The Basics of Map Scoping & Framing

I’m breaking this prompt into a series. The components of the series don’t necessarily go in order, so be patient, you’ll get the entire prompt as I currently use it at and end of the series. I think it’s important for you to understand some of the logic behind this for a few reasons:

1. I haven’t refactored this at all and hope you can organize the prompt so it’s easier to follow
2. I haven’t rationalized this very much and hope you can simplify the prompt without losing the quality of the output
3. It’s a mess (coming from a recovering anal retentive developer)

In essence, I believe this prompt can be streamlined but simply haven’t had the time to do it

The Prompt

Map the End Users Job-to-be-Done

Below I’m going to itemize the points I use in the prompt and explain them. Then I’ll give you a copy and paste version since I don’t generally write them in separate lines. That will be the last installment of this series.

BEGIN!

Act as a(n) {{end user}} with a deep expertise in Jobs-to-be-Done theory, which you will use here. As you know, Jobs have steps, much like a process, but they do not indicate how the {{end user}} does something, they represent what the {{end user}} must accomplish.

Assigning Roles: this is a technique that can be used style the output or improve accuracy. In this case, I’m injecting the {{end user}} as a variable as well as the {{industry}} and the {{sector}}. So, “Act as an actuary who works in the Health Insurance industry with a specialty focus in the Managed Care sector”. In this case Health Insurance is sector within the Healthcare industry.

Also, steps fall under 9 main phases. These phases are sequential. Each of the phases are explained below.

Information:

Explanation of Phases:

Do not assume a method or solution in any of these phases unless it is provided in the job or context inputs. For example, if the job is “Commuting to work” do not assume the commuter is using a personal vehicle. If the job is “Driving to a destination” then you can assume they are using a personal vehicle.

Information:

1. Define: in the define phase, we want to know what aspects of getting the job done need to be defined, planned, or assessed by the {{end user}} upfront in order to proceed.
1. Include anything that needs to be defined, planned or determined prior to performing any of the subsequent steps.
2. If I’m driving a car to a destination, I might need to determine where I am going, where I can park, assess traffic conditions, and/or determine the available route options
2. Locate: in the locate phase, we want to know what items or resources - tangible or intangible - must be located, gathered, collected, accessed, or retrieved by the {{end user}} to do the job.
1. Include anything that you might need access to and that you must take action in order to obtain it or them.
2. If I’m driving a car to a destination, I might need to locate my vehicle, find my drivers license, locate my glasses, etc.
3. Prepare: in the prepare phase, we want to know how the {{end user}} must prepare or integrate the inputs, or the environment(s), from the Locate step to do the job.
1. Include anything that might need attention or setup before executing the Job. The planning is done, and the necessary tangible or intangible resources have been obtain, but now the might need to be setup, or configured to work together
2. If I’m driving a car to a destination, I might need to inflate my tires to the proper pressure, or fill the gas tank to an adequate level, etc.
4. Confirm: in the confirm phase, we want to know what the {{end user}} must verify, prioritize, or decide before doing the job in order to be successful.
1. Include anything that is critical to double check, or any final decisions that must be made
2. If I’m driving a car to a destination, I might need to select the best or fastest route, or verify that the car is in proper working order.
5. Execute: in the execute phase, we want to know the primary thing the {{end user}} must do to execute the job successfully.
1. Include anything that is core to getting the job done, and would otherwise leave a gap in the process.
2. If I’m driving a car to a destination, the logical step would be “Drive to the destination”
6. Monitor: in the monitor phase, we want to know what the {{end user}} must monitor in order to ensure the job is executed successfully.
1. Include anything that should be checked in real-time, or while the execute step(s) are happening, to determine if if something is going off track.
2. If I’m driving a car to a destination, I might want to monitor the fuel level, or my tire pressure, worsening traffic conditions, or emergency situations.
7. Resolve: in the resolve phase, we want to know what problem the {{end user}} might need to troubleshoot, restore, or fix for the job to be completed successfully.
1. When a risk is identified we want to resolve it before it becomes an issue. If an issue emerges, we need to resolve it in order to proceed
2. If I’m driving a car to a destination and I run low on fuel, I would want to find a gas station to fill my tank
8. Modify: in the modify phase, we want to know what the {{end user}} might need to alter, adjust, or modify for the job to completed successfully.
1. If I’m driving a car to a destination and traffic worsens, I may want to alter my route to one that has less car volume, or is moving at a faster pace.
9. Conclude: in the conclude phase, we want to know what the {{end user}} must do to finish the job.
1. If I’m driving a car to a destination, I may want to park my car, secure my belongings and/or make sure it’s still in good condition for the next drive.

Information & Example: I go to great lengths to describe how a practitioner would frame a Job when conducting interviews. I describe the phase, sometimes provide an instruction, and then provide an example. You might notice that I’ve include a Phase called Resolve. I’ve taken this from Lance Bettencourt’s book Service Innovation: How to Go From Customer Needs to Breakthrough Services. Since most of us are concerned with UX issues, the service innovation approach is the one I chose.

The Job-to-be-Done for the {{end user}} is {{job}} {{context}}. Only consider the context if one is supplied, otherwise disregard it. Generate a list of job steps that consider each of the phases. There should be a minimum of one step per phase. However, there could be more than one.

Instruction: This is where I tell the prompt who the end users is, what job they are trying to get done, and in what context (if any). It’s important to word your context variable so it seamless appends to the Job. However, maybe it’s not that important because it always seems to figure out what I meant 🤫

Steps should be always begin with a verb. A bad step would be “Route Planning” and a good step would be “Plan the route.”

Instruction & Example: I’m telling the AI how to state the job step and providing an example.

The job steps should be focused on what the {{end user}} is trying to accomplish faster, with better output, or better throughput when {{job}} {{context}}.

Information: One more instruction to explain that this is not about what someone is doing, but rather what they are trying to accomplish.

Do not reference the phase in a job step unless absolutely necessary.

Instruction: This was an area of concern early on when AI would spit out whatever it wanted to. Since the phases are merely guidelines, I didn’t want them appearing as steps.

Stay tuned….there’s more coming.