Leadership co-processing with LLMs
In the rapidly evolving landscape of AI, it is refreshing to see perspectives on Large Language Models (LLMs) that go beyond coding assistance or virtual companionship. James Stanier, in his post for The Engineering Manager, provides a look at how leaders can use LLMs as a “co-processor” to enhance their thinking and decision-making.
He frames the core idea as follows:
Effectively, I now think of LLMs as a co-processor for my brain. It isn’t always correct or even trustworthy, but in practice it always puts momentum behind my thinking, and often helps me to see things from a different perspective.
Stanier outlines several practical techniques for integrating LLMs into leadership workflows:
- Prompting: Using simple prompts to inject momentum into problem-solving and overcome the initial friction of a blank page.
- Pair Prompting: A collaborative method where two people use an LLM as a third member of the team to work through a problem, documenting the entire thought process.
- Deep Research: Leveraging the LLM as a research assistant to explore topics in depth, saving significant time.
- Contrarian Thinking: Employing the LLM to challenge assumptions and identify personal biases, leading to more robust decisions.
- The Executive Assistant: Using the LLM to prioritise tasks and structure the day, especially during busy periods.
- The Coach and Sounding Board: A way to process thoughts and reactions to complex situations in a structured, two-way dialogue.
This perspective is valuable because it focuses on augmenting, not replacing, human thought. I particularly liked the concept of “pair prompting,” where the tool facilitates a richer, documented collaboration between two people.
Pair prompting is just like pair programming, but with an LLM as the third member of the team. The idea is that you and your partner can use the LLM to help you both think through a problem together, and it can help you to see things from a different perspective.
In my day-to-day work, I also use LLMs for many non-coding tasks. Beyond basic grammar and spelling checks, I use them to navigate complex situations. By using pre-set prompts based on principles like those from Michael Pilarczyk, I can more quickly find a path to a decisive, well-considered action.
Of course, it is crucial to remain critical. An LLM does not have the full context of a situation, nor to all of your thougths and ideas, so its output must be adapted and validated against your specific circumstances.
The full article by James Stanier offers more detail and example prompts. You can read it on his Substack: Leadership co-processing with LLMs.
