Could An AI “Bot” Demonstrate Emotional Intelligence As Your Coach? I Think Yes.
Last month (February 2023) I published an article suggesting that within 5–7 years generative AI technology would likely be advanced enough for leaders to have their own personal executive coach that is 100% non-human. An AI chatbot device. A droid.
“Interesting,” some readers and colleagues noted, “but c’mon, do you really think that a non-human entity, a thing that doesn’t have emotions, could be an effective coach, since demonstrating emotional intelligence (EQ) is a foundational skill for good coaching conversations?”
It’s a good point and it’s one that underlies the premise of this commentary piece. And that answer is yes!
The rationale is this: Though I believe that while at least for the foreseeable future AI engines will not have the capacity to actually “feel,” they could still use emotional intelligence principles effectively because there is a cognitive component to EQ. A coach-bot would not have to use or even have emotions in order to use emotional intelligence principles in a conversation.
This same point can be made about humans. If you’re knowledgeable in EQ principles and techniques and know what to look for and listen for in a situation, you can engage with others in a genuinely emotionally intelligent way.
As I did for my previous article to explore current AI capabilities, I used the very popular chatbot Chat GPT to ask for a script that I could use in a mock coaching conversation, one that would employ emotional intelligence methods. I’ll share the unedited dialogue below to advance my point of view. Spoiler alert — the bot used EQ talking points that were as good or better than any human could have responded, and I’ve had hundreds of very capable managers participate in EQ training classes I’ve conducted over the years.
Emotional Intelligence (EQ) Defined
But first, perhaps a quick recap of the definition of EQ and its components would ensure that we’re all generally talking about the same thing. While there are several related definitions of EQ, perhaps Daniel Goleman’s are known best by students and practitioners of emotional intelligence.
Goleman defines emotional intelligence as “a person’s ability to manage their feelings so that those feelings are expressed appropriately and effectively.” For him, the five factors of emotional intelligence are:
- Self-awareness (“Know thyself”)
- Self-regulation (Impulse control)
- Internal motivation (Being “inner”-driven)
- Empathy (Understanding the emotions of others)
- Social skills (“Active” listening and other communication skills).
As a side note, in the many management training sessions I’ve conducted on EQ, participants overwhelmingly indicated that for them, empathy is the most difficult skill to regularly practice. In a conversation, demonstrating empathy often forces people to slow down to test for a read of emotions. Using empathy can also take the conversation to a deeper level of connection. But neither of those empathy by-products are usually top of mind in the heat of problem-solving or issue resolution.
But all elements of EQ are skills that can be learned — including empathy — if someone is seeking a successful outcome in a conversation and chooses to use an EQ-laden approach. The statement “It sounds like you don’t think you’re being supported by the rest of the team…” is a demonstration of empathy. It simply takes discernment and discipline in knowing when and how to use empathy and other EQ skills in an effective way.
Humans can and do learn those skills even if emotional intelligence seems to them like an unnatural act. Employing the head (cognitive) rather than the heart (emotions) can still be effective.
So, an AI-powered coach-bot cannot tap into the “heart” as a source for EQ behavior but is very well equipped to use the “head” and thus can exercise both discernment and discipline without having the requisite emotions.
In the 2021 article titled “Will Alexa 4.0 be your leadership coach of the future?” I suggested how a future bot-coach might pick up physical/physiological clues from the coachee that could provide insight into the coachee’s emotional situation.
“During the conversations, Pat [the coach-bot] might ask why you got slightly emotional with one of your responses. You see, Pat has access to even your most subtle physiological changes in heartbeat or breathing rate. Thanks to the rise of the Internet of Things (IoT), the physical sensors woven into your clothes and embedded in your jewelry are sending constant streams of data about you. After a few days, Pat will know which words or situations will elevate your positive state or, conversely, bring you down.”
That physiological “read” by the coach-bot would be just as revealing as a psychological “read” from an astute human. The cognitive computing powers of the bot would more than compensate for the lack of an emotional reservoir upon which to understand another’s emotions.
Chat GPT Coaching Script
Here, then, is the verbatim script created by Chat GPT in a matter of seconds to my prompt.
My Prompt: I need to coach a subordinate on a performance issue using emotional intelligence methods. Can I get a script?
Chat GPT Response
Certainly, here is a script that you could use to coach a subordinate on a performance issue using emotional intelligence methods:
Hi [Subordinate’s name],
I want to take some time to talk to you about an issue that has come up with your performance recently. I want to start by acknowledging that you have a lot of great skills and qualities that you bring to the team, and I value your contributions.
However, there have been some concerns about [specific performance issue]. I want to work with you to address this and help you succeed in your role.
Before we get into the details, I want to make sure that you feel comfortable and heard. How are you feeling about your performance so far? Do you have any concerns or questions that you’d like to bring up?
[Listen actively to the employee’s response, and try to understand their perspective without judgment.]
I appreciate you sharing that with me. I want you to know that I’m here to support you, and I want to work with you to find a solution that works for everyone.
Now, let’s talk about the specific issue at hand. I’ve noticed that [specific example of the performance issue]. This is important for us to address because it can have an impact on [specific consequences of the issue].
I’d like to work with you to come up with a plan to address this issue. What are some ideas you have for how we can improve in this area?
[Listen actively to the employee’s ideas, and provide feedback and guidance where necessary.]
Thank you for sharing those ideas with me. I think they’re great starting points. Here are a few other suggestions I have based on my experience in this role [provide specific suggestions and guidance].
Let’s work together to develop a plan to improve in this area, and set some specific goals and timelines for improvement. I want to make sure that we’re both on the same page and that you have the support and resources you need to succeed.
Is there anything else you’d like to discuss or any other questions you have?
[Listen actively to the employee’s response, and provide any additional support or resources as necessary.]
Thank you for taking the time to discuss this with me. I appreciate your dedication and commitment to our team, and I’m confident that we can work together to improve your performance and achieve success.
Remember, it’s important to approach the conversation with empathy, active listening, and an open mind. Emotional intelligence is all about understanding and managing emotions, so try to keep the conversation positive and supportive. By working together with your employee, you can help them improve their performance while also building a stronger, more productive working relationship.
Evaluating the Script
The chatbot’s suggested coaching script and ending summary capture the EQ principles advocated by Goleman and others in a way that is simple yet elegant. Realistic yet aspirational. It’s a very well-executed coaching exchange and can serve as a useful template or crib sheet for a human manager preparing for the conversation with the team member.
But it also demonstrates an exchange that can occur between an individual and their own bot-coach when that person knows they have a performance challenge and they want to resolve it and pre-empt the need for a coaching conversation with the boss. It’s like sitting down over a cup of coffee with a trusted and helpful colleague and talking through a solution. Except in this case, the colleague is a set of microchips and does not drink coffee.
We are only at the front end of this AI-enabled chat technology and it is both exciting and a little frightening where it might take us. And it might be a job security issue for a lot of executive and business coaches.
About the author: Mike Hoban is a business topics writer. He is actively working at becoming a world-class grandpa to his five young granddaughters. In addition to his 40 years experience as a leader, consultant, executive coach, and business owner he has also published extensively in Fast Company and wrote many thought leadership pieces for DDI when he was there. He also wrote a business column for 12 years. His many commentary articles can be found on his LinkedIn page: https://www.linkedin.com/in/mike-hoban-b5756b6/ He can also be reached at mjhoban99@gmail.com.
