@AiwithYasir: 🚨 BREAKING: Perplexity Compute...
@AiwithYasir
15 views
Mar 16, 2026
1
🚨 BREAKING: Perplexity Computer just became the most dangerous tool on a public market desk.
Perplexity started out as an AI search engine but their new product Computer turns it into an AI research analyst that does real work.
Here are 8 prompts that turn Computer into a full investment analyst with real-time filings, cited sources, and zero hallucinated numbers 👇
(Save for later)
Perplexity started out as an AI search engine but their new product Computer turns it into an AI research analyst that does real work.
Here are 8 prompts that turn Computer into a full investment analyst with real-time filings, cited sources, and zero hallucinated numbers 👇
(Save for later)
2
1/ LONG/SHORT EQUITY THESIS
Task: Build a complete investment thesis for [COMPANY NAME / TICKER] with a 12-18 month time horizon.
Search and retrieve:
- Latest annual and quarterly filings (10-K, 10-Q)
- Analyst consensus estimates and recent revision direction
- Last 2 earnings call transcripts
- Recent news flow (past 90 days)
- Current valuation multiples vs. 5-year historical range and sector peers
Analysis framework:
1. Identify the variant perception: what does consensus currently believe vs. what the retrieved data actually shows
2. Build normalized earnings power in base, bull, and bear case with specific drivers sourced from filings
3. Map 3 catalysts with estimated timing that could close the gap between current price and intrinsic value
3. Construct valuation range using comparable company multiples and DCF cite the source for every input
5. Define entry, add, and exit conditions
Constraints: Every estimate requires a cited source. Flag where retrieved data contradicts management guidance. Separate what is priced in from what is not. Do not synthesize a bull case from press releases.
Output: Variant perception statement (2 sentences), earnings power table across 3 scenarios with sourced assumptions, catalyst calendar with probability weights, valuation bridge, position framework.
Task: Build a complete investment thesis for [COMPANY NAME / TICKER] with a 12-18 month time horizon.
Search and retrieve:
- Latest annual and quarterly filings (10-K, 10-Q)
- Analyst consensus estimates and recent revision direction
- Last 2 earnings call transcripts
- Recent news flow (past 90 days)
- Current valuation multiples vs. 5-year historical range and sector peers
Analysis framework:
1. Identify the variant perception: what does consensus currently believe vs. what the retrieved data actually shows
2. Build normalized earnings power in base, bull, and bear case with specific drivers sourced from filings
3. Map 3 catalysts with estimated timing that could close the gap between current price and intrinsic value
3. Construct valuation range using comparable company multiples and DCF cite the source for every input
5. Define entry, add, and exit conditions
Constraints: Every estimate requires a cited source. Flag where retrieved data contradicts management guidance. Separate what is priced in from what is not. Do not synthesize a bull case from press releases.
Output: Variant perception statement (2 sentences), earnings power table across 3 scenarios with sourced assumptions, catalyst calendar with probability weights, valuation bridge, position framework.
3
2/ EARNINGS QUALITY FORENSICS
Task: Run a comprehensive earnings quality assessment on [COMPANY NAME / TICKER] to determine whether reported earnings accurately reflect economic reality.
Search and retrieve:
- Last 5 years of income statement, balance sheet, and cash flow statement from SEC filings
- Recent auditor commentary or restatement history
- Any accounting policy changes disclosed in filing footnotes
- Comparable earnings quality data for 3 sector peers
Analysis framework:
1. Calculate Beneish M-Score: retrieve all 8 required variables from filings and flag any above manipulation warning thresholds
2. Accrual ratio trend: compare net income to operating cash flow across 5 years, flag widening gaps with specific filing citations
3. Revenue recognition signals: DSO trend, deferred revenue movements, channel stuffing indicators in distributor commentary
4. Expense management: SG&A and R&D as a percentage of revenue over 5 years, flag unusual compressions
5. Score earnings quality 1-10 with the specific retrieved data points driving the score
Constraints: Classify every metric as clean, yellow flag, or red flag. Reference retrieved industry norms when classifying outliers. Link every flag to a specific line item in a specific filing.
Output: M-Score table with sourced variable breakdown, accrual analysis with filing citations, 5 ranked quality flags, overall quality score with rationale.2
Task: Run a comprehensive earnings quality assessment on [COMPANY NAME / TICKER] to determine whether reported earnings accurately reflect economic reality.
Search and retrieve:
- Last 5 years of income statement, balance sheet, and cash flow statement from SEC filings
- Recent auditor commentary or restatement history
- Any accounting policy changes disclosed in filing footnotes
- Comparable earnings quality data for 3 sector peers
Analysis framework:
1. Calculate Beneish M-Score: retrieve all 8 required variables from filings and flag any above manipulation warning thresholds
2. Accrual ratio trend: compare net income to operating cash flow across 5 years, flag widening gaps with specific filing citations
3. Revenue recognition signals: DSO trend, deferred revenue movements, channel stuffing indicators in distributor commentary
4. Expense management: SG&A and R&D as a percentage of revenue over 5 years, flag unusual compressions
5. Score earnings quality 1-10 with the specific retrieved data points driving the score
Constraints: Classify every metric as clean, yellow flag, or red flag. Reference retrieved industry norms when classifying outliers. Link every flag to a specific line item in a specific filing.
Output: M-Score table with sourced variable breakdown, accrual analysis with filing citations, 5 ranked quality flags, overall quality score with rationale.2
4
3/ EARNINGS CALL INTELLIGENCE
Task: Extract the intelligence from [COMPANY NAME / TICKER]'s most recent earnings call that moves the investment thesis.
Search and retrieve:
- Full transcript of the most recent earnings call
- Prior 2 earnings call transcripts for comparison
- Management guidance from the prior quarter
- Consensus estimates vs. actual results for the reported period
Analysis framework:
1. Guidance accuracy score: compare last quarter's guidance to this quarter's actuals across revenue, margin, and FCF
2. Language shift detection: flag specific changes in tone, hedging frequency, or emphasis vs. prior 2 calls with direct quotes
3. Analyst question quality map: score each management response as direct answer, partial deflection, or non-answer
4. High-signal extraction: identify 3 data points from the transcript that did not surface in post-earnings coverage
5. Thesis update: state specifically whether this call strengthens, weakens, or complicates the investment case
Constraints: Focus on what changed, not what was confirmed. Flag every deflection explicitly with the question that triggered it. Weight management credibility against prior guidance accuracy before taking forward estimates at face value.
Output: Guidance accuracy table (3 metrics, prior guidance vs. actual), 3 language shift flags with direct quotes, analyst question scorecard, 3 high-signal data points, one-paragraph thesis update.
Task: Extract the intelligence from [COMPANY NAME / TICKER]'s most recent earnings call that moves the investment thesis.
Search and retrieve:
- Full transcript of the most recent earnings call
- Prior 2 earnings call transcripts for comparison
- Management guidance from the prior quarter
- Consensus estimates vs. actual results for the reported period
Analysis framework:
1. Guidance accuracy score: compare last quarter's guidance to this quarter's actuals across revenue, margin, and FCF
2. Language shift detection: flag specific changes in tone, hedging frequency, or emphasis vs. prior 2 calls with direct quotes
3. Analyst question quality map: score each management response as direct answer, partial deflection, or non-answer
4. High-signal extraction: identify 3 data points from the transcript that did not surface in post-earnings coverage
5. Thesis update: state specifically whether this call strengthens, weakens, or complicates the investment case
Constraints: Focus on what changed, not what was confirmed. Flag every deflection explicitly with the question that triggered it. Weight management credibility against prior guidance accuracy before taking forward estimates at face value.
Output: Guidance accuracy table (3 metrics, prior guidance vs. actual), 3 language shift flags with direct quotes, analyst question scorecard, 3 high-signal data points, one-paragraph thesis update.
5
4/ SHORT THESIS CONSTRUCTION
Task: Build a complete short thesis for [COMPANY NAME / TICKER] with a 6-18 month horizon.
Search and retrieve:
- Revenue and gross margin trend by quarter (last 8 quarters)
- FCF conversion history and current debt maturity schedule
- Short interest data, cost to borrow, and short interest trend (past 12 months)
- Insider selling filings (Form 4s, past 6 months)
- Current valuation multiples vs. 3-year historical range and sector peers
Analysis framework:
1. Identify the fundamental deterioration vector: the specific metric declining that the current price does not fully reflect
2. Build the earnings revision path: how far below current consensus could estimates move, and what specifically drives each step down
3. Balance sheet stress test: debt maturity schedule against current FCF generation and refinancing conditions
4. Sentiment setup: short interest trend, analyst ratings distribution, institutional ownership direction from latest 13F filings
5. Squeeze scenario model: what triggers a squeeze, what the carry cost is at current borrow rate, how to structure around it
Constraints: Do not short valuation alone. A fundamental deterioration catalyst is required. Source insider selling data from retrieved Form 4 filings. Model borrow cost drag explicitly.
Output: Deterioration vector (1 paragraph), earnings revision path across 3 scenarios, balance sheet stress test table, sentiment setup from retrieved filings, squeeze risk assessment with trigger conditions.
Task: Build a complete short thesis for [COMPANY NAME / TICKER] with a 6-18 month horizon.
Search and retrieve:
- Revenue and gross margin trend by quarter (last 8 quarters)
- FCF conversion history and current debt maturity schedule
- Short interest data, cost to borrow, and short interest trend (past 12 months)
- Insider selling filings (Form 4s, past 6 months)
- Current valuation multiples vs. 3-year historical range and sector peers
Analysis framework:
1. Identify the fundamental deterioration vector: the specific metric declining that the current price does not fully reflect
2. Build the earnings revision path: how far below current consensus could estimates move, and what specifically drives each step down
3. Balance sheet stress test: debt maturity schedule against current FCF generation and refinancing conditions
4. Sentiment setup: short interest trend, analyst ratings distribution, institutional ownership direction from latest 13F filings
5. Squeeze scenario model: what triggers a squeeze, what the carry cost is at current borrow rate, how to structure around it
Constraints: Do not short valuation alone. A fundamental deterioration catalyst is required. Source insider selling data from retrieved Form 4 filings. Model borrow cost drag explicitly.
Output: Deterioration vector (1 paragraph), earnings revision path across 3 scenarios, balance sheet stress test table, sentiment setup from retrieved filings, squeeze risk assessment with trigger conditions.
6
5/ MACRO REGIME POSITIONING
Task: Analyze the current macro regime and build a tactical positioning framework for public equities over the next 3-6 months.
Search and retrieve:
- Current GDP growth rate and trend direction (latest release)
- Inflation reading and momentum (last 3 months of data)
- Federal Reserve current policy rate and most recent forward guidance language
- Investment grade and high yield credit spread levels vs. 12-month average
- Current yield curve shape and 12-month change
Analysis framework:
1. Classify the macro regime using the retrieved data: identify the growth/inflation quadrant and current sub-phase
2. Pull historical analogs: the 2-3 closest macro environments from the past 40 years and how equities, rates, and credit performed
3. Factor and sector tilt: which equity factors and sectors historically outperform in this specific retrieved regime
4. Consensus positioning assessment: where is the market leaning based on recent positioning data, and where is that crowding vulnerable
5. Tactical allocation framework: rate sensitivity posture, equity exposure direction, sector tilts, tail hedge structure
Constraints: Every positioning recommendation requires a sourced historical basis. Flag where consensus positioning creates asymmetric vulnerability. Separate structural views (12+ months) from tactical trades (3-6 months).
Output: Regime classification with confidence level, historical analog table with sourced performance data, factor/sector tilt matrix, consensus vulnerability points, 3 positioning recommendations with entry rationale and exit conditions.
Task: Analyze the current macro regime and build a tactical positioning framework for public equities over the next 3-6 months.
Search and retrieve:
- Current GDP growth rate and trend direction (latest release)
- Inflation reading and momentum (last 3 months of data)
- Federal Reserve current policy rate and most recent forward guidance language
- Investment grade and high yield credit spread levels vs. 12-month average
- Current yield curve shape and 12-month change
Analysis framework:
1. Classify the macro regime using the retrieved data: identify the growth/inflation quadrant and current sub-phase
2. Pull historical analogs: the 2-3 closest macro environments from the past 40 years and how equities, rates, and credit performed
3. Factor and sector tilt: which equity factors and sectors historically outperform in this specific retrieved regime
4. Consensus positioning assessment: where is the market leaning based on recent positioning data, and where is that crowding vulnerable
5. Tactical allocation framework: rate sensitivity posture, equity exposure direction, sector tilts, tail hedge structure
Constraints: Every positioning recommendation requires a sourced historical basis. Flag where consensus positioning creates asymmetric vulnerability. Separate structural views (12+ months) from tactical trades (3-6 months).
Output: Regime classification with confidence level, historical analog table with sourced performance data, factor/sector tilt matrix, consensus vulnerability points, 3 positioning recommendations with entry rationale and exit conditions.
7
6/ ACTIVIST AND EVENT-DRIVEN SETUP
Task: Analyze [COMPANY NAME / TICKER] as a potential activist or event-driven opportunity and size the probability-weighted return.
Search and retrieve:
- Current market cap, EV, trailing EBITDA, and FCF yield
- Share price performance vs. sector peers over 1 and 3 years
- Capital allocation history from filings: buybacks, dividends, M&A
13D/13G filings to identify any current activist ownership
- Proxy filing for board composition, governance structure, and shareholder proposal history
Steps:
1. Quantify the value gap: the difference between intrinsic value and current price, and why it has persisted
2. Map value creation levers from retrieved filings: operational improvement, capital structure change, strategic alternatives
3. Activist viability: ownership concentration from 13F data, board entrenchment mechanisms, poison pill provisions
4. Scenario return table: base (management self-help), catalyst (activist or strategic buyer), broken case
5. Near-term catalyst calendar: 3 specific events within 12 months that could close the gap
Constraints: Do not conflate cheap with activist-viable. Governance defenses must be sourced from actual proxy filings. Assign explicit probability weights to each scenario.
Output: Value gap analysis, value creation lever table, activist viability score, scenario return table with probability weights, catalyst calendar.
Task: Analyze [COMPANY NAME / TICKER] as a potential activist or event-driven opportunity and size the probability-weighted return.
Search and retrieve:
- Current market cap, EV, trailing EBITDA, and FCF yield
- Share price performance vs. sector peers over 1 and 3 years
- Capital allocation history from filings: buybacks, dividends, M&A
13D/13G filings to identify any current activist ownership
- Proxy filing for board composition, governance structure, and shareholder proposal history
Steps:
1. Quantify the value gap: the difference between intrinsic value and current price, and why it has persisted
2. Map value creation levers from retrieved filings: operational improvement, capital structure change, strategic alternatives
3. Activist viability: ownership concentration from 13F data, board entrenchment mechanisms, poison pill provisions
4. Scenario return table: base (management self-help), catalyst (activist or strategic buyer), broken case
5. Near-term catalyst calendar: 3 specific events within 12 months that could close the gap
Constraints: Do not conflate cheap with activist-viable. Governance defenses must be sourced from actual proxy filings. Assign explicit probability weights to each scenario.
Output: Value gap analysis, value creation lever table, activist viability score, scenario return table with probability weights, catalyst calendar.
8
7/ 13F HOLDINGS INTELLIGENCE
Task: Analyze recent 13F filings to extract institutional positioning intelligence on [SECTOR / THEME / SPECIFIC STOCK].
Search and retrieve:
- Most recent 13F filings for 5-10 relevant institutional investors
- Quarter-over-quarter position size changes for each fund
- New positions initiated and full exits in the most recent quarter
- Any 13D or 13G activist filings in the sector over the past 6 months
Steps:
1. Map the smart money consensus: which names appear as new buys or significant adds across multiple funds
2. Identify exit signals: positions being reduced or closed across multiple funds simultaneously
3. Flag conviction divergence: where top funds are taking opposite positions in the same name and why
4. Assess crowding risk: holdings with excessive concentration across the retrieved fund universe
5. Extract 3 actionable insights: names with strong institutional accumulation that have not yet moved
Constraints: 13F data is 45 days delayed, state this explicitly in the output. Flag where ownership concentration creates liquidity risk on the exit.
Output: Smart money consensus table, conviction divergence analysis, crowding risk flags, 3 actionable positioning insights with sourced fund accumulation data.
Task: Analyze recent 13F filings to extract institutional positioning intelligence on [SECTOR / THEME / SPECIFIC STOCK].
Search and retrieve:
- Most recent 13F filings for 5-10 relevant institutional investors
- Quarter-over-quarter position size changes for each fund
- New positions initiated and full exits in the most recent quarter
- Any 13D or 13G activist filings in the sector over the past 6 months
Steps:
1. Map the smart money consensus: which names appear as new buys or significant adds across multiple funds
2. Identify exit signals: positions being reduced or closed across multiple funds simultaneously
3. Flag conviction divergence: where top funds are taking opposite positions in the same name and why
4. Assess crowding risk: holdings with excessive concentration across the retrieved fund universe
5. Extract 3 actionable insights: names with strong institutional accumulation that have not yet moved
Constraints: 13F data is 45 days delayed, state this explicitly in the output. Flag where ownership concentration creates liquidity risk on the exit.
Output: Smart money consensus table, conviction divergence analysis, crowding risk flags, 3 actionable positioning insights with sourced fund accumulation data.
9
8/ COMPETITIVE INTELLIGENCE BRIEF
Task: Build a real-time competitive intelligence brief on [COMPANY NAME / TICKER] and its 3-5 primary competitors.
Search and retrieve:
- Latest earnings results and guidance for each competitor, past 2 quarters
- Recent product announcements, pricing changes, and market share data
- Litigation, regulatory actions, or supply chain disclosures from recent filings
- Analyst commentary on competitive dynamics, past 60 days
Steps:
1. Map the current competitive position: market share direction, pricing power evidence from margin data, customer retention signals
2. Identify the inflection point: which competitor is gaining ground and what specific retrieved evidence supports the claim
3. Flag asymmetric risks: regulatory, litigation, or supply chain exposure one competitor carries that the others don't
4. Extract alternative data signals: any web, app, or review trend data that leads reported financials
5. Translate to investment implications: how the competitive landscape affects the thesis on the primary holding
Constraints: Separate retrieved facts from analyst opinion in every section. Flag where competitive data is estimated rather than disclosed.
Output: Competitive position map, inflection point analysis, asymmetric risk table by competitor, alternative data signals, 3 investment implications for the primary holding.
Task: Build a real-time competitive intelligence brief on [COMPANY NAME / TICKER] and its 3-5 primary competitors.
Search and retrieve:
- Latest earnings results and guidance for each competitor, past 2 quarters
- Recent product announcements, pricing changes, and market share data
- Litigation, regulatory actions, or supply chain disclosures from recent filings
- Analyst commentary on competitive dynamics, past 60 days
Steps:
1. Map the current competitive position: market share direction, pricing power evidence from margin data, customer retention signals
2. Identify the inflection point: which competitor is gaining ground and what specific retrieved evidence supports the claim
3. Flag asymmetric risks: regulatory, litigation, or supply chain exposure one competitor carries that the others don't
4. Extract alternative data signals: any web, app, or review trend data that leads reported financials
5. Translate to investment implications: how the competitive landscape affects the thesis on the primary holding
Constraints: Separate retrieved facts from analyst opinion in every section. Flag where competitive data is estimated rather than disclosed.
Output: Competitive position map, inflection point analysis, asymmetric risk table by competitor, alternative data signals, 3 investment implications for the primary holding.
10
What separates these from the prompts circulating on X:
Most investor prompts tell Perplexity to "research" a company. That produces a summary with a few financial metrics and no citations worth trusting.
These prompts give Perplexity a complete retrieval and analysis architecture every time:
→ Specific data sources named: 10-K, 10-Q, 13F, Form 4, proxy filings
→ A step-by-step methodology executed on retrieved data
→ A goal state that defines what institutional-grade output looks like
→ Constraints that force citation and flag estimated vs. reported data
→ A structured output format a PM can present without reformatting
Perplexity's edge is real-time cited retrieval. These prompts are built to extract that edge fully.
Most investor prompts tell Perplexity to "research" a company. That produces a summary with a few financial metrics and no citations worth trusting.
These prompts give Perplexity a complete retrieval and analysis architecture every time:
→ Specific data sources named: 10-K, 10-Q, 13F, Form 4, proxy filings
→ A step-by-step methodology executed on retrieved data
→ A goal state that defines what institutional-grade output looks like
→ Constraints that force citation and flag estimated vs. reported data
→ A structured output format a PM can present without reformatting
Perplexity's edge is real-time cited retrieval. These prompts are built to extract that edge fully.
11
I hope you've found this thread helpful.
Follow me @AiwithYasir for more.
Like/Repost the quote below if you can:
Follow me @AiwithYasir for more.
Like/Repost the quote below if you can:
View Tweet