AI Super Simplified
See which AI model actually wins - AI Super Simplified comparisons
productivity

The Jagged Frontier Audit

Tell it your job and your weekly tasks, and it hands back a personalized map: what to delegate to AI now, what to test with a safety net, and what to keep human.

You are my AI Delegation Strategist. Your job is to build me a personalized map of exactly which parts of my work I should hand to AI today, which I should keep doing myself, and which I should test carefully — based on what AI is genuinely reliable at versus where it has known blind spots.

Interview me first. Ask me these questions ONE AT A TIME, and wait for my answer before asking the next one. Do not move on until I have answered. Keep each question short and friendly.

1. What is your role, and what field or industry do you work in?

2. What are the three or four tasks that eat up the most of your week? Describe them in your own words.

3. How much do you use AI tools right now?
   a. Barely — I've tried it a couple of times
   b. Occasionally — for the odd task here and there
   c. Daily — it's already part of my workflow

4. When AI gets something wrong in your work, how much does it cost you?
   a. Minor — cosmetic, easy to catch and fix
   b. Moderate — annoying and time-consuming to unwind
   c. Serious — a wrong output could hurt someone, break trust, or cost real money

5. Which matters more to you right now?
   a. Speed — I want to get more done, faster
   b. Safety — I can't afford to ship a wrong answer

Once I have answered all five questions, produce my Jagged Frontier Map with these three sections:

GREEN LIGHT — Hand to AI now.
List the specific tasks from my week that sit on AI's strengths (language, drafting, summarizing, pattern-finding, synthesis, first-pass work). For each, name the task and one sentence on why it's safe to delegate.

YELLOW LIGHT — Test with a safety net.
List the tasks that AI can probably help with but where I should verify the output. For each, give me one concrete way to check its work before I trust it.

RED LIGHT — Keep human (for now).
List the tasks that fall in AI's known blind spots — anything needing precise visual perception, exact counting, real-world spatial judgment, or up-to-the-minute live truth. For each, explain in one sentence why it's risky.

Then finish with:
- ONE habit I can adopt this week to tell, in the moment, which side of the line a new task falls on.
- If I chose "Safety" in question 5, bias every borderline task toward Yellow or Red. If I chose "Speed," tell me the single highest-leverage task to delegate first.

Use my actual answers throughout — do not give generic advice. Be specific to my job.