Skip to content

Progressive Automation Practice

A graduated approach to autonomous agent loops that builds confidence and prevents costly failures.

The problem

Jumping from zero automation to overnight unattended runs is high-risk. A single misconfigured loop can burn tokens, produce wrong output, or silently diverge from intent. Progressive practice builds verified confidence at each stage.

The four stages

Stage 1: Single iteration (manual)

Run one pass of any automated workflow manually. Verify output. Understand what the agent does at each step.

# Example: run one verification pass
/vt-c-ralph-wiggum-loop  # single iteration, watch every step

Graduate when: You've run 3+ single iterations with correct output.

Stage 2: Short attended loop (2-3 iterations)

Let the loop run 2-3 iterations while you watch. Interrupt if anything looks wrong.

# Watch it loop
/loop 2m /vt-c-ralph-wiggum-loop  # every 2 minutes, stay present

Graduate when: 3+ short loops complete without needing intervention.

Stage 3: Longer attended loop (5-10 iterations)

Extend the loop duration. Check in periodically but don't watch every step.

/loop 5m /vt-c-ralph-wiggum-loop  # every 5 minutes, check back occasionally

Graduate when: The loop handles edge cases and errors gracefully without your input.

Stage 4: Unattended loop

Only after stages 1-3 have built verified confidence. Set up proper guardrails:

  • Max iterations: Always set a hard limit (ralph-wiggum-loop defaults to 5)
  • Token budget: Monitor token usage — runaway loops are expensive
  • Output review: Always review output after unattended runs
  • Rollback plan: Know how to undo what the loop did (git reset, file backups)

Common mistakes

Mistake Prevention
Skipping to Stage 4 Always start at Stage 1 for new workflows
No iteration limit ralph-wiggum-loop enforces max 5; never remove this
Ignoring token costs Check metrics/verification-loops.json after each run
Trusting completion claims The Iron Law: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
Running overnight without guardrails Set token budget alerts, use max iterations, review output next morning

Integration with toolkit skills

  • /vt-c-ralph-wiggum-loop: Convergence-based verification with built-in safety limits
  • /loop: Native interval-based scheduling — pair with ralph-wiggum-loop for verified convergence
  • Metrics: Check metrics/verification-loops.json to track false claim prevention and loop efficiency