Practical AI · Episode 46 · Deep Dive 1

How to stop prompting AI and start writing loops

The framework is Dharmesh Shah's. The part where I tried it in my own business, that's the story.

Framework credit: Dharmesh Shah, co-founder of HubSpot · simple.ai

The hook

Something changed how I work this week.

Dharmesh Shah, the co-founder of HubSpot, writes a newsletter called simple.ai. This week's issue was titled "How to Write Your First AI Loop." I read it twice. I think it can change how you work too.

"I don't prompt Claude anymore. I write loops, and the loops do the work. My job is to write loops." Boris Cherny, the engineer who created Claude Code — quoted in Dharmesh Shah's newsletter

Dharmesh's framework (all credit to him)

What a loop actually is

Most of us use AI like a vending machine. Type a request, get an answer, type the next one. That's prompting. A loop is different. It has three parts.

ObjectiveWhat "done well" looks like, in one sentence.

MetricHow the AI scores its own work, so you're not reading every word.

BoundaryHow far it runs on its own before it stops and checks with you.

His sharpest point

A loop that runs vs. a loop that learns

A loop that runs does the same thing every day. A loop that learns has a feedback signal wired in, so it gets better every time.

Aim for the one that learns.

My idea

Could a non-developer actually build these?

Here's where I come in. I'm not a developer. I think in outcomes, not code. So when I read this, my first thought wasn't "nice theory." It was: could I actually build loops for my own businesses? My recruiting firm, my sales-training startup, this show. Real work, today, not someday.

The prompt I ran

One simple instruction. No code.

What I typed"Read this Dharmesh email. Then give me five loops I could run for each of my businesses, using the way I actually work."

That was the whole thing. Read this. Apply it to me. Five per business.

The result

A playbook came back. Twenty loops.

Five for each of my four businesses. A loop to find and score candidates. A loop to keep my content on-message. A loop to turn every episode into something AI engines will actually quote. Each one had that same shape: a goal, a way to grade itself, and a line where I still decide.

Example 1 · Business development

What happened when I ran one for real

I picked the loop to reach back out to deals that had gone quiet, and actually ran it. I gave it a boundary: check my real email history before anything is final.

The loop drafted the messages, then checked itself against my history and caught that its own first drafts were wrong. It had assumed a backstory that didn't match what really happened with those people. So it rewrote them, accurately, before I ever saw a bad version. The judgment was mine. The loop carried it out.

Example 2 · Naming this show

The loop I like even better

Because you can watch every single pass. I run a loop to write the title and hook for each piece of the show. Same three parts, and the feedback signal is baked right in.

ObjectiveA title that leads with the viewer's value, not "what I did."

MetricSelf-scored 1–10 on a five-point rule. Rewrite anything under 9.

BoundaryIt hands me ten winners. I gut-pick.

The five-point rule it grades against: leads with viewer value · one clear promise · curiosity without clickbait · under ~60 characters · kills my banned framing ("watch what I built / I tried / my…"). That last rule is the feedback signal that makes this a loop that learns my taste.

Example 2 · Naming this show

Watch a weak title climb

Three real ones from this very episode:

"Watch How I Built AI Loops For My Business" → 2/10 → "How To Build An AI Loop" → 7/10 → "Make AI Do The Work While You Sleep" → 10/10

"AWS Adds AI Traffic Monetization To WAF" → 2/10 (jargon, zero viewer value) → "Get Paid When AI Reads Your Website" → 10/10

"My Brain Is Fried From Using AI All Day" → 3/10 (banned "my," all problem no fix) → "Why AI All Day Fries Your Brain (And The Fix)" → 10/10

Example 2 · Naming this show

It cranks. I make the call.

Same shape as the first loop. It generated, scored itself against my rule, rewrote everything under 9, and handed me ten finished titles to choose from. The keystroke work goes away. The judgment work stays with me.

See all ten title loops, scored and rewritten →

What I want you to try this week

Turn one task into a loop.

Take one thing you already use AI for. Drafting emails, prepping for a meeting, summarizing a call. Write down three things.

The objective. What does "done well" look like, in one sentence?
The metric. How would it grade itself, without you reading every word? If you can't answer that yet, you just found the real work.
The boundary. What can it do alone, and where does it stop and check with you?

The close

The keystroke work goes away. The judgment work stays with you.

The framework is Dharmesh Shah's, from his simple.ai newsletter "How to Write Your First AI Loop." Go read it. Then come build one. I did, and I'm not a developer.