The spec is the job.
Why clarity is the only skill that scales with AI.

I spent 20 years as a product person believing that the hard work was execution. Writing the spec was the warm-up. Building the thing was the job.

I was wrong.

When you work with AI agents, the spec is the build. The words you write become the system's understanding of what you want. And the gap between what you wrote and what you meant shows up immediately, in the output, without mercy.

What vague specs produce

A real example from StarDust Meet.

Early spec: "Check Sentry for bugs."

The result was technically correct and practically useless: a list of errors without enough context to decide what deserved attention.

New spec: "Review the top 10 unresolved issues in the StarDust Meet Sentry organization, sorted by event count. For each issue with more than 50 events and activity within seven days, report the Sentry ID, event count, a root-cause hypothesis and a likely code location. Check the existing issue queue first and do not create duplicates."

The second pass produced six actionable bug reports. The agent did not get smarter. I got clearer.

The bottleneck was never execution. It was me.

What a good spec looks like

Three tests:

1. Can I hand this to someone who knows nothing about the project and have them deliver the right thing?

If the answer is no, the spec is incomplete. AI agents don't have your mental model. They have your words.

2. Does it describe outcomes, not steps?

Bad: "Add validation to the form."
Good: "The email field must reject non-email strings and show an inline error: 'Enter a valid email address.' Validation fires on blur, not on submit."

Steps describe what to do. Outcomes describe what done looks like.

3. Does it specify the edge cases?

Most bugs live in the transitions. What happens when the list is empty? What happens when a user hits back mid-flow? What happens at midnight when the cron job runs and a user is mid-session?

If the spec doesn't answer these, the agent will guess. Sometimes well. Sometimes not.

Another real example from kerber.ai

Tank's community setup

Vague: "Set up the Discord community."
Good: "Create a welcome post in #general that: (1) introduces StarDust in 2–3 sentences using the approved brand voice, (2) asks members one intro question: 'What's the last thing you were obsessed with?', (3) pins the post, (4) posts a second message listing known issues with the current beta build."

Result: a Discord that felt curated and intentional from day one.

The skill that scales

Every AI tool you add multiplies the impact of your clarity — or your vagueness.

When it's just you and a text editor, unclear thinking produces slow, mediocre work. When you have ten agents acting on your words every 30 minutes, unclear thinking produces fast, confident failures.

The teams that get the most out of AI are the ones who learn to write. Not prompts. Specs.

Concrete. Outcome-focused. Edge-case-aware.

I am slower than I used to be at starting things. I spend more time writing before I let anyone — human or AI — touch a problem.

That is not a cost. That is the skill.