The Question I Ask Myself Before I AI
In working with AI, I’m stopping before typing anything into the box to ask myself a question : what do I expect from the AI?
2x2 to the rescue! Which box am I in?
On one axis, how much context I provide : not very much to quite a bit. On the other, whether I should watch the AI or let it run.
If I provide very little information & let the system run : ‘research Forward Deployed Engineer trends,’ I get throwaway results: broad overviews without relevant detail.
Running the same project with a series of short questions produces an iterative conversation that succeeds - an Exploration.
“Which companies have implemented Forward Deployed Engineers (FDEs)? What are the typical backgrounds of FDEs? Which types of contract structures & businesses lend themselves to this work?”
When I have a very low tolerance for mistakes, I provide extensive context & work iteratively with the AI. For blog posts or financial analysis, I share everything (current drafts, previous writings, detailed requirements) then proceed sentence by sentence.
Letting an agent run freely requires defining everything upfront. I rarely succeed here because the upfront work demands tremendous clarity - exact goals, comprehensive information, & detailed task lists with validation criteria - an outline.
These prompts end up looking like the product requirements documents I wrote as a product manager.
The answer to ‘what do I expect?’ will get easier as AI systems access more of my information & improve at selecting relevant data. As I get better at articulating what I actually want, the collaboration improves.
I aim to move many more of my questions out of the top left bucket - how I was trained with Google search - into the other three quadrants.
I also expect this habit will help me work with people better.
🤖 AI 4 Agile Coach | PST Scrum.org | Author “Scrum Anti‑Patterns Guide” | Saving SMs, Coaches, POs, PMs from Busywork: AI 4 Agile BootCamp : Sept ’25 Cohort Now Open; see 👇.
2wThis shift from top-left prompting to collaborative exploration feels less like learning to prompt, and more like learning to think aloud with a system. Curious: how do you balance the up-front burden of precision with the fluidity that exploration invites? And do you see a future where agents learn enough from context that even PRD-style prompting becomes unnecessary?
Senior Data Scientist | Retail and Supply Chain Intelligence
2wthis seems like a common problem. i think we'll build a brain eventually. it will be way more advanced than current context engineering (we are here) into true personalization.