6 ways to use chatbots as part of your HR automation strategy

6 ways to use chatbots as part of your HR automation strategy

6 ways to use chatbots as part of your HR automation strategy

Human resources (HR) is a department that relies entirely on communication and conversation. So it makes sense that conversational AI is one of the best solutions when looking into automation options for the HR team. Chatbots allow HR teams to scale their conversations while keeping things personal.


Here are some ways you can use a chatbot to support your HR department.

Answering employee questions

Employees have questions; it’s normal. And depending on the size of the company, the volume of questions can be pretty high. The nice thing about a question for the HR team is that if one employee has it, there’s a high chance others will have the same question. This means that many of the questions are repetitive– which is one of the key characteristics of automation.

By automating basic questions like, How do I ask for time off? or How do I get a replacement badge?, your HR Managers have more time to follow up on more complex cases. Plus, a bot’s available 24/7, so employees can get a response immediately, instead of waiting for an HR Manager to wade through their overflowing inbox to respond. 

One of our all-time favorite HR chatbots is Proximus’s YODA, who helps answer +6,600 questions per month.

Proximus's chatbot, Yoda, chats with employees and answers all their HR questions

Automating employee onboarding

A chatbot is a perfect onboarding assistant because it can help HR teams automate frequently overlooked processes that are time-consuming and repetitive.


According to research by the Brandon Hall Group, strong employee onboarding can increase new hire retention by 82%. However, Sapling estimates that the average onboarding process includes 54 different activities. Of these activities, a majority of them are administrative and include questions such as What keyboard format do you want?, Who’s your emergency contact?, Do you need a standing desk?, etc. These are all questions that a chatbot can easily automate. Plus, it’s always nicer to answer these questions from the comfort of your desk, instead of sitting in a meeting room while the HR Manager awkwardly watches you complete all the forms. 


Another reason an onboarding chatbot is so helpful is that it’s basically your new employee’s single point of contact and is always accessible. When starting a new job, it’s normal to have questions, but in many cases, you don’t know who to ask and don’t want to bother someone who’s busy with a silly question. Integrating an employee onboarding flow within a company FAQ chatbot gives your new hires instant support whenever they need it.

Marshall Mallow, Campfire AI's onboarding chatbot, chats with an employee on Slack the night before his first day

Simplifying recruitment

Recruiting is expensive and time-consuming. SHRM estimates in its 2022 benchmarking reports that the average cost per hire is $4,700. SHRM also calculates that it takes ~33 days to fill a position. And the even crazier part?! You can use a chatbot to automate most of the tasks in the recruitment funnel. 


A recruitment chatbot can support a variety of repetitive recruiting tasks, such as answering questions about the company, submitting applications, pre-screening, scheduling interviews, confirming next steps, sending offers, etc. 


We’re still looking for a recruitment bot to fall in love with. So if you have some great examples, feel free to share them with us via WhatsApp. Or even better, if you’re looking to build a recruitment bot, get in touch with Alexis so that we can build one everyone loves together!

Improving employee engagement

Chatbots are a great way to stimulate employee engagement. They don’t judge, they’re always available and you only have to talk to them when you’re in the mood. 


When it comes to employee engagement, bots are a great way to regularly collect authentic employee feedback. They’re more personal, casual and relevant than an annual survey sent by mail every March. Why? Because it’s easier to respond to how you’re feeling about a company initiative when it happens, rather than trying to remember what the initiative was 4 months later when the annual survey pops up in your inbox. It’s also more natural to respond in a conversational format, and using emojis can help express emotions. Plus a bot can ask follow-up questions or use buttons to keep the conversation moving forward.

Standardizing performance management

Similar to employee engagement, performance management isn’t something that you should leave for one moment of the year. Growth happens throughout the year and for an employee to successfully improve and learn, there should be regular evaluations and check-ins. 


This usually panics managers because if you manage a multi-person team, then you’ll probably end up spending more time reviewing your team’s performance than working with them, right? Wrong. Let a chatbot automate performance management for you. By implementing short, regular feedback moments throughout the year that the bot manages, you’ll increase transparency and automate the reminders, input collection and follow-up.

Campfire AI's chatbot automates monthly performance review check-ins

Executing employee transactions

Similar to conversational banking, HR bots can help automate conversational transactions, such as viewing recent payslips, calculating an employee’s remaining holidays, submitting expenses, etc. Instead of housing this information on different platforms with different logins, make it as easy to access as having a conversation with a friend. Trust us, your employees will thank you for this major upgrade in user experience. 
An HR chatbot helps an employee check their last payslip

Everything you need to know about HR and conversational AI

Everything you need to know about HR and conversational AI

Everything you need to know about HR and conversational AI

You’re probably thinking, what does human resources (HR) have to do with artificial intelligence (AI)? Well, they have a lot more in common than you might think. As the name suggests, HR is a human business, and humans communicate using language. Conversational AI uses natural language processing (NLP), which is essentially AI for language. Since language powers both HR and conversational AI, it makes sense that HR departments use conversational AI to automate tasks and processes that lead to better employee experiences. 


The HR department is the one team in a company that connects with every employee. Therefore, it’s no surprise that messages, requests, questions, etc. flood HR representatives. A lot of the incoming questions for HR teams are repetitive, easy to recognize and easy to answer. This is the trifecta for conversational AI automation, making chatbots a win-win for HR teams and employees. 

The benefits of conversational AI for HR teams

💾 Save time and resources

Imagine how much time your HR team could save if they answered a question once instead of repeatedly answering it multiple times a week or day. By implementing a chatbot to answer employees’ most frequently asked questions, an HR team can save anywhere from 10-20% of their time, depending on the scope. 

🧬 Focus on complex issues

You can repurpose the extra 10-20% of time that your HR team saves to focus on more complex issues. There are always a few employee cases that require extra follow-up, a meeting, some calls and whatnot, that your HR reps now have time to do. Instead of chaining your HR team to their email inbox answering simple questions, they’re able to solve problems and support your employees. That’s the real objective of an HR employee anyway, right?

⚠️ Reduce human error

Mistakes happen. Whether you miss an email, send the wrong link, forget about a policy update… HR managers are only human. Whereas a chatbot is programmed to follow a standardized logic with pre-defined responses, making small mistakes almost impossible. This way, HR managers don’t waste time and energy memorizing the small details and can focus on the more complex issues mentioned above. 

🏢 Reinforce your company culture

A chatbot is a great way to reinforce your company culture and values. You can design its personality to be exactly who you want it to be, and it’ll never have a bad day! Plus, it’s just as happy answering a question the first time as it is answering it the 200th time. 

The benefits of conversational AI for employees

⚡️ Immediate answers

A chatbot is available 24/7/365 and can answer an employee’s question in seconds. There are no office hours, long queues or 2-week OoO messages. 

🎯 Personalized experiences

A chatbot integrates seamlessly with your company platforms, making it possible to identify your employees and tailor the bot responses to match their needs and profiles. For example, Kathy from the Chat Team messages the bot on Microsoft Teams and asks for a copy of her most recent payslip. The bot recognizes her work profile and matches it to her file on the company payroll system. The bot then retrieves the link for her most recent payslip and shares the PDF download link via the Teams chat. Personalizing answers based on an employee’s profile is crucial for HR teams since most questions are specific to that employee. 

🤝 Interactive communication

It’s more enjoyable to chat and interact via conversation than create a ticket and send it out into cyberspace, hoping it lands in the correct inbox. By chatting, employees receive immediate recognition of their questions and can follow up with additional questions.

📱 Integrated accessibility

These days we can integrate a chatbot on almost any channel. That way you can connect with your employees via a channel that they already use. Whether it be on your intranet, in a company app or via workplace messaging (Teams or Slack anyone?), it’s easier to ask a question rather than digging around in an old onboarding document or the internal organogram trying to find the email of your HR business partner. 

What are the best use cases for HR chatbots?

There are so many different ways a chatbot can support your HR Team. Here are some ideas to spark your interest:

  • Conversational job applications
  • Screen candidates
  • Schedule interviews
  • Answer (prospective) employee frequently asked questions
  • Build pre-boarding, onboarding and deboarding flows
  • Gather employee feedback
  • Facilitate performance reviews
  • Submit expenses
  • Request holidays
  • Share shift schedules
  • View payslips

For a more detailed business case, check out our work for Proximus HR or dive deeper into the topic with 6 ways to use chatbots as part of your HR automation strategy.

What’s next for HR and conversational AI?

HR teams will continue to adopt conversational AI at varying rates depending on their company’s digital maturity and willingness to innovate. Here are our predictions for how we think AI will change HR teams in the coming years. 

Most large companies will have a robot on their HR teams

Robots are available and scalable. As companies work towards digitization goals and automate internal processes, they’ll turn towards a bot for support. If you’re curious to know more, check out 5 reasons why your next hire should be an HR bot.

Handovers to online HR agents will replace shared HR email addresses

A great chatbot never works alone. It’s usually backed up by a team of human colleagues who take over the conversation when the bot can’t continue. This means that instead of employees actively sending a question to a shared HR email, they’ll start chatting with a chatbot. When the bot needs additional human support, it’ll bring the employee directly in contact with an HR representative via an offload or live handover flow.

Chatbots will become the centralized interface for all internal needs

Instead of having an email for payroll, a website for mobile expenses, an app for holiday requests and a phone number for healthcare benefits, we see all of this coming together in one chatbot. Not only is it easier for employees to use– they just need to visit one place– it’s easier for HR teams to manage. 

NLP will become the main engine behind process automation

Since HR is all about communication and language, it makes sense that conversational AI will become the main engine for automating HR tasks. From immediately answering questions to directing employees to the right contact, chatbots will take the lead in increasing HR efficiency. 

Bots will conduct screening interviews

We expect larger corporations to adopt bot-run screening interviews over the next few years. Asking basic questions and evaluating the responses compared to a clear rubric is a task that a bot can easily take over. Just as you would teach a junior recruiter what to look for in a candidate, you can teach a bot the same. Automating the screening process will free up recruiters to focus on the interviews where emotional intelligence is required.

How to scope your next chatbot project

How to scope your next chatbot project

How to scope your next chatbot project

When sitting down to decide what information your chatbot should know (i.e. scoping your chatbot), you’re actually trying to predict what questions your future users will ask. And by giving your users a keyboard, you’re opening up the list of possible questions to include literally everything and anything


When a user asks a question, your bot will use natural language processing (NLP) to try and determine the intent (or purpose) of your user’s question. These intents are the building blocks of your bot’s knowledge. 


For your bot to recognize an intent, you need to identify what questions your users will ask, build an NLP model based on that information and train your bot with +40 expressions per intent. 

There’s a big difference between what your bot could know and what it should know. But to get to the should, you need to start with the could. Below we share our favorite places to look for possible intents and our tips on selecting the most impactful ones. Because at the end of the day, your chatbot needs to save you time and money.

Gather all the possible intents

The scoping phase of a chatbot project is when you gather all the possible intents. This is the time to dig out a magnifying glass and play Sherlock Holmes. Just like a detective, you need to poke around in the dusty corners, interview witnesses and listen for the truth. 


This is the phase where you’ll look into all the possible questions your bot could answer. If you’re feeling impatient and want to know what your bot should answer, skip ahead to the next section.

Start with the FAQs

There’s a reason companies have FAQs– they’re the select set of questions that users ask the most. Not only do you already know that these are high-volume questions, but the content is also structured and the answers are there! It’s almost a perfect outline for your chatbot’s scope. All you need to do is rework the questions to match a single intent and rewrite the copy to fit a conversation.

Chat with your customer support team

No one knows your users better than your customer support agents. They interact with and solve your users’ questions and issues daily. Most customer support teams have a knowledge library of questions and answers beyond the basic FAQs. Similar to an FAQ, you can assume that users ask these questions repeatedly, and there’s already a clear outline of how the bot should answer.


Customer support teams are also your gateway to the “information universe.” They manage the access to the digital archive of all past user conversations, and in most cases, they classify these conversations with topics, tags, and have template responses. This is a friendly warning that reading through real user conversations can lead you down the black hole of information overload, but we swear that this is the best way to understand who your bot will talk to and how they’ll respond to it. 


In case you’re still not convinced, the final reason to involve your customer support agents in scoping your chatbot is that they’ll be your bot’s direct colleagues. When your bot can’t close a user request on its own, your customer support agents will take over the conversation via an offload flow. You need to know how they work to design a bot that will help them, and they need to understand how the bot will work to help users better.

Review company documentation

Is there an onboarding manual? Or a handbook of company processes? Since this is information that your company wants to share with employees, partners, customers and more, it’s a great thing to read for inspiration. You’ll be pleasantly surprised how many intents you can find in a basic About-CompanyX.pdf.

Identify the manual processes

Chatbots exist to automate repetitive tasks. Basic manual processes inspire some of the best intents and future conversational flows.


A common manual process is data capture. You can easily put the bot in charge of collecting and updating user data, so that your human colleagues can focus on more complex tasks. Managing appointments, routing to the right queue and sending reminders are other processes that a chatbot can easily take over.

Turn user questions into chatbot intents

Questions and intents are similar, but not the same. A question is literally what your user asks, while an intent is the purpose of what your user asks. For example, a user asks Hey Google! What’s the number for Amy’s Pizza? The Hey Google… is the question, but 01-restaurant-contact-info is the intent.

When scoping a chatbot make sure you understand the difference between question, intent and response

Transforming a question into an intent isn’t always easy. The key is to capture the essence in one to three words. A good rule of thumb is that if your intent doesn’t fit on a post-it, it’s too long.

Choose the best intents

Now that you have a collection of possible intents, it’s time to decide which intents will have the largest potential impact and therefore, the highest priority. For a pilot project, we recommend starting with ~20 intents. It’s always better to get a small set of intents working well before making a dumpster of half-understood intents.

Look for the trifecta

The best intents are the ones that are repetitive, easy to recognize and easy to answer. When you find this trifecta, put this intent at the top of your implementation backlog.

Repetitiveness, recognizability and easiness are the trifecta for choosing intents to include in your chatbot's scope

But how do you know if you have a trifecta? We use a systematic framework to visualize which intents will have the largest potential impact.


Recognizability: Can a bot easily recognize this intent? Is it clear and unique, or very vague, or similar to other intents?

Repetitiveness: How frequent is this intent? Will it be triggered 200 times a day or twice a day?  

Easiness: How simple or complex is it to implement this intent? Do we need to use APIs, create a microservice, etc.? 


Review each intent and give it a score from 1-10 for recognizable and repetitive (1 being the least and 10 being the most). Then give the intent a score from 1-5 based on how easy it’ll be to implement (1 being the easiest and 5 being the most difficult). 


Now it’s time to map each intent on a graph; recognizability is on the y-axis and repetitiveness is on the x-axis. Once you have the coordinates for an intent, mark it with its easiness score.

A cluster in the top right quadrant will appear. These are the intents that you should prioritize for your chatbot. Start with the easiest intents to implement, and then work your way up through the more difficult ones.

How to decide which intents to include in your pilot chatbot's scope

Any intents that don’t make the list for the pilot should go on your backlog so that you can pick them up to include in future releases. 

A chatbot’s knowledge isn’t static

Launching your bot is only the beginning. This is one of our favorite diagrams of all time because it’s so simple, yet so accurate 👇

How people think a bot works vs. how it actually works

The best source of new intents for your chatbot comes from its users. Once your bot is live, take time to review the incoming conversations. This allows you to make sure that the bot’s recognizing existing intents correctly and to see what other questions users ask that are currently not in scope. 


Look for patterns and figure out how the bot could answer that question instead of putting it in a not understood flow. Your priority should be to make every experience a neutral or positive experience for the user. Looking at the missed questions gives you all the necessary information to increase your bot’s knowledge. The best bots grow continuously and are updated regularly to answer actual user questions. 

5 ways to use conversational artificial intelligence in banking

5 ways to use conversational artificial intelligence in banking

5 ways to use conversational artificial intelligence in banking
It’s no surprise that the financial industry is perfect for applying artificial intelligence (AI)– banks, crypto companies and financial institutions have thousands of customers who use their services multiple times a day.

We often receive the question from prospective banking clients: How can we use conversational AI? Here are 5 of the best ways to implement conversational AI in banking, insurance and crypto companies.

Customer support

Setting up a chatbot to answer repetitive customer questions such as: What is the BIC code?  and Where can I find my routing number? is a no-brainer for any bank.

These questions come in at high volumes, they’re easy to recognize and the answers are relatively simple– usually, a short text, link or image can answer the user’s question. Let’s assume that What is the BIC code? represents 5% of the incoming questions. If you use a bot to automate that answer, you reduce your incoming question volume by 5%. FAQs are a great area to start with for your MVP (minimum viable product) because even with a small scope of ~20 intents, you can immediately experience the benefits of automation by reducing the volume of incoming questions and the time spent by your customer support agents answering them.

Plus, most customer support tools (Sparkcentral, Zendesk, Freshdesk, etc.) have out-of-the-box connections to chatbot building software, so you can keep your existing technology stack. BTC Direct’s Toshi and KBC’s Kate are two of our favorite customer support chatbots automating conversations in the financial industry.

Data capture

Another area where banks tend to lose a lot of time is during data capture flows. Many financial procedures require additional information before completing a request. Sometimes asking for a user’s name, birthday and email can take up to 10 min. By using a virtual assistant to automate the data capture, you avoid having your agent wait for the customer to respond and the customer wait around to have the agent ask the next question. It’s a win-win for both sides!   Some typical baking processes that require additional information and could benefit from automated data capture are:
  • Raising daily limits
  • Requesting a new card reader
  • Ordering foreign currency
  • Canceling or blocking a card
We’re probably biased, but Argenta’s Charlie is our favorite example of automated data capture in a banking app. Another great example is Belfius’s myBo.
Argenta's chatbot Charlie answers user questions

Financial transactions

Forget logging into an app or, even worse, opening your computer. Encrypted messaging apps, like WhatsApp, Signal and Telegram make checking your balance, paying bills and transferring money between accounts easier than ever. And the best part? Customers can use an app they already have instead of installing a new one!


Check out Capital One’s Eno and Rawbank’s Rawbot to see how they use conversational AI to execute financial transactions.

Filing insurance claims

Filing an insurance claim is never a fun process. But it’s even worse when you don’t know what to do and have to wait for someone to help you. Developing an insurance claims chatbot is one of the more complex implementations, but the time saved and improved customer experience make this a huge cost savings opportunity in the long run. Instead of spending hours processing a single claim, AI automates the complete data capture, so a claims agent only needs to spend a few minutes reviewing the case.

We can also use AI to detect fraudulent language and build flows within the chatbot that stop users from submitting fake claims or adapting existing claims to increase their insurance payout.

For an excellent implementation of an insurance claims chatbot, take a look at Belfius’s myBo.
Belfius insurance claims chatbot

Coaching and budget management

Chatbots make great coaches for many reasons: they’re always on time, they never tire of nagging and most importantly, they don’t judge. We’re human, and sometimes we need a (not so) gentle reminder to keep ourselves in line, especially when it’s about budget management. Sticking to a budget and reaching financial goals, such as saving for a house or retirement, require constant discipline.

Building a coach-like virtual assistant is one of the most challenging implementations because it requires integrating with your bank’s infrastructure and security requirements, engineering If This, Then That(IFTT) triggers and preparing for how the bot will handle conversations outside its scope.

Our personal favorite is Cleo. She’s sassy, honest and just the kind of girl to help keep your spending habits in line. If you want something a bit more traditional, check out Hope.
Cleo chatbot

What is conversational banking?

What is conversational banking?

What is conversational banking
Conversational banking is exactly what it sounds like: it’s when a financial institution uses conversational AI to answer banking and insurance questions. Put simply, it’s a bank’s chatbot.
Conversational banking uses natural language processing (NLP), which is a fancy way of saying AI for words. Like any other chatbot, we built the NLP model using intents, expressions, entities and flows.

When a user asks a chatbot a question, we refer to that as an expression. For example, the user asks, “How do I cancel my credit card?” The bot processes the user’s expression and compares it to the different expressions within its NLP model. Each expression within the NLP model is associated with a specific intent, or answer to an expected question. The bot then assigns a confidence score to each intent, and based on the different thresholds and rules that we define, it responds to the user with the appropriate answer.
A look into how a chatbot assigns confidence scores

A look into how a chatbot assigns confidence scores

Why is conversational AI interesting for the banking sector?

Banking is the perfect business case for conversational AI because banks and insurance providers have thousands of customers who use their services multiple times a day. This inevitably leads to problems that need solving and questions that need answering. Most of the incoming questions are repetitive, easy to recognize and easy to answer. This is the trifecta for conversational AI automation, making it a win-win for banks and customers.

Benefits for banks

💾 Save resources

On average, banks implementing a basic chatbot save between 10-20% of an agent’s time. The customer support agents can repurpose their saved time to focus on more complex cases that need human attention.

❌ Reduce human error

Humans make mistakes; it just happens sometimes. Whereas a chatbot follows standardized, pre-programmed logic, making it almost impossible to make mistakes.

🤳 Interact with customers where they are

A chatbot can live almost anywhere: on your website, in your app, WhatsApp, Instagram, Twitter, etc. By placing your chatbot where your customers already are, you widen your customer reach and reduce the barrier to connect.

💸 Focus on upselling

Instead of spending time answering the same question 20 times a day, a customer support agent can delegate these types of tasks to a chatbot. They then have the time to focus on resolving complex client issues and upselling clients.

Benefits for customers

⚡ Instant answers

A chatbot is available 24/7 and can answer a user’s question in seconds. This is a significant contrast when compared to more traditional question-and-answer approaches. For example, think about when a customer had to wait on the phone line for 10-30 minutes for a representative to pick up or send an email and wait a few days for a response. With a chatbot, your customers ask whenever is most convenient for them and they receive an instant response. There are no opening hours, no queues and no waiting times.

🎯 Personalized experiences

It’s easy to connect your chatbot to your CRM system. This allows you to identify your customers and tailor the conversation to their needs and profile. For example, if you’re logged into your banking app and trying to file an insurance claim, the bot can look up your existing policy and respond with an answer tailored to your insurance policy. Each user’s experience with the chatbot is customized and unique.

💬 Interactive communication

It’s much more enjoyable and efficient to have an interactive conversation rather than trying to fill out a form that doesn’t allow you to express your problem or fighting with an IVR system that doesn’t understand your request. Chatbots are flexible and trained to solve problems and answer questions.

🔮 Omni-channel accessibility

We can place a chatbot on almost any channel, making it much easier for your customers to connect with you via the channel that they prefer. This allows them to seamlessly switch between channels and makes it a more convenient experience for everyone.

What are the best use cases for conversational banking?

Like any other industry, a chatbot can support all types of departments and roles. Here are some different implementations for banking chatbots:
  • Answer frequently asked questions
  • Sell new plans and upgrades
  • Register and onboard new clients
  • Remind users of upcoming payments and deadlines
  • Coach and motivate users to stick to their budget and savings goals
  • Request a new card reader
  • Raise your daily limit
  • Plan your budget
  • Check your balance
  • Make a transfer
  • Pay your bills
  • File an insurance claim

If you’re eager to dive deeper into some actual business cases, check out our work for Argenta and Rawbank.

What’s next?

Banks will inevitably continue adopting conversational AI to automate frequently asked questions, execute transactions and streamline processes. Financial institutions that don’t make this switch won’t be able to sustain the increasing volume of incoming questions and remain competitive. 

Are you interested in implementing a chatbot at your company? Reach out to Alexis for a quick chat.