The obligatory GPT acknowledgment

There’s a couple different elements that I pull into the solar system of consulting: primarily, I love thinking about & working with clients to help them understand what they actually want, and how to better work together. This often turns into explorations around process (or lack thereof) and priorities, and how to frame decisions so they’re more likely to produce what clients actually want, not just labor and `git` commits.

So far, as best I can tell, GPT and friends aren’t especially helpful at this:

[SYS]: You are a helpful assistant.

[ME]: How can I use the principles of solution-based brief therapy to help a business leadership client understand their own values and priorities?

[AI]: Great question! Here are some steps you could take to help your business leadership client understand their own values and priorities using solution-based brief therapy principles:

  1. Identify the client’s goal: Begin by clarifying with the client what they hope to achieve from this session. What is their desired outcome?

  2. Explore exceptions: Ask the client to identify times when they felt they were living in alignment with their values and priorities. This helps the client recognize that they are capable of living in alignment with their values.

  3. Identify strengths: Help the client identify their personal strengths that have helped them achieve their past successes.

  4. Identify the client’s values and priorities: Ask the client to identify what is most important to them in their work and personal life. You can ask questions like “What do you value the most?” or “What brings you the most joy and fulfillment?”

  5. Help the client examine their actions: Encourage the client to examine how their values and priorities are reflected in their actions. Are their actions consistent with their values and priorities?

  6. Reframe the problem: Reframe the problem from what’s wrong to what’s right. Ask the client what they would like to have more of in their work and personal lives.

  7. Focus on the future: Ask the client to identify what their ideal future would look like, and work together to create a plan for achieving that future.

Through these steps, you will help your client understand their own values and priorities in aligning them with their work and personal life goals.

(GPT loves lists. Loves ’em.)

That’s not terrible, but it’s not actually helpful, either. The language is dry, and the information isn’t at all adapted to people’s needs. (Another attempt at generating from this prompt led with suggesting using “The Miracle Question”, which is rarely appropriate for clinical clients, and probably never in the business consulting context.)

All that is to say: there’s not much actually usable there. It could help with outlining. Someone with passing familiarity with SFBT could write something like that without referring to any outside documentation. We might see all this change in the near future–but right now, today, this isn’t an exciting use case.

I also happen to be familiar with a few programming languages. And, boy, is that a different use case:

[ME]: Please create a new application in Ruby on Rails. The application allows a user to log in, select a donation amount from the set $5, $10, or $20, and then proceed to pay my account that amount using Stripe.

[AI]: Creating a complete Ruby on Rails application with Stripe integration is beyond the scope of this text-based platform. However, I can provide you with a high-level overview and some code snippets to help you create the application yourself.

…and then proceeds to generate code for your views, controllers, Stripe integration configuration and implementation, client-side JS, and so on.

You may not be able to use it right out of the box, but that’s a lot of documentation and API references that you don’t have to look up and toy with.

The generalization (from, granted, n=2 here) is that this tool isn’t super at replacing humans entirely, but it’s fabulous for accelerating work where you have a lot of boilerplate or external-to-your-cranium knowledge that needs referencing.

I’m excited to see how teams start to restructure and shift processes to respond to this different balance. Experimenting is a lot cheaper than it was a few months ago; will we see folks shifting implementation earlier than research and task definition?

Did that make your day a little better?

I write every weekday, and many weekends. Subscribe here and you'll get new posts straight to your inbox, just like that.

    We won't send you spam. Unsubscribe at any time.