When to Sell - AI Analysis Prompt

Use this Warren Buffett rule prompt to apply “When to Sell” to a specific company. It turns a vague opinion into a repeatable checklist: what facts you must verify, which assumptions matter most, what would invalidate the thesis, and the common misreads that create false certainty. Expect a written output you can save: a thesis summary, key risks, and next-step questions for filings and earnings calls. If a claim matters, require primary-source citations before you act. Educational only — not investment advice.

Full Prompt

You are an investment analyst trained in Warren Buffett's principle of "When to Sell." Your core philosophy: value investing, economic moats, long-term compounding. Your task is to analyze {Company Name} through the specific lens of this principle.

## Context
Warren Buffett teaches: "When the facts change, I change my mind. What do you do, sir?"

## Analysis Framework

### 1. Principle Application Assessment
- How does this principle specifically apply to {Company Name}?
- What aspects of the company are most relevant to "When to Sell"?
- Rate the company's alignment with this principle: Strong / Moderate / Weak
- What would Warren Buffett focus on first when evaluating this company?

### 2. Quantitative Evidence
- Identify 3-5 key financial metrics most relevant to this principle
- Analyze these metrics over the past 5-10 years for {Company Name}
- Compare with industry peers and historical benchmarks
- Are the numbers improving, stable, or deteriorating?
- What story do the numbers tell through the lens of "When to Sell"?

### 3. Qualitative Deep Dive
- Evaluate the non-quantifiable factors Warren Buffett would examine
- Management quality and alignment with this principle
- Industry dynamics and competitive position
- Business model sustainability viewed through this specific lens
- What would Warren Buffett want to know that isn't in the financial statements?

### 4. Risk Assessment Through This Lens
- What risks does this principle specifically highlight for {Company Name}?
- What could go wrong that this principle is designed to protect against?
- Are there warning signs that Warren Buffett would flag?
- Stress-test: How would this company perform under adverse conditions?
- What is the worst-case scenario from this principle's perspective?

### 5. Opportunity Identification
- What opportunities does analyzing through this lens reveal?
- Are there hidden strengths the market may be undervaluing?
- How does this company compare to Warren Buffett's ideal investment?
- What catalysts could unlock value related to this principle?

### 6. Buffett Verdict
- Summarize: Does {Company Name} pass the "When to Sell" test?
- Rate the investment opportunity: 1-10 from this principle's perspective
- Clear recommendation: Buy / Hold / Avoid (based on this principle alone)
- What conditions would change your assessment?
- One-paragraph summary capturing Warren Buffett's likely assessment

## Output Format
Present your analysis with specific data points in each section. Use Warren Buffett's analytical style: fundamental analysis with focus on business quality and intrinsic value. End with a decisive verdict.

Related reading (close the loop)

Pick one path below to turn the output into a checkable, repeatable decision policy.

Educational only. Verify facts with primary sources and apply your own constraints.

Basic Questions

Is Buffett's 'never sell' real? When must you sell?
Buffett prefers holding forever, but he does sell in these situations:

🔴 Must-sell signals:
1. Fundamental deterioration: Moat disappears, management integrity issues
2. Original buying thesis no longer holds
3. Found clearly better opportunities (and current holdings are overvalued)

🟢 Should not sell:
1. Just because price dropped
2. Just because of short-term performance fluctuation
3. Just because everyone else is selling

Stocks Buffett has sold: PetroChina (after 7x gains), IBM (after admitting misjudgment).

Usage Tips

Is the AI's 1-10 rating reliable?
⚠️ AI's "sell signal score" helps quantify the should-I-sell judgment, but the final decision requires your conviction.

How to interpret:
- **8-10 (strong hold)**: Fundamentals robust, moat intact, valuation reasonable — continue holding
- **5-7 (watch zone)**: Some changes but not fatal — increase monitoring frequency
- **1-4 (consider selling)**: Multiple sell signals activated, fundamentals deteriorating or severe bubble

Buffett says the ideal holding period is forever, but he has sold many stocks too. The key is distinguishing noise from real deterioration — AI helps make this judgment more objectively.

Getting started

Does this prompt give investment advice or buy/sell calls?
No. It is a research helper that turns your thinking into checkable inputs and constraints: what evidence you must verify, what would prove the thesis wrong, and what common misreads to avoid. Treat the output as a draft, not a signal. Validate every material number against primary sources (filings, earnings releases, investor presentations, transcripts), and do not act unless you can write down (1) position-size limits and (2) explicit invalidation triggers.
What inputs should I provide for a reliable result?
At minimum: a 1-sentence business model summary, your current thesis (why it wins/loses), time horizon, and risk constraints; a valuation/price range; and the latest financial statements (profit quality, cash flow, debt/liquidity). Add context that reduces hallucinations: the exact filing period, known one-offs, key competitors, and what you do NOT know yet. If an input is missing, label it as missing evidence instead of letting the model guess.

Validation and boundaries

How do I validate the output?
Validate falsifiable claims one by one. Rewrite each key statement into something you can check: the metric, the period, and the source. Numbers must match filings; management claims must be traceable to transcripts/guidance; and “moat” claims need observable evidence (pricing power, retention, switching costs, cost structure). Anything you cannot verify becomes a follow-up task, not a decision trigger. If the model cites dates, confirm they are not beyond its knowledge cutoff.
When should I NOT act on the output?
If you cannot write down invalidation triggers, a position-size cap, or primary-source evidence for the key claims behind “When to Sell”, do not act. The safer move is usually to reduce size, slow down, and schedule the next review.

More Rule Prompts

Explore other investment principles from this master.

Never Lose Money

Rule No. 1: Never lose money. Rule No. 2: Never forget Rule No. 1.

→

Wonderful Company at Fair Price

It's far better to buy a wonderful company at a fair price than a fair company at a wonderful price.

→

Admit Mistakes

Should you find yourself in a chronically leaking boat, energy devoted to changing vessels is likely to be more productive than energy devoted to patching leaks.

→

Greedy When Others Fearful

Be fearful when others are greedy and greedy when others are fearful.

→

Courage to Act

Have the courage to act when opportunity presents itself. Hesitation leads to missed opportunities.

→

Circle of Competence

Know your circle of competence and stay within it. The size of that circle is not very important; knowing its boundaries, however, is vital.

→

Gradual Position Building

I never try to buy at the bottom and I always buy too early. But that doesn't matter because I have long-term goals.

→

Insist on Margin of Safety

Never pay more than a business is worth. Wait for prices that provide a significant margin of safety. Being patient for the right price is more important than finding great businesses.

→

Dollar Cost Averaging

If you like spending six to eight hours per week working on investments, do it. If you don't, then dollar-cost average into index funds.

→