Steering

Garden · not yet reviewed Established: widely used

Directing AI work as it happens: setting the goal and limits, approving one step at a time, correcting course early and cutting anything it does beyond what you need.

Also called: directing AI · guiding the work · course-correcting · managing AI · plan mode

Connections

Understand first

Ideas this one builds on.

• Prompting (garden)

Leads on to

Ideas that build on this one.

• Allocation economy (garden)
• Human in the loop (garden)
• Vibe coding (garden)

Related

Often used together or easily confused.

• Smallest useful version (garden)
• Agents (garden)
• Clarifying questions (garden)
• Delegating to AI (garden)

Skills that use it

• practice-coach (garden)
• /build-brief (garden)
• /stuck-or-pivot (garden)

Blueprints that practise it

• Write a handover brief before you give an agent a real task (garden)

Resources that teach it

• The AI Fluency Index (garden)
• The Knowledge Economy Is Over. Welcome to the Allocation Economy. (garden)
• Compound Engineering (garden)
• The Eight Levels of AI Adoption (garden)
• The non-technical PM's guide to building with Cursor (Lenny's Podcast, with Zevi Arnovitz) (garden)
• Management as AI superpower (garden)
• Use My /Human-Review Skill to Edit HTML and Markdown Files Visually (garden)

Competency

• Steer
• Frame the outcome

Find steering on the commons map ↗

You may know it from

• management delegating to a new team member Clear goal, agreed limits, early check-ins, and feedback before small misunderstandings grow.
• film a director giving notes between takes

In products

The same idea, under different names in different tools.

Provider	What they call it
Anthropic	Plan mode in Claude Code

In plain words

As AI takes on bigger jobs, directing the work well matters more than writing the perfect request. That directing is steering. It looks a lot like managing a capable but literal new colleague.

Steering has a few parts. Set the goal and the limits up front, including what’s out of scope. Ask for a plan before the work, and approve it. Review early output and correct course while changes are cheap. Notice scope creep: AI often adds sections, features or polish you never asked for, and saying “remove that, keep it simple” is part of the job. And know when to stop and restart rather than patching a run that went wrong.

People with management, editing or project experience are often better at this than they expect. The habits transfer directly.

Example

A program lead asks AI to draft a volunteer handbook. Before any writing, she asks for an outline and cuts two sections. After the first chapter, she says “shorter sentences, and drop the legal language.” By chapter three, the drafts need almost no edits.

How it connects

• Extends prompting into an ongoing conversation about direction.
• Central to working with agents and to vibe coding.
• Cutting scope ties it to the smallest useful version; approvals tie it to human in the loop.

Try it

On your next bigger AI task, ask for a plan first and don’t let it start until you’ve changed at least one thing in the plan. Note what you changed and why.

---

Read this card as plain Markdown: /concepts/con-steering.md. Know a parallel from your own field, or a product that implements this? Add it.