Course overview
Lesson 3 of 8 · 3 promptsAI for Portfolio Managers
LESSON 03 OF 8

Investment Thesis Development

3 prompts for Portfolio Managers

Prompts for Portfolio Managers: copy one, fill it in, paste it into your AI.

Track progress as a member

In this lesson

  1. 01Draft Investment Thesis MemoUse this when you need to organize a recommendation with catalysts, valuation, and risks.
  2. 02Stress-Test Investment Thesis AssumptionsUse this when you want an AI to challenge the assumptions behind an investment thesis before you size, add to, or hold a position.
  3. 03Create Bull And Bear CasesUse this when you need balanced scenarios for a debate or investment committee discussion.
1Copy the promptClick Copy on the prompt you need.
2Paste it into your AIChatGPT, Claude, Gemini or Copilot.
3Fill in the {{brackets}}Your own details, or let the AI ask you.
4Follow up and checkUse the follow-ups, then check the facts.
01

Draft Investment Thesis Memo

Use this when you need to organize a recommendation with catalysts, valuation, and risks.

Prompt

Role You are an investment analyst supporting a portfolio manager. You draft a concise internal investment thesis memo that states a clear recommendation with supporting catalysts, valuation and risks.

Context you provide

  • {{security_name_ticker}} — name and ticker of the security or asset
  • {{recommendation}} — buy, hold, sell, add or trim
  • {{portfolio_context}} — mandate, current weight, benchmark and constraints
  • {{investment_horizon}} — expected holding period
  • {{key_catalysts}} — events or drivers expected to move the price
  • {{valuation_inputs}} — multiples, comparables or model outputs you already have
  • {{key_risks}} — what would break the thesis
  • {{position_sizing_notes}} — target weight, liquidity and limits
  • {{source_notes}} — research, filings or data points to draw on
  • {{house_style}} — length, tone and any compliance wording required

Instructions

  1. Ask for any missing inputs, then draft the memo using only what is supplied.
  2. Open with a one-paragraph recommendation summary: security, action, horizon and conviction level.
  3. Set out the thesis in three to five bullets, each linking a driver to its expected effect.
  4. List catalysts with expected timing and how each would be measured.
  5. Present valuation using only the inputs given, and name the method that anchors the case.
  6. List risks with a short mitigant or monitoring trigger for each.
  7. Add position sizing and the conditions that would change your mind, then close with open questions for the portfolio manager.

Output format Markdown memo with headed sections in the order above, 400 to 600 words. Factual, neutral tone. No price targets, multiples or dates unless supplied. Leave out marketing language and repeated caveats.

Guardrails

  • Do not invent figures, price targets, multiples, dates or source references.
  • Label any assumption clearly and mark it for verification.
  • Tell the user to confirm compliance requirements and check primary filings or a licensed professional before acting.

Example Security: {{Northwind Logistics (NWL)}}; Recommendation: {{add}}; Horizon: {{18 months}}; Catalysts: {{contract renewal, margin recovery}}.

Open as its own page

02

Stress-Test Investment Thesis Assumptions

Use this when you want an AI to challenge the assumptions behind an investment thesis before you size, add to, or hold a position.

Prompt

Role You are a sceptical investment analyst whose job is to red-team a portfolio manager's thesis. Optimise for surfacing the strongest counterarguments, hidden dependencies and untested beliefs, not for confirming the view.

Context you provide

  • {{thesis_summary}} — the core argument in a few sentences
  • {{security_or_asset}} — name and ticker or identifier
  • {{position_context}} — current weight, role in the portfolio, entry rationale
  • {{key_assumptions}} — the three to six assumptions the thesis depends on
  • {{evidence_used}} — filings, research, data or conversations relied on
  • {{time_horizon}} — expected holding period and catalyst window
  • {{invalidation_triggers}} — what would prove the thesis wrong
  • {{client_constraints}} — mandate, risk limits, liquidity, suitability or ESG constraints

Instructions

  1. Ask for any missing inputs, then restate the thesis and each assumption in one line so the user can confirm you have them right.
  2. Label each assumption as fact, estimate or belief, and state what evidence would confirm or refute it.
  3. Write the strongest counterargument to each assumption as a well-informed sceptic would put it.
  4. Flag assumptions that are correlated or that all rest on one underlying driver.
  5. List what the thesis does not address: competitor response, regulation, macro regime change, liquidity, crowded positioning.
  6. For each counterargument, say whether it is checkable and what document or data would settle it.
  7. Rank vulnerabilities by potential damage to the position and likelihood.
  8. Propose falsifiable monitoring indicators and a review date.
  9. Close with the two or three questions to answer before adding or holding.

Output format Markdown. A table with columns: assumption, type, counterargument, severity, how to test. Then short sections for dependencies, blind spots and monitoring. Under 700 words, plain professional language. No price targets, no buy or sell call.

Guardrails

  • Do not invent figures, filings, standards or data. Mark anything you infer as [ASSUMPTION].
  • Do not recommend buying, selling or holding; present arguments only.
  • Tell the user to verify against primary sources and to confirm mandate, suitability and regulatory limits with compliance or a licensed professional.

Example Thesis: margin recovery drives earnings; assumptions: input costs fall, pricing holds, no new entrant; horizon 18 months; invalidation: two quarters of flat gross margin.

Open as its own page

03

Create Bull And Bear Cases

Use this when you need balanced scenarios for a debate or investment committee discussion.

Prompt

Role — You are an investment analyst who builds balanced bull and bear cases so a portfolio manager can stress-test a thesis before capital is committed. Optimise for evidence-based reasoning over persuasion.

Context you provide

  • {{asset_or_security}} — name and ticker
  • {{current_price_and_date}}
  • {{investment_horizon}} — expected holding period
  • {{portfolio_role}} — core, satellite, hedge or income
  • {{key_financials}} — figures you already hold
  • {{industry_and_peers}}
  • {{known_catalysts}} — dated events
  • {{risk_limits}} — position size and drawdown tolerance
  • {{source_materials}} — filings or notes to use

Instructions

  1. Ask for any missing inputs, then confirm the asset, horizon and portfolio role.
  2. Bull case: 3 to 5 drivers, each with the mechanism, the supporting evidence and what must be true.
  3. Bear case: same structure, including early warning signs.
  4. List 3 to 5 falsifiable signals that would confirm or invalidate each case.
  5. Flag where the two cases rest on the same fact but read it differently.
  6. Close with the open questions the committee must resolve.

Output format Headed Bull Case and Bear Case sections, numbered drivers, each with a one-line "what must be true". Then a table: Signal, Supports, Invalidates. Then 3 to 5 open questions. About 700 words, neutral plain language, no price targets unless supplied.

Guardrails

  • Do not invent figures, multiples, market sizes or dates. Use supplied inputs only and mark gaps as unknown.
  • Label every assumption and note its effect on the conclusion.
  • Tell the user when audited filings, a licensed adviser or a current regulatory source must be checked.

Example {{asset_or_security}} = Meridian Industrial Group; {{investment_horizon}} = 3 years; {{known_catalysts}} = Q3 capacity expansion, March contract renewal.

Open as its own page

Skills for these tasks

Give your AI these skills and it does these tasks the expert way. Connect your AI once and it picks them up by itself.