss thoughts around the technology, the various approaches to handling conversation management, the market. Like in any field, after a few evenings out, the entire chatbot landscape became a thing about a friendly mix of techy folks and the surrounding ‘sales and marketing’ mates, trying to make a business out of this. We were all on the same battle, each trying to invent new ways to better models and manage conversations, continuously improving things collaboratively, each trying to be the next one.

Callbot for the dummies

Anyway, one of the most interesting topics covered there was callbots. The technology pieces are now in place, ready to be leveraged by the chatbot makers. The key building blocks are readily available (provided you have the right team to play with those blocks):

  • Similarly, the Text to Speech part is also easily available from the GAFAM. You’ll be able to choose from a number of languages, accents, gender for voice generation.
  • A telephony gateway is required to connect the bot infrastructure with public telephony networks or internal business communication platform. In Tel Aviv, we recently met with AudioCodes, a company with a strong background in the telephony world and a substantial business around the Microsoft Azure and O365 ecosystem. AudioCodes have come up with a solution they call Voice.AI gateway that can connect chatbots to any telephony-based platform creating fully voice-enabled engagement channels. We chatted with Ilan and quickly after our return to France, started an evaluation.
  • · Unless you want to build a basic IVR (Interactive Voice Response), a good Chatbot technology is required. It needs to be flexible enough to accommodate to the constraints of voices, with a strong NLP (we’ll see later that a callbot needs good NLP, much more than what is required for a basic ‘button bot’!). Luckily, we had this part, having spent two years building a solid NLP stack, and not diving into callbots before mastering this NLP piece.


My team has started to implement a callbot around our Kbot for IT Help Desk solution. This callbot’s mission is to assist enterprise users with their technical issues and it already integrates with webchat, skype, Microsoft team, etc. We are now developing callbot integration because we learned with our partners that very large support organizations still handle most of their contacts through traditional phone calls, handling these is becoming critical for their survival — and we think the future market winners will be those agile enough to adapt quickly to rapidly changing conversational means.


One of the most interesting challenges for a callbot is to understand “when the user is done with its statement”. In human communication, body language plays a key part in a conversation flow. A phone conversation makes it harder, but we concentrate more and can then understand when the other is done and a response may be provided. Overall, humans are quite good at it, even if cell phones with their latency are often introducing this issue and making people used to it (there are much more callers collisions over a Skype or a satellite line than over a so-called direct line — well, these do not exist anymore in fact, the good old RTC lines are gone for good, no more direct pair of copper wire between two folks thousands of miles apart, that model didn’t scale!).

My core passion is building softwares. I am now CTO and co-founder of Konverso, a startup building virtual assistants powered by AI and NLP (www.konverso.ai)