Autopilot

<Execution_Policy>

• Each phase must complete before the next begins
• Parallel execution is used within phases where possible (Phase 2 and Phase 4)
• QA cycles repeat up to 5 times; if the same error persists 3 times, stop and report the fundamental issue
• Validation requires approval from all reviewers; rejected items get fixed and re-validated
• Cancel at any time by saying "stop" or "cancel"; progress is preserved for resume </Execution_Policy>

1. Phase 1 - Planning: Create an implementation plan from the spec

   • If ralplan consensus plan exists: Skip — already done in the 3-stage pipeline
   • Architect (Opus): Create plan (direct mode, no interview)
   • Critic (Opus): Validate plan
   • Output: .dog/plans/autopilot-impl.md

2. Phase 2 - Execution: Implement the plan using Ralph + Ultrawork

   • Executor (Haiku): Simple tasks
   • Executor (Sonnet): Standard tasks
   • Executor (Opus): Complex tasks
   • Run independent tasks in parallel

3. Phase 3 - QA: Cycle until all tests pass (UltraQA mode)

   • Build, lint, test, fix failures
   • Repeat up to 5 cycles
   • Stop early if the same error repeats 3 times (indicates a fundamental issue)

4. Phase 4 - Validation: Multi-perspective review in parallel

   • Architect: Functional completeness
   • Security-reviewer: Vulnerability check
   • Code-reviewer: Quality review
   • All must approve; fix and re-validate on rejection

5. Phase 5 - Cleanup: Delete all state files on successful completion

   • Remove .dog/state/autopilot-state.json, ralph-state.json, ultrawork-state.json, ultraqa-state.json </Steps>

<Tool_Usage>

• Use Task(subagent_type="dog:architect", ...) for Phase 4 architecture validation
• Use Task(subagent_type="dog:security-reviewer", ...) for Phase 4 security review
• Use Task(subagent_type="dog:code-reviewer", ...) for Phase 4 quality review
• Agents form their own analysis first, then spawn Claude Task agents for cross-validation
• Never block on external tools; proceed with available agents if delegation fails </Tool_Usage>

<Escalation_And_Stop_Conditions>

• Stop and report when the same QA error persists across 3 cycles (fundamental issue requiring human input)
• Stop and report when validation keeps failing after 3 re-validation rounds
• Stop when the user says "stop", "cancel", or "abort"
• If requirements were too vague and expansion produces an unclear spec, offer redirect to /deep-interview for Socratic clarification, or pause and ask the user for clarification before proceeding </Escalation_And_Stop_Conditions>

<Final_Checklist>

• All 5 phases completed (Expansion, Planning, Execution, QA, Validation)
• All validators approved in Phase 4
• Tests pass (verified with fresh test run output)
• Build succeeds (verified with fresh build output)
• State files cleaned up
• User informed of completion with summary of what was built </Final_Checklist>

Optional settings in .claude/settings.json:

{
  "dog": {
    "autopilot": {
      "maxIterations": 10,
      "maxQaCycles": 5,
      "maxValidationRounds": 3,
      "pauseAfterExpansion": false,
      "pauseAfterPlanning": false,
      "skipQa": false,
      "skipValidation": false
    }
  }
}

Resume

If autopilot was cancelled or failed, run /dog:autopilot again to resume from where it stopped.

Best Practices for Input

1. Be specific about the domain -- "bookstore" not "store"
2. Mention key features -- "with CRUD", "with authentication"
3. Specify constraints -- "using TypeScript", "with PostgreSQL"
4. Let it run -- avoid interrupting unless truly needed

Troubleshooting

Stuck in a phase? Check TODO list for blocked tasks, review .dog/autopilot-state.json, or cancel and resume.

QA cycles exhausted? The same error 3 times indicates a fundamental issue. Review the error pattern; manual intervention may be needed.

Validation keeps failing? Review the specific issues. Requirements may have been too vague -- cancel and provide more detail.

Deep Interview Integration

When autopilot is invoked with a vague input, Phase 0 can redirect to /deep-interview for Socratic clarification:

User: "autopilot build me something cool"
Autopilot: "Your request is open-ended. Would you like to run a deep interview first?"
  [Yes, interview first (Recommended)] [No, expand directly]

If a deep-interview spec already exists at .dog/specs/deep-interview-*.md, autopilot uses it directly as Phase 0 output (the spec has already been mathematically validated for clarity).

3-Stage Pipeline: deep-interview → ralplan → autopilot

The recommended full pipeline chains three quality gates:

/deep-interview "vague idea"
  → Socratic Q&A → spec (ambiguity ≤ 20%)
  → /ralplan --direct → consensus plan (Planner/Architect/Critic approved)
  → /autopilot → skips Phase 0+1, starts at Phase 2 (Execution)

When autopilot detects a ralplan consensus plan (.dog/plans/ralplan-*.md or .dog/plans/consensus-*.md), it skips both Phase 0 (Expansion) and Phase 1 (Planning) because the plan has already been:

• Requirements-validated (deep-interview ambiguity gate)
• Architecture-reviewed (ralplan Architect agent)
• Quality-checked (ralplan Critic agent)

Autopilot starts directly at Phase 2 (Execution via Ralph + Ultrawork). </Advanced>