Now that your virtual agent is live, expectations are that the bot is prepared to handle everything. Customers will ask their question, get the right answer every time, conversations will be fully automated and impeccable and everyone’s happy. But, let’s be honest, that’s not actually how it goes, right?
To imagine every scenario and design deep and meaningful content for every interaction is frankly not possible, despite your best efforts. Pesky customers ask questions in different and unique ways, or they ask about things the bot has never before encountered and it doesn’t have a response: New products? Check. Policy updates? Check. More detail on existing responses? Check.
Rising to the challenge of intent discovery
The goal of an intelligent virtual agent is to enable customer self-service, guiding customers to the right answer, without needing agent escalation. But, how can it do that when customers ask questions it can’t handle?
Conversational AI is a lot of things, but it’s not magic. The chatbot team has the important responsibility of making sure your virtual agent is trained and ready to respond.
Maybe your customers are asking questions in unexpected ways and the bot needs additional NLU (Natural Language Understanding) training. It may be that conversations have stalled and you can upgrade the automation by fine tuning intents with sub-topics, or it may simply be that it is a completely new topic that is suddenly seeing an upswing of inquiries and you need to quickly design and introduce new intents.
The key to correcting performance is being able to find and fix those conversations that are causing your virtual agent to stumble. Intent discovery is the path to progress, but it doesn’t always come easy…
The problem with intent discovery that’s not designed for scale
Intent discovery is a huge problem for chatbot teams – that’s hiding in plain sight.
Every day, your virtual agent fields thousands, if not tens of thousands of inquiries every day. And for some portion of that, the chatbot simply will be unable to provide a helpful answer. Finding those intents and topics, and then designing a work plan to fix them is integral to the day-to-day activities of a chatbot team. You know you need to do the work, but what a headache!
Some teams turn to SQL to help them out. Following hunches, writing queries, sometimes, it feels like a game of hunt and peck.
We know of at least one team that prioritized a daily task of scrolling through 100 conversations every day to find those awkward moments, manually assessing each one to evaluate whether this was an opportunity to retain the bot or build a new intent. Managing vast spreadsheets was a daily practice that consumed a lot of time and energy.
The longer a virtual agent is in production, the more volume is driving to the bot, the harder it is to manually scrub through the data and make sense of it all. And that’s if you’re lucky enough to have access to timely conversation data. Many teams do not, and experience long waiting times to get access.
Other teams rely on specialized resources with deep data science expertise: it usually isn’t a priority, they don’t always understand the ask, and when the report comes back it’s not always usable and needs to be deciphered, organized, questioned … Sadly, for at least one team we know, that process took upwards of six months. What a missed opportunity to address customer inquiries and build better automated experiences!
If your virtual agent is managing conversations at scale, you simply can’t afford to wait weeks or months, continuing to serve up frustrating conversations and agent escalation.
Evolving a virtual agent to become more responsive, more thorough, and deliver the automated experience you’re looking for, requires a different approach.
Taking the headache out of a thankless job with AI-driven intent discovery and chatbot analytics
From the newly launched to the most established, virtual agents will always field questions they are unable to answer. Conversational AI is taking hold, and virtual agent conversations are becoming increasingly complex. Chatbot teams need the right tools to help them hone in on unsuccessful conversations, navigate this complexity, and build better conversations.
The good news is that innovative technologies exist that easily pinpoint those difficulties, allow you to identify them as training opportunities or new intents, and then help you prioritize a worklist to address the issues.
Check out our interactive demo session Accelerating intent discovery with AI and learn how you can easily combat intent discovery, and get ahead of the growing pace of automated conversations.
