How to use Generative AI like a Strategy Consultant

ChatGPT has changed the game for many professions. None more so, perhaps, that in the consulting world. Strategy consultants, especially at the “lower” level of the pyramid, are expected to find information and offer scenarios to solve issues within companies (this is a wild over-simplification, but tracks based on experience).

This becomes much easier to do when you have a generative AI tool that can answer questions, act as a sparring partner, or organise large amounts of data. Of course, there may come a time when the role of strategy consultant altogether disappears because of large language models. But in the meantime, tools like ChatGPT augment our skills; they do not replace them.

Below is a few tips and tricks to use ChatGPT like a strategy consultant, and provide value in your role.

ChatGPT prompts for consultants

Just as an Analyst needs to learn PPT and Excel shortcuts, one now needs to know the easiest and best ways to use ChatGPT to optimize their work. Obviously, this in no way replaces the grunt work that needs to be done for clients… but it can often be a helpful start.

Highlight obvious areas of improvements

“I am a consultant. I am working on a project to [define project’s nature]. I wrote the text below for [audience]. Please point out possible areas of improvement to make it more impactful.”

HINT: Always say please to the AI; just in case

Summarize meeting / interview minutes (ex: in bullet-points)

“I am a consultant. I am working on a project to [define project]. Summarize the below notes in easy-to-understand bullet points, highlighting the pain points and key take-aways.”

Mass title production

“I am working on a sub-project with 3 streams: [Stream 1], [Stream 2], [Stream 3]. Give me 20 possible titles for my project”

HINT: ask for longer lists, more professional lists…

Categorisation

“I have hereafter listed 20 success factors for my project: [factor 1], [Factor 2], [Factor n]… Categorise them in 3 different categories, and write a short definition of each category.”

Find something you’ve missed

“I am working on [topic]. Below is a list of 10 ideas I’ve had to answer [problem statement]. Please give me 10 more ideas. [Paste existing ideas as bullet points].”

Find quotes and examples

“Can you give me some data and quotes from business leaders to support the below statement? [Paste statement that supports your analysis].”

WARNING: only works for Bing, not ChatGPT

Find metaphors / ELI5

“Please explain [complicated concept] like I’m 5 years old. Use metaphors if possible”

HINT: ask for more than one example, and use different ages

ChatGPT for consultants: 10 commandments

While ChatGPT is very useful, there are easy mistakes that should be avoided. The most obvious one is that you should not tell your client you are using ChatGPT. They are paying good money for a service, and your shortcuts are for you alone to know about. Below are 10 more things to keep in mind.

Thou shalt not use ChatGPT like Google — don’t use it to search for information; that’s not the point
Thou shalt not use it for specific examples — it’s a “good enough” type of tool
Thou shalt validate and verify — ChatGPT “lies” all the time (hint: use chain of thought prompting to spot errors)
Thou shalt understand the underlying statistical technology — no anthropomorphizing the AI!
Thou shalt use it early for brainstorms and workshops — Use the tools at your disposal… and keep the hard analysis for yourself
Thou shalt provide context — Give the model relevant background information
Thou shalt iterate and refine — Use ChatGPT’s responses as a starting point and iterate on them
Thou shalt prioritize human expertise — human expertise, judgment, and experience are paramount
Thou shalt have fun with it — it’s the closest we may ever get to humanity hive-experiencing itself; feel the magic
Thou shalt be cautious with sensitive data — Don’t share sensitive or confidential information with ChatGPT (!!!)

Generative AI reading list for Management Consultants

Below is a list of the best reads on the topic. I’ve advised all my analysts read them before talking to clients. You should do the same.

Relaxing reads

Will A.I. Become the New McKinsey? — The New Yorker
OMG! What Will Happen When A.I. Makes BuzzFeed Quizzes? — The New York Times
ChatGPT Is a Blurry JPEG of the Web — The Atlantic
Prepare for the Textpocalypse — The Atlantic
GPT’s Very Inhuman Mind — Neoma
ChatGPT Can Be Broken by Entering These Strange Words, And Nobody Is Sure Why — Vice
What’s the Point of Reading Writing by Humans? — The New Yorker
Here’s how 10 industries are experimenting with ChatGPT — Quartz
ChatGPT Isn’t ‘Hallucinating.’ It’s Bullshitting — Undark.org

Serious reads

Talking About Large Language Models — Cornell University
Who are we talking to when we talk to these bots? — Medium
Eight Things to Know about Large Language Models — Samuel Bowman
What every CEO should know about generative AI — McKinsey
These are the jobs that AI can’t replace — World Economic Forum
Prompting Techniques — Prompt Engineering Guide

Good AI newsletters

Courses & Books

The 29 Best (And Free) ChatGPT And Generative AI Courses And Resources — Forbes
Artificial Intelligence: A Modern Approach — S. Russel & P. Norvig
Artificial Intelligence: A Guide for Thinking Humans — M. Mitchell
Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence — K. Crawdord
You Look Like a Thing and I Love You — J. Shane

In 1962, in his book “Profiles of the Future: An Inquiry into the Limits of the Possible”, science fiction writer Arthur C. Clarke famously wrote that “any sufficiently advanced technology is indistinguishable from magic.”

This is true more than ever today. The future is uncertain, and we may not have a job in 5 years. We may as well enjoy the magic while it still has some shine on it. But we must do it right. Call it professional conscience.