How an HR team can break free from routine with the help of AI

Previously, we learned how to write personalized emails to candidates faster using the ChatGPT-based email generator. We did this with podbor.io (platforms for finding IT specialists). This experience has been described in detail. Here. In short: we succeeded. We reduced the time for writing personalized emails and inspired the decision to test AI tools on other routine processes. After all, volumes are growing, but the number of hours in a day is not increasing. More automation for the god of automation!

In the experiment that I want to talk about in this article, we formulated several hypotheses and selected two of them as the most priority for us:

1. If the AI did well with letters, then it will also cope with boolean queries? Recruiters spend a lot of time putting together complex queries that have various operators and keywords to filter their search results. Can we significantly reduce this time without losing quality?

2. AI, speed up the process of editing job descriptions for us, please! A well-crafted job posting is a big part of attracting the best candidates. In the sea of the same type of vacancies, it becomes more and more difficult to keep the attention of a candidate. At the same time, recruiters have little time to write a catchy job description without using formulaic phrases. Can ChatGPT speed up the process of writing a job description that the candidate won’t pass by?

So we checked.

Case #1. We learned how to write boolean queries using a chatbot based on ChatGPT

In case you haven’t used boolean queries before: *Boolean search is a search method that uses logical operators to get more relevant search results on websites and social networks.

Many recruiters are aware of the existence of this tool, but not everyone is familiar with its capabilities or may make mistakes when using it. We decided to check how a chatbot based on ChatGPT writes such requests.

Examples of boolean search queries may include the use of the “AND”, “OR”, and “NOT” operators in combination with keywords and phrases. For example:

“software developer” AND “at least three years of work experience”
“sales manager” OR “marketing specialist”
“engineer” NOT “trainee”

We used an AI-based chatbot, which was given the request “write a boolean query to search for a resume on HH.ru. DBA with PostgreSQL, Linux (Ubuntu), Ansible, Bash, Shell (scripts)”:

Result:

Chat can write boolean queries to different resources, we tried several. Here are examples of issuing a request for LinkedIn and Zen:

Result:

It turns out that AI coped with this task quite successfully.

Case #2. We learned how to write vacancies using a ChatGPT-based chatbot

A well-crafted job posting is the key to attracting the best candidates. Often recruiters have little time to write a catchy job without template phrases. We tried to generate new vacancies using a chatbot based on ChatGPT.

You work, you work, and then – bam! – You receive a vacancy from the head of the development department with a brief description: we are looking for a kind, energetic and cheerful person who knows JavaScript perfectly, like his native language, and has a passion for travel. We need a real adventurer!

The customer does not have time to dive into the details of the vacancy. From these inputs, you must write an attractive job advertisement, and do it quickly, because the vacancy needs to be filled “yesterday”. Has it happened?

After the AI tool coped with the boolean requests, we decided to try to give it this process as well.

With the help of the chat, we can create job templates and receive a generated text based on the entered parameters and requirements.

For example, you can set the following options:

Job Title: web developer
Requirements: knowledge of HTML, CSS, JavaScript
Work experience: from two years
Responsibilities: Development and support of web applications

Based on these parameters, the chatbot generated a job description, which we can edit and modify at our discretion. This saves time and simplifies the process of creating job descriptions from scratch.

What conclusions did we draw:

In these cases, the main goal was achieved – automation of writing vacancies and compiling Boolean queries.
Often the bot wrote boolean queries, where the output was zero. But by gradually simplifying Boolean queries, we expanded the distribution funnel and still saved time.
Chat will write the text for you, but keep in mind that you still have to edit it.
The more inputs you give to the bot, the more beautiful and correct the text you want will be displayed.
We will definitely continue to use AI tools in our processes (and will be happy to share our experience with you later).