2 min read
My daughter Lily is nearly five. Last Sunday over waffles, I told her: “Put the plate on the counter.”
She walked straight to the bathroom counter.
I almost got frustrated. Then I realized—she’d just washed her hands there before breakfast. In her context, that WAS “the counter.”
So I changed my approach. Now I ask: “Lily, can you tell me the steps you’re going to take to put that plate on the kitchen counter?”
If her plan involves climbing on the counter and swinging from the light fixture, we catch that before she starts. That’s the investment. Taking two minutes upfront to build a spec and implementation plan together instead of hoping it works out and dealing with the mess after.
Now imagine Lily has every PhD and basically all of human knowledge in her head. That’s your Large Language Model.
Here’s what I see in every organization:
“Fix this code.” “Make this better.” “Optimize our process.”
We’re giving billion-parameter models vaguer instructions than we’d give our kids learning basic tasks. Then we’re surprised when they don’t read our minds.
What actually works:
-
Give context first. “We’re in the payment processing module, cutting latency without breaking PCI compliance.”
-
Ask for the plan. “Walk me through your approach before you write anything.”
-
Iterate. “Caching works, but adjust for data freshness requirements.”
-
Save patterns. Document what works as your standard approach.
The real shift:
This isn’t about better prompts. It’s about moving from “the AI screwed up” to “we didn’t provide enough context.” The engineers who struggle are the ones who skip this step.
Sound familiar? It’s the same realization we had breaking apart monoliths and moving to continuous deployment. The problem is systemic.
What this means for you:
-
Your team needs to become specification writers and context architects, not just prompt crafters
-
ROI isn’t “tools deployed”—it’s cycle time reduction and first-pass success rates
-
The culture change matters more than the technology budget
I watch Lily get better every day. Not because she magically got smarter, but because we invested in clearer communication and better feedback loops instead of hoping she’d figure it out.
Your AI systems work the same way. Better collaboration patterns beat better models.
The question isn’t whether AI transforms your business. It will. The question is whether you’ll invest the time to give it clear context—or keep wondering why the plate ended up on the bathroom counter.
Companion
