Skip to main content

Agent.AI - Mobile Customer Service with the AI Bot

Earlier in June I had the opportunity to talk to Barry Coleman, CTO of, an about 2-year-old company at the time of writing this. The company spun off of, a very different business that enable the delivery of in-app advertisements. In order to support this mission more and more, first internal, then external support capabilities were needed.
At first they built chat functionality for internal and for support purposes. Then there was the question of how to efficiently provide 24/7 support. This resulted in giving birth to a bot structure that can help customer service agents in an assisting mode, called co-pilot mode, and an autonomous mode, called autopilot. And it gave birth to’s mission is to enable “exceptional customer service for all”.
While this mission is not particularly unique, their approach is. First, has built its customer service software around a machine-learning platform. Second, the company provides their solution without asking their clients for a huge upfront investment or the need to have of AI-proficient developers in house. Third, they wanted to avoid the pitfall of inflated expectations. With AI and machine learning being very hyped topics at the moment, this is a very valid concern.
Going backwards through the objectives, opted for offering very specialized bots first. As there is no general AI yet, this is pretty straightforward. Specific, tightly framed topics are far easier to support with AI and exposed by bots than broader bodies of knowledge. For example, specializations include the handling of order inquiries or of support call closure surveys.
The second objective was achieved by doing all the heavy lifting, including the customer specific training of the AI in their own system, by providing specialized bots, and by offering APIs for their customers to implement own specialized bots.
One interesting aspect is that’s software fabric allows the individual bots to collaborate with each other and communicate internally with agents and externally with customers. This collaboration is necessary due to the strong specialization of the bots and is mainly controlled by a ‘central’ AI-based bot that resides in the infrastructure, called ‘AVA’, which is an abbreviation for Automated Virtual Agent. AVA is the brains of the system.
The job of the AI bot is to understand speech and to identify a user’s intent using NLP, neural networks, and deep learning. This intent could be a request for information or a call to support an incident.
With this done the AI bot dispatches the incoming request to the corresponding specialized ‘intent’ bot that can take up the transaction and hand it over to another bot, or escalate to a human agent in case they get stuck.
The system is trained from a variety of sources, such as FAQ, existing documentation, and e-mail trails.
Chat transcripts prove to be especially valuable as they allow for identification of both, problem and a solution. These transcripts also offer an excellent means for continuously training the bots while being in co-pilot mode, the mode in which they suggest answers, along with a confidence level in the answer, to human service agents. The usage of chat protocols along with the service agents choosing to use bot recommendations or not, allows for constant recalibration of suggestions’ confidence levels.
Which leads to the topic of trust; user trust as well as agent trust – and to the question when a specific bot can be put into the wild and work autonomously. The answer to this is surprisingly simple although there is no explicit measurement: If suggestions consistently exceed a defined high confidence level then the bot is good to go unsupervised and escalates issues it cannot answer itself to a human service agent. Another possibility of identifying trust levels is the change of customer sentiment in the course of a transaction.
Working in co-pilot mode, with the ability to have bots work unsupervised, human agents free up the time to work on novel problems. Typically, these can be the issues that bots haven’t been trained for, and maybe cannot be trained for. Barry emphasizes that “human-machine cooperation is really important”.

My Take has an interesting story to tell. The idea of offering an affordable infrastructure to provide 24/7 mobile in-app customer service using bots that are driven by machine learning and AI is probably not new but consequently implemented. Bots can considerably speed up the support transaction by continuously listening to specific queues. With well-trained bots this can lead to positive support experiences by showing that a customer’s time is valuable. This also applies to the co-pilot mode, when the bots can already prepare suggestions along with confidence levels that help the service agent prepare herself for an issue.
In addition to providing a toolkit for mobile in-app support, is supporting nearly all major messaging platforms, which allows for richer customer profiles as well as for a wider reach for both,’s customers, and itself.’s customers can offer their customers availability on the channels they prefer without being in the need to look for additional vendors to cover different messaging channels.’s bot-driven mobile first approach puts the company into an interesting position. Mobile in-app specialists normally do not support messaging services with the correct argument that the service engagement can be made far more personalized. This is due to more information being available to the service agent via the SDK. It simply can provide more information than the messaging service will ever do. On the other hand there will be many users who simply do not want to install vendor apps.
Integrations with Zendesk and Salesforce give exposure to the world of the ‘big guys’. Zendesk does believe that bots are not yet far enough to be really useful in customer facing service interactions. Meanwhile Salesforce does not have any bot capabilities either, as far as I know. Both companies offer integration into major messaging apps, with Zendesk also offering an app SDK, though. Still, this leaves an opportunity for innovative vendors.
I believe that the strategy of covering the breadth of mobile along with the ability to cover small to big customers is pretty strong. It puts dead into a spot that no major vendor covers, while at the moment having a technological advantage.
However, there are also some concerns. I suspect that the approach of taking away the ‘heavy lifting’ from customers may lead to consulting services, which do not scale well. In addition is a young company, which always raises the fear of viability. says it has more than 1,000 customers from small to large in different industries. These customers are using SDK and web client most, followed by the Facebook Messenger. While this sounds like a big number there is no information on actual users.

Still, this is a company to watch.


Last Year's Top 5 Popular Posts

SAP CRM and SAP Jam - News from CRM evolution

During CRM Evolution 2017 I had the chance of talking with Volker Hildebrand and Anthony Leaper from SAP. Volker is SAP’s Global Vice President SAP Hybris and Anthony is Senior Vice President and Sales GM - Enterprise Social Software at SAP. Topics that we covered were things CRM and collaboration, how and where SAP’s solutions are moving and, of course, the impact that the recent reshuffling in the executive board has. Starting with the latter, there is common agreement, that if at all it is positive as likely to streamline reporting lines and hence decision processes. First things first – after all I am a CRM guy. Having the distinct impression that the SAP Hybris set of solutions is going a good way I was most interested in learning from Volker about how there is going to be a CRM for S4/HANA. SAP’s new generation ERP system is growing at a good clip, and according to the Q1/2017 earnings call, now has 5,800 customers with 400 new customers in the last quarter alone. Many

SugarCRM explains how the third wave of CRM adds value

The news On October 4 and 5, 2023, SugarCRM held its Connected event followed by an analyst summit in London. The first day – Connected – was targeted mostly at customers while the second day focused on analysts.  The event started off with an intense speech by Katherine Grainger, DBE , a British rowing champion. Her core messages were about team bonding, the importance of communication, continuous improvement, and perseverance (well, at least that’s my take). This was followed by information about what is new in the software and, more importantly, a customer panel.  The main sponsor, Mobileforce , placed some words about the partnership. In addition, the analysts had 1:1s with customers, partners, and Sugar executives. The second day was filled with information targeted at analysts. CEO Craig Charlton and his executive team shared about financial status, strategy and more in-depth product news. Sugar being a privately held, VC backed company, the financials are of course under NDA, s

How to play the long game Zoho style

The news On February 7 and 8 2024, Zoho held its annual ZohoDay conference, along with a pre-conference get together and an optional visit to SpacX’s not-too-far-away Starbase. Our guide, who went by Chief, and is probably best described as a SpaceX-paparazzi was full of facts and anecdotes, which made the visit very interesting although we couldn’t enter Starbase itself. The event was jam-packed with 125 analysts, 17 customer speakers, and of course Zoho staff for us analysts to talk to. This was a chance we took up eagerly. This time, the event took place in MacAllen, TX, instead of Austin, TX. The reason behind this is once more Zoho’s ruralization strategy, transnational localism.  Which gives also one of the main themes of the event. It was more about understanding Zoho than about individual products, although Zoho disclosed some roadmaps. More about understanding Zoho in a second.  The second main theme was customer success and testimonials. Instead of bombarding us with presenta

Relevance, reliability, responsibility are key for AI – the SAP way

The News A lot is going on in the SAPverse during October and the early days of November 2023. First, SAP conducted its CXLive event with CX-related announcements, then the company reported good Q3/2023 figures, a new version of its CX software that includes new generative AI capabilities got released and lastly, it executed its SAP TechEd event with a good number of AI-, BTP-, and ERP related announcements. As this is quite a lot, I covered the CX world in a previous post and will cover the TechEd related news in this post.  So, what is new at SAP TechEd ? For one, it is enough to fill a 17-page pre-event news guide that SAP sent out. SAP certainly is able to stack up the news for major events. I took the liberty to ask ChatGPT for a summary of the document, which I slightly edited afterwards. Here we are: AI and Development Environments: ·       SAP introduces SAP Build Code with generative AI, improving application development and testing, while new AI capabilities are integrate

The Generative AI Game of Thrones - Is OpenAI toast?

The News This has been an exciting weekend for the generative AI industry. On Friday November 17, OpenAI announced that the company fired its figurehead CEO Sam Altmann and appointed Chief Technology Officer Mira Murati as interims CEO in a surprise move. The press release states that Altmann “ was not consistently candid in his communications with the board .” Surprised was apparently not only Sam Altmann, but also the till then chairman of the board Greg Brockman who first stepped down from this position and subsequently quit OpenAI. Investors, notably Microsoft, found themselves blindsided, too – or flat footed depending on the individual point of view. Satya Nadella was compelled to state that Microsoft stays committed to the partnership with OpenAI in a blog post that got updated on November 19, 11:55 pm. All hell broke loose. Microsoft shares took a significant hit. A number of additional senior OpenAI personnel quit. Both, Altman and Brockman, voiced the idea of founding anoth