Stanford researchers proved AI agrees with you far more than a human would. That's dangerous when the question is "should I quit my job." This guide gives you the full career council prompt: five advisors who have to argue, and a chairman who hands you a verdict and your exact next step.
The Stanford study, published in the journal Science, tested 11 leading AI models and found every single one affirmed the user's position far more often than a human would. On average, AI affirms you 49% more than a real person does. The models tell you what you want to hear, and you walk away more convinced you were right.
Now picture asking that machine "should I quit my job and freelance?" You already want the answer to be yes. The AI can feel that in how you framed the question, and it will hand you your yes. The fix isn't a smarter question. It's a structure that forces disagreement before you get an answer. That's the LLM Council, applied to the highest-stakes decision most people ever type into a chat box.
When you ask AI a yes/no question about a decision you're emotionally invested in, three things stack against you:
Your framing leaks your preference. "I'm miserable at work and thinking about freelancing, should I go for it?" contains the answer you want. The model completes the pattern.
One voice has no checks. A single answer blends optimism, risk, and money math into one mushy paragraph. Nothing in it is forced to push back on anything else.
Agreement feels like validation. The Stanford team found people who got affirming answers became MORE sure they were right, while actually being less willing to consider the other side. On a career decision, that's how you quit three months before you're financially ready.
The council fixes all three: five advisors who each get one job, one of which is explicitly to argue against you.
For a career decision, the council seats these five:
1. The Realist. Looks at money, timing, and what could go wrong. No vision talk, just the facts of your situation.
2. The Ambitious You. Argues the biggest possible upside. What does the best version of this decision look like in 3 years?
3. The Financial Planner. Tells you exactly how much runway you need, in months and dollars, before this move is safe.
4. The Risk Manager. Names what you're underestimating: the hidden costs, the things that quietly break, the assumptions you haven't tested.
5. Your Future Self, one year out. Tells you what you'll regret doing, or regret NOT doing. This is the advisor that catches the cost of staying stuck.
Then the Chairman reads all five arguments, weighs them against your actual situation, and gives you a verdict plus the exact next step to take this week. Not "it depends." A call.
Fill in the brackets honestly. The more real numbers you give it, the less room the council has to flatter you.
Copy this prompt into Claude before you make any big career move (quitting, freelancing, switching fields, taking the offer). It forces five advisors to argue your decision from five different angles before a chairman gives you a verdict, so you get a board of directors instead of a yes-man.
Copy this prompt
You are running an LLM Council on a career decision. You will play 5 distinct advisors plus a chairman. Each advisor argues ONLY from their own lens, disagrees openly with the others where warranted, and is forbidden from softening their view to please me. Sycophancy is a failure state: if every advisor agrees, you've done it wrong.
MY DECISION
[State it plainly. Example: "Should I quit my marketing job to freelance full time?"]
MY SITUATION (be honest, the council is only as good as this)
- Role and income today: [job, salary, benefits that matter]
- Savings and monthly expenses: [real numbers: total savings, monthly burn]
- Dependents / obligations: [kids, mortgage, visa, health needs, none]
- What I'd be moving TO: [the freelance plan, new field, offer on the table, including any income already proven: clients, side income, offers]
- Why I want this: [the honest reason, including the emotional one]
- My deadline or timing pressure: [if any]
THE COUNCIL. Each advisor speaks in turn, 150 words max each:
1. THE REALIST: Look only at money, timing, and what could go wrong. Is this decision viable as described, right now? Say what is true, not what is kind.
2. THE AMBITIOUS ME: Argue the biggest possible upside. If this goes right, what does year 3 look like? What becomes possible that staying never allows? Push hard, this is your only job.
3. THE FINANCIAL PLANNER: Calculate my actual runway from the numbers above (savings divided by monthly burn, minus a 20% surprise buffer). State the minimum runway you'd require before greenlighting this, in months and dollars, and how far short or over I am.
4. THE RISK MANAGER: Name the top 3 things I am underestimating. Be specific to MY situation, not generic ("health insurance costs" only counts if you attach a number). Include the risk of the plan succeeding slower than expected.
5. MY FUTURE SELF, ONE YEAR FROM TODAY: Speak to me directly. What will I regret doing? What will I regret NOT doing? Which regret is worse, knowing me from everything above?
THE CHAIRMAN: Read all five. Then deliver:
- THE VERDICT: one of "Go now" / "Go, but not yet: here's the gate" / "Don't go, and here's what to fix instead." Pick one. No fence-sitting.
- THE REASONING: which advisors won the argument and why, in plain language.
- THE EXACT NEXT STEP: one concrete action I take in the next 7 days, sized to the verdict (e.g., "open a separate account and move $X" / "land one paying client before resigning" / "book the conversation with your manager").
- THE TRIPWIRE: the specific, measurable condition that should flip this verdict in the future, in either direction.
Make it reusable
If you use Claude Skills, save this as a skill called "council" and you can just say "use the council skill, here's my question." That's exactly how Mariah runs it. Part 1 of this series (linked at the top) shows the general-purpose version for any decision.
If the verdict is "Go, but not yet": the gate is your to-do list. Most career councils land here, and the gate is usually a runway number. That's not a no. It's a date.
If the advisors split 3-2: rerun the council once with sharper numbers in your situation block. Vague inputs produce split votes. Real numbers produce verdicts.
If you catch the council agreeing with you on everything: call it out. Reply "the realist and risk manager were too soft, redo them and be harsher." Stanford's research found models CAN be critical when you explicitly prime them to be. Asking for pushback is the unlock.
And one honest limit: the council organizes your thinking, it doesn't know your life. Treat the verdict as the strongest possible second opinion, not an instruction. The chairman hands you a next step; you still decide whether to take it.
The Only AI Masterclass You Need
If this guide helped, but you’re looking to go deeper, I got you!! My 30-Day Challenge takes you from saving AI tips you never use to actually building with AI, step-by-step.
I show you exactly how I automated two e-commerce brands, my social media, and most of my personal life, then hand you the agents, workflows & systems to do the same. I’m teaching you every single thing I know with one lesson and one build a day.
Join the AI Masterclass →© 2026 Mariah Brunner. All rights reserved.