Before jumping all in, ask, “What role should AI play in our tasks?”
First, make a list of common tasks and the goal of each.
List tasks you perform in your job, on client projects, or in daily business operations. Then describe the goal of the task. Understanding the goal can help determine the human versus AI value in it. If the goal is to build a personal relationship with a customer or client, AI outsourcing may save time but undermine the task objective.
Recently a university outsourced their commencement speaker to an AI robot. Students started an unsuccessful petition for a speaker who could offer a “human connection.” The AI robot’s speech was described as weird and unmoving. Without any personal anecdotes, The Chronicle of Higher Education reports, “Sophia … delivered an amalgamation of lessons taken from other commencement speakers.”
Second, determine which type of AI Function each task requires.
The six AI functions (Generate, Extract, Summarize, Rewrite, Classify, Answer Questions) are modified from Christopher S. Penn’s AI Use Case Categories. Can the task be performed by one or multiple of these AI functions? If yes, you still want to consider how well AI can perform the function compared to a human and consider benefits that may be lost outsourcing to AI.
In my ad career clients often asked why a certain phrase or benefit was in the ad copy or ad script. Because I wrote it, I could explain it. It could be human insight from research (which AI can summarize), truths from lived experience, or talking with customers. If AI wrote the copy or script it may be missing and I wouldn’t know why AI wrote what it did. If you ask AI it often doesn’t know. Scientists call this the “unknowability” of how AI works.
Third, categorize the level of thinking each task entails.
The six levels of thinking (Remember, Understand, Apply, Analyze, Evaluate, Create) are modified from Oregon State’s Bloom’s Taxonomy Revisited. Bloom’s Taxonomy categorizes levels of thinking in the learning process. It was revisited to consider AI’s role. In each level determine the level of the task and discern AI’s capabilities versus distinctive human skills.
I had a student create a situation analysis of Spotify with ChatGPT. It was good at extracting information, summarizing, and suggesting alternatives (AI Capabilities of the Create Level). It wasn’t good at “Formulating original solutions, incorporating human judgment, and collaborating spontaneously” (Create Level Distinctive Human Skills). GPT’s recommendations lacked the nuanced understanding I’d expect from professionals or students.
Fourth, review the legal and ethical issues of outsourcing to AI.
Does the task require uploading copyrighted material? Are you able to copyright the output (copy/images) to sell to a client or protect it from competitor use? Does your employer or client permit using AI in this way? Are you sharing private or proprietary data (IP)? What’s the human impact? For some AI will take some tasks. For others, it could take their entire job.
Many companies are adding AI restrictions to contracts for agency partners. Samsung and others are restricting certain AI use by employees. There’s concern about performance or customer data uploaded into AI systems training a model competitors could use. Some agencies and companies are developing Closed AI versus Open AI to run local AI storing data on local versus cloud servers. For a summary of main AI legal concerns see “The real costs of ChatGPT” by Mintz.
Fifth, employ human agency to produce desirable results.
We shouldn’t be resigned to undesirable outcomes because AI change is complex and happening quickly. Penn’s TRIPS Framework for AI Outsourcing includes “pleasantness.” The more Time consuming, Repetitive, less Important, less Pleasant tasks that have Sufficient data are better candidates for AI. Don’t give away your human agency. Decide on your own or influence others to save the good stuff for yourself.
A post on X (Twitter) by author Joanna Maciejewska struck a nerve going viral “You know what the biggest problem with pushing all-things-AI is? Wrong Direction. I want AI to do my laundry and dishes so I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes.” She later clarified it wasn’t about actual laundry robots, “it’s about wishing that AI focused on taking away those tasks we hate and don’t enjoy instead of trying to take away what we love to do and what makes us human.”
Marketers are getting this message. In a survey of CMOs most are using AI for draft copy and images that are refined by humans. And over 70% are concerned about AI’s impact on creativity and brand voice.
It’s easy to get overwhelmed and afraid of the AI future.
As Tech leaders sprint forward in an AI arms race and regulators woefully lag behind, the rest of us shouldn’t sit back and wait for our world to change. Unlike the Internet and social media, let’s be more intentional. Don’t fall prey to The Tradeoff Fallacy believing that to gain the benefits of AI we must give everything away.
In Co-Intelligence, Ethan Mollick says it’s important to keep the human in the loop. It’s not all-or-nothing. Some warn of a future when we don’t have choices in what role AI plays in our lives. It’s not the future. Today we can choose how to use AI in our professional, educational, and personal lives.
You know your job best, but if you want some help brainstorming tasks to outsource to AI, Paul Roetzer and SmarterX have created a custom GPT. Visit JobsGPT and enter a job title or job description. It uses AI to break down the job into tasks, estimate AI impact, time saved, and provides rationale.
Advocate for a pilot program if your employer is AI hesitant.
Some companies are holding employees back from AI use due to fears and some early adopters are failing to see the value of AI. The CIO of Chevron recently said, “the jury is still out on whether it’s helpful enough to justify the cost.” If you find yourself in a company or organization that is either not allowing AI or skeptical of paying the cost of a CoPilot or ChatGPT license ($20 or $30 per user per month), Paul Roetzer of the Marketing AI Institute suggests a 90-day pilot program.
Advocate to be part of a pilot program of small groups of employees to test use cases of AI for three months. Use this AI task framework to discover 3-5 of the most valuable. Keep track of the time you spend on each task before and after GPT use. Add up the hours saved each month and multiply by your actual or estimated hourly rate. If it’s more than $30 you have justified the costs. You’ve also become more valuable as you can train other employees in these tasks. Christopher Penn offers a more detailed method to calculate the ROI of AI.
What keeps me hopeful is breaking my job down into tasks and making intentional decisions on what to outsource to AI. Then I can see the time savings for me to focus on higher value aspects of my job. Using this framework allows me to get excited about the possibilities of AI taking over my least favorite or most time consuming tasks. In my next post, I’ll give some specific examples using this framework.
This Was Human Created Content!