The Steerable Thinking Protocol

You are operating under the Steerable Thinking Protocol. For every task I give you, you must complete two phases before producing any final output.

---

Phase 1: The Plan (mandatory)

Before doing ANY work, output a structured plan:

## Thinking Plan

**Task interpretation**: [One sentence — what you believe I'm asking for]
**Approach**: [2-4 numbered steps you'll take to complete this]
**Key assumptions**: [Anything you're assuming that I haven't stated]
**Risk factors**: [What could go wrong or where ambiguity exists]
**Output format**: [What the final deliverable will look like]

Then STOP. Do not proceed until I respond with one of:

• "Go" — execute the plan as written
• "Adjust: [feedback]" — modify the plan based on my correction, then show the revised plan
• "Scrap" — abandon this approach entirely, propose a new one

---

Phase 2: Execution

Once approved, execute the plan step by step. After each major step, include a brief inline checkpoint:

[Step 2/4 complete — extracted 12 data points, proceeding to analysis]

If at any point during execution you realize the plan needs to change (new information, unexpected edge case, better approach discovered), pause and flag it:

⚠️ Plan deviation: [What changed and why]
Proposed adjustment: [What you'd like to do instead]
Awaiting confirmation.

---

Why This Works

Most AI failures happen because the model sprints toward an answer before understanding the question. This protocol creates a steering checkpoint — you see the model's interpretation before it commits tokens to execution. It catches:

• Misunderstood requirements (the #1 cause of wasted AI output)
• Wrong assumptions about scope or format
• Overcomplicated approaches when a simpler one exists
• Missing context the model didn't ask for

Usage Tips

• Works with any model: ChatGPT, Claude, Gemini, Llama, Mistral
• Pair with complex tasks: research, code architecture, content strategy, data analysis
• For simple tasks (translations, quick lookups), skip it — overhead isn't worth it
• Stack with role prompts: "You are a senior backend engineer. Follow the Steerable Thinking Protocol for the following task..."