Just last week we attended Beyond Conventions in Essen participating in a pitch challenge competing to build a HR Chatbot for Thyssenkrupp. This event, amongst many others is proof that there is definitely the need of coming up with new ideas and innovations to stand out as an employer between all of the sought-after qualified employees. Companies understand that they need to be present and active on all social media channels in order to do a great job in employer branding. As generations Y and Z are coming of age and ready to enter the business world, it’s becoming more and more natural to inform themselves about career opportunities not only via Website but also on Social Media such as writing on Facebook Messenger to those companies. We are going to publish a series about demos, concepts, insights, and much more regarding HR chatbots.
In this blog entry we will explain the showcase we have developed with our HR chatbot pitch for Thyssenkrupp. You will get to know how to set up one of many application processes within Facebook Messenger. This process will include collecting information on candidates, asking screening questions as well as ranking the candidates.
Step 1: Selecting a job
- First of all you have to create an intent which starts the application process. This should also be integrated as a Quick Reply (Button) in the Navigation.
- The next step is to integrate a job board as a webview of the specific website so users can select their preferred job they want to apply for.
- So how does the chatbot know which job was selected by the applicant? Firstly, all website URLs of the job listings need to be whitelisted on Facebook. Then just by integrating the messenger extension SDK on the website, we can enable the communication between the bot and webview. So when the user clicks on a button e.g. “Apply now” within the webview, an action can be triggered which can close the window and send the job which the user wants to apply for in parameters to the chatbot.
Step 2: Collecting information
- The first step is to ask the applicant for the resume or other relevant documents. It’s important to know that the users are not able to upload a PDF file on Messenger via mobile. It can only be accomplished through desktop. However, you could also offer them to upload an image or a screenshot of their resume. This obviously needs to be communicated clearly in advance to the user.
- Once the applicant has uploaded the files, we recommend integrating an API which can automatically extract all information such as contact details about the candidate. For instance, we are using the Vision API by Google to extract the text from the uploaded image and then we look for specific entities via Google’s NLP APIs to find the particular information. You can also implement a method asking for missing information when someone forgets to state them in their documents (see example picture).
Step 3: Asking screening questions and ranking candidates
Asking screening questions
The third step is to actually see if the candidate is the right one for the position by testing how well he/she fits the job requirements. In this case you can already use existing requirements from the job listings. This sounds like a lot of work when you have to insert all of the requirements from thousands of job listings into the chatbot, but there is actually a very scalable way to automate that. Just by integrating an API into a CMS or any other system where information is stored, you can instantly utilize them in the chatbot.
To be able to rank the applicant, you can create a scale ranging from 1 to 5 where the user has to select a number on how well he/she fits the requirements. Choosing a 5 means that the candidate fits the requirements by 100 % and picking a 1 obviously the opposite. After the candidate has answered all screening questions, the chatbot will calculate a score in the background on how well the job fits to his/her qualifications and skills which gives the recruiter the chance to compare applicants. By the way, it is also possible to give certain requirements a different weight into the score calculation. For instance some demands might be more important than other ones e.g. 5 years experience in programming could be more crucial than a degree in computer science with a scarce background.
In the last step of the process, the user is being asked in a personal video from a recruiter to upload a video of him/her explaining why he/she would like to work for the company (or any other question which could be in regards to the companies cultures and values). This creates a personal experience for the potential employee which can also lead to a unique branding effect. The candidate’s video presents the perfect opportunity to provide a good impression and to show if he/she is a good fit for the company.
Step 4: Integrating the chatbot application into the regular recruiting process
After the user finishes the process, the chatbot will gather all information (see image above). Now, there are various ways on how to handle received applications. It can be either directly sent to a recruiter via email or integrated into an application tracking system (ATS). The score given through the screening questions could help the recruiter prioritize applications.
I hope this provided you with a great insight on how an application process can be created for a chatbot. There are obviously many other ways on how to set up the process. Please share your thoughts in the comments below on how it can be improved or optimized. This was also the first blog entry on HR chatbots. Stay tuned by subscribing to our newsletter for more input!
Michelle Skodowski is a co founder of BOTfriends with a primary focus on chatbot design and UX. However, as the CMO of the company, she is not only in charge of marketing & PR but also HR & Recruiting. She has also spoken at various events such as the Google Cloud Summit or the Hashtag.Business. As she was bootstrapping the startup, she managed to graduate at the University of Applied Sciences in Würzburg in E-Commerce and had the great chance to work at companies such as eBay or Bosch Rexroth along her study.