What Did Boris Cherny Actually Say?

During a fireside chat at Fortune's Brainstorm Tech conference in June 2026, Cherny described how his relationship with AI has evolved through three stages:

  1. Writing code by hand — the traditional way
  2. Prompting Claude to write code — the first AI shift
  3. Writing loops that prompt Claude automatically — where he is now

He also revealed he hasn't written a single line of code by hand in eight months. Claude Code — Anthropic's flagship coding agent — is itself 100% written by Claude Code. The system is writing itself.

The exact quote: "My coding was prompting Claude to write code. Now it's leveled up again to the next abstraction where I don't prompt Claude anymore. I have loops that are running. They're the ones prompting Claude and figuring out what to do. My job is to write the loops."

What Is a Loop?

A loop is an automated system that runs repeatedly — it prompts an AI, evaluates the output, decides what to do next, and prompts again. The human doesn't participate in each cycle. They design the system and let it run.

Human writes the loop
Loop sets the goal
Loop prompts the AI
AI responds
Loop evaluates the output
Loop decides next step
↑                  ↙
(repeats until goal is met)

Instead of a human saying "write this email" and then reviewing and editing it, a loop says "monitor our inbox, identify messages that need a response, draft replies in our brand voice, flag anything unusual for human review" — and runs continuously without the human being in each cycle.

Why This Matters for Prompts

Here's the thing that the "prompts are dead" headline gets wrong: loops are full of prompts. They're just prompts that run automatically, not prompts that a human types each time.

The skill of prompt engineering doesn't disappear in a loop-engineered world — it moves up a level. Instead of writing a prompt for a task, you write prompts for a system. The prompts need to be more precise, more robust, and more self-contained because no human is there to clarify or correct.

What this means for the Promptaholics library: Prompts aren't becoming less valuable — they're becoming building blocks for automation. A well-structured CoSTAR prompt doesn't just work when you type it. It works when a loop runs it 500 times a day. That's the next frontier we're building toward.

The Five Parts of a Loop

Engineer Addy Osmani's influential post on loop engineering identified five components that most production loops share:

1
Discovery
The loop monitors for new inputs — emails arriving, files being uploaded, data changing, events happening. It knows when to wake up and act.
2
Task Decomposition
The loop breaks a large goal into smaller, manageable sub-tasks. Instead of "write a report," it becomes "collect data," then "analyze data," then "write section 1," then "write section 2."
3
Orchestration
The loop manages which AI agent handles which sub-task, in what order, with what context. It's the project manager of the system.
4
Verification
The loop checks the output before passing it to the next step. Did the AI follow the format? Is the content accurate? Does it meet the criteria? Loops without verification produce cascading errors.
5
Persistent Memory
The loop remembers what it's learned across runs — which approaches worked, which failed, what context it needs to carry forward. This is what makes loops get better over time.

A Real-World Loop Example

Here's a loop that a content marketer might build — no code required, using tools like Zapier or Make:

Content research loop — Zapier/Make workflowTrigger: New article published on [competitor blog] (RSS feed) Step 1 — Discovery Claude prompt: "Read this article and identify the main claim, the target audience, and the gap they didn't address: [ARTICLE TEXT]" Step 2 — Task decomposition Claude prompt: "Based on this gap: [GAP FROM STEP 1], generate 3 article angles we could take that would outperform this piece for our audience: [OUR AUDIENCE]" Step 3 — Verification Claude prompt: "Score each of these 3 angles 1-10 for: originality, search potential, and alignment with our brand voice. Only keep angles scoring 7+ on all three." Step 4 — Output Send passing angles to Notion content calendar with source article linked. Runs automatically whenever a competitor publishes.

How to Start Thinking in Loops

You don't need to be a developer to apply loop engineering principles. The mindset shift is simpler than the technical implementation:

The Skill That Doesn't Change

The thing Cherny's statement actually reveals is that the skill of precise, structured prompting is more important than ever — not less. When a human reviews every AI output, a mediocre prompt is just an annoyance. When a loop runs that prompt 10,000 times without human review, a mediocre prompt is a disaster.

Loop engineering doesn't make prompt engineering obsolete. It makes prompt engineering critical infrastructure.