stepback

/stepback — One-Shot Perspective Reset

Source: team-attention/hoyeon pattern. Read-only, zero side effects.

Purpose

Scan the current work context, generate 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.

Use when you're deep in implementation and need to check if you're solving the right problem at the right level.

Dominant Variable

Whether the work direction is solving the right problem at the right level — if this is off, even flawless implementation produces the wrong outcome.

Key Assumptions

1. Current work context exists in the conversation — if broken: ask once, "tell me in one line what you're doing."
2. Output fits an abstraction level expressible in ≤10 lines — if broken: the question is too concrete → self-check "go more abstract."

Trigger

• /stepback
• "step back"
• "zoom out"
• "blind spot"
• "am I on track"
• "big picture"
• "what am I even doing"

Discard If

• Work is already completed (use retrospective tools instead)
• Code review requested (use code review tools instead)
• Specific change impact analysis needed (use scope definition tools instead)

---

Architecture

Recent conversation context (current work direction)
    ↓
[PARSE]      → Extract current direction + original intent + scope signals
    ↓
[STEP-BACK]  → Generate 1 abstract reframing question
    ↓
[CHECK]      → Run 3 checks
    ↓
[OUTPUT]     → Under 10 lines, return immediately

---

Stage 1: PARSE

Extract from recent conversation:

• Current direction — what the user is actively working on
• Original intent — why this work was started (implicit is OK)
• Scope signals — size/complexity of the change

---

Stage 2: STEP-BACK

DeepMind step-back pattern: abstract from the specific subject of current work → the general principle/system it belongs to.

Current Work	Step-Back Question
"Fixing this null pointer bug"	"Is the error handling strategy of this module correct in the first place?"
"Adding a new API endpoint"	"Should this feature live in the API layer, or somewhere else?"
"Refactoring this function"	"Should this function exist at all, or is the caller the real problem?"
"Writing tests for module X"	"Is X's boundary designed in a testable way?"
"Optimizing this query"	"Should this query be called at this point at all?"