AI Therapists: Self Reflection With AI

April 2025

“I am not ready for this conversation.” We all know that feeling. The endless mental rehearsal. The anxiety building with each imagined scenario.

But what if I told you that AI could be your practice partner for both difficult conversations and deeper self-reflection?

AI as a therapeutic practice partner


The Power of One Question at a Time

The approach is remarkably straightforward. When you need to prepare for a challenging conversation or understand your own hesitation, start with one of these prompts:

“I need to have a difficult conversation with [person] about [X]. Asking me one question at a time, help me to prepare.”

or for self-reflection:

“Asking one question at a time, help me think through step by step why I am feeling [emotion] about [situation].”

The beauty lies in its simplicity. Each question creates space for deeper understanding.

A Personal Example: When Sending an Email Feels Overwhelming

Recently, I found myself hesitating to send an important email to a mailing list. A simple task, yet I felt inexplicably nervous. Using the self-reflection prompt, I discovered something surprising.

My reluctance had nothing to do with the email itself. The real fear was about what would happen after sending it. The responses would require me to step further outside my comfort zone. Through this questioning process, I uncovered that I was still carrying grief and loss from work-related events from the previous year.

This realisation was powerful. These were not valid reasons to avoid action. They were old wounds masquerading as current limitations. Once I understood this, I could send the email with confidence.

Why This Approach Works

The deliberate pace forces you to think deeply about each response. There is no rushing. No surface-level thinking. No AI doing your thinking for you. Most importantly, there is no avoiding the uncomfortable aspects of either the conversation or your own feelings.

Understanding Multiple Perspectives: Through targeted questions, you will develop a deeper understanding of the other person’s viewpoint. This is not about preparing a script but about truly comprehending the various angles of the situation.

Clarifying Your Objectives: What do you actually want to achieve from this conversation? Often, the process reveals that our initial objective needs refinement or that we have multiple goals that need prioritising.

Identifying Potential Challenges: By working through scenarios with AI, you can anticipate possible objections or concerns. This is not about creating counterarguments but about understanding valid concerns that deserve consideration.

Building Your Evidence Base: The questioning process helps you identify where you need more concrete examples or data to support your position. It reveals gaps in your preparation that you might have overlooked.

Refining Your Approach: Each iteration of questions and answers helps you refine how you will present your thoughts. The AI never tires of helping you explore different approaches until you find one that feels authentic and effective.


We often hear that breakthroughs are just “one awkward conversation away.” Sometimes that conversation needs to be with ourselves first. With AI as your practice partner, you can prepare for both external discussions and internal reflection thoroughly and thoughtfully.

The next time you find yourself rehearsing a difficult conversation or avoiding action due to unclear feelings, stop. Open your favourite AI tool, type out one of these prompts, and begin a more structured and productive process.

Remember, the goal is not to script the perfect conversation or find the perfect answer. It is about understanding more deeply. Each question brings you closer to that understanding, and with it, the confidence to move forward effectively.


More articles

Introducing Kaijo: AI functions that just work

kaijo

For months, I have wrestled with a problem that has consumed my thoughts and challenged everything I know about software development.

This week I wrote about building the future with AI agents. One of the key areas for me is moving beyond prompt engineering to something more reliable.

I have spent decades learning how to craft reliable software. Now I want to bring that reliability to AI development.

Today I am ready to share what I have been building in the background.

It started with a game. It ended with something that could change how we build AI applications forever.

Read more

Building the Future

A diagram of the future of AI agents

Something has been on my mind for months. The rapid evolution of AI agents has opened up possibilities I cannot ignore.

We are witnessing the emergence of semi autonomous agents that will fundamentally reshape how we work and communicate. The opportunities in this space are extraordinary. I am diving deeper into this world of AI agent development and product creation.

My newsletter is evolving. Instead of dispensing tips from a position of authority, I invite you on a journey of discovery. I will document my experiences building with AI, how to apply my tech experience in a new world, and navigating the inevitable struggles and setbacks.

Read on for several key areas I am exploring.

Read more

The Reality of AI Power Usage

AI Power Usage

AI power usage generates significant controversy. Headlines paint it as an environmental catastrophe waiting to happen. The reality proves more nuanced and potentially more optimistic than these dire warnings suggest.

A ChatGPT query uses 10 times more energy than a Google search. This sounds alarming until one realises it equates to running your hairdryer for six seconds. The entire data centre industry, including all AI operations, accounts for just 1.5% of global electricity consumption.

Here is a rundown of the more pressing issues with AI power usage.

Read more

Coding with AI: How To Do It Well And What This Means

I am shipping AI-first production code every day. Not experimental features. Not throwaway prototypes. Real, deployed, mission-critical code powering Cherrypick’s tens of thousands of users.

Social media overflows with “vibe coding” demonstrations. These flashy but superficial examples show AI apparently conjuring perfect code in seconds. The reality of professional AI-assisted development runs much deeper. Real production work with AI is messier, more nuanced, and demands rigorous thinking, but very effective.

This is not about magical code generation. It is about a new way of thinking about development. It requires substantial real-world development experience to do well: the onus is upon those of us with this experience to teach the next generation how to harness these tools effectively.

This is how I am doing it, what it all might mean, and how we can help others find the way.

Read more

Prompting Sucks (And What We Can Do About It)

Prompting sucks. If you have spent any time working with LLMs, you already know this.

It is not just that prompting is difficult - it is fundamentally broken as an approach to working with AI. It is brittle, model-specific, and endlessly repetitive.

Here is why we need to move beyond prompting, and what we can do about it.

Read more