Investment Due Diligence Assistant

1. Overview

The Investment Due Diligence Assistant gathers a company’s pitch deck, its financial statements, and any relevant news articles, then condenses this information into a concise, structured report that an analyst can use to evaluate an investment opportunity.

2. Business Value

A structured diligence report saves analysts time, ensures that all critical data points are captured consistently, reduces the chance of overlooking important information, and provides a single, easy‑to‑read document that can be shared with partners or investment committees.

3. Operational Context

When it should run	Who uses it	How often
When a new potential investment is identified and a quick, yet thorough, review of the target company is needed.	Venture‑capital analysts, investment associates, and senior partners who need an overview before deeper research or a meeting with the founders.	Once for each target company (or each new funding round) – a new run whenever a new company is being evaluated.

4. Inputs

Input Name	Type	Details Provided
Company Name	Text	The legal or operating name of the target company (e.g., “Acme AI”).
Pitch Deck	Document (PDF)	The most recent investor pitch deck. It typically contains a company overview, market analysis, product description, business model, traction, financial highlights, and the team.
Financial Statements	Document (PDF or spreadsheet)	The latest audited or unaudited financial statements (income statement, balance sheet, cash‑flow statement) and any key‑metric tables (e.g., revenue, EBITDA, cash balance).
News Articles	List of Documents (PDF)	One or more PDFs containing press releases, news stories, analyst reports, or other external commentary about the company.
Additional Notes (optional)	Text	Any specific focus areas, questions, or concerns the analyst wants highlighted (e.g., “Focus on revenue growth and recent partnership”).

Note: All files must be provided in the specified format; no external websites or live data sources will be accessed.

5. Outputs

Output Name	Contents	Formatting Rules
Diligence Report	A plain‑language report containing the following sections in order: 1) Company Overview, 2) Business Model, 3) Market Opportunity, 4) Product / Technology, 5) Competitive Landscape, 6) Traction & Milestones, 7) Financial Summary, 8) Risk Assessment, 9) Investment Summary, 10) Sources. Each section uses a clear heading (e.g., “## Company Overview”). Bullet points list items; tables are used only for the Financial Summary.	Use a neutral, professional tone. All headings in bold, dates in `YYYY‑MM‑DD` format, monetary values in USD with two decimal places (e.g., `$1,234,567.00`). The “Sources” section lists every input file name and the page numbers referenced. No new IDs are generated.

6. Detailed Plan & Execution Steps

Verify Input Availability – Confirm that the Company Name, Pitch Deck PDF, Financial Statements document, and at least one News Article PDF are present. If any mandatory input is missing, halt the process and flag for manual review.
Open the Pitch Deck – Review each slide and extract:
- Company’s mission and value proposition.
- Product description and stage.
- Market size and target segment.
- Business model (how revenue is generated).
- Traction metrics (customers, revenue, growth).
- Financial highlights (revenue, cash, runway).
- Team composition and key hires.
Extract Financial Data – From the financial statements:
- Revenue (current period and prior period).
- Gross profit, EBITDA, net profit/loss.
- Cash balance, burn rate, runway in months.
- Key growth rates (YoY %).
- Any footnotes or unusual items.
Read News Articles – For each PDF:
- Note date and source of each article.
- Capture new events (funding rounds, partnership deals, product launches, regulatory approvals, or legal issues).
- Flag any conflicting statements with the pitch deck or financials.
Organize Extracted Information – Fill in a working outline with the following sections:
1. Company Overview – name, location, founding year, mission.
2. Business Model – description of revenue streams and pricing.
3. Market Opportunity – TAM, SAM, SOM, growth rate.
4. Product / Technology – core product, tech stack, development stage.
5. Competitive Landscape – main competitors, differentiation, barriers to entry.
6. Traction & Milestones – customers, ARR, user growth, major achievements.
7. Financial Summary – use a table (see step 8).
8. Risk Assessment – list market, product, regulatory, financial, and execution risks.
9. Investment Summary – 3‑5 bullet points summarizing why the company is attractive or not.
10. Sources – list each input file with page references.
Create Financial Summary Table (place within the Financial Summary section):

Metric FY2023 (USD) FY2022 (USD) YoY %
Revenue $X,XXX,XXX $Y,YYY,YYY Z%
Gross Profit $... $... ...
EBITDA $... $... ...
Cash Balance (End of Period) $... $... ...
Burn Rate (monthly) $... $... ...
Runway (months) X Y –
Write the Diligence Report – Using the outline and the financial table, compose each section in plain language, following the formatting rules. Keep each section concise (usually 1–3 paragraphs) and use bullet points for lists.
Add Sources Section – List each input file (e.g., “AcmeAI_PitchDeck.pdf – Slides 2–8”, “AcmeAI_Financials_Q1_2024.xlsx – Sheet ‘Income Statement’”).
Quality Review –
- Verify every required section is present.
- Cross‑check all numbers against the original documents.
- Ensure dates and numbers follow the formatting rules.
- Confirm that each fact is attributed to a source (slide number, spreadsheet row, article page).
- Ensure the tone remains neutral and professional.
Finalize and Export – The completed Diligence Report is ready for distribution to the investment committee or for further internal review.

7. Validation & Quality Checks

Section completeness – All 10 sections listed in the output definition must be present.
Numeric consistency – Every figure in the Financial Summary must match the numbers in the Financial Statements. Any discrepancy must be noted in the “Risk Assessment” section.
Source citation – Every data point must have a source reference (page number, slide number, or spreadsheet cell).
Formatting – Headings are bold and capitalized, dates use YYYY‑MM‑DD, monetary figures include a dollar sign and two decimal places.
Tone check – The language is neutral, professional, and free of personal opinions.
Missing data flag – If any required data (e.g., revenue) is missing, the report must contain a clear note: “Data not provided – analysis of this item is unavailable.”
Conflict resolution – If the pitch deck and financial statements report different numbers for the same metric, list both values, cite each source, and flag the inconsistency in the “Risk Assessment”.

8. Special Rules / Edge Cases

Missing Pitch Deck – Proceed with the other inputs. The “Company Overview” and “Business Model” sections will be brief and rely on news articles and the financial statements. Note the missing deck in the “Risk Assessment”.
Missing Financial Statements – The “Financial Summary” and any financial‑ratio analysis are omitted. Include a note in the “Risk Assessment” that financial analysis could not be performed.
No News Articles – Skip the “News & External Commentary” section. If the company has a recent press release not provided, note that “No external news sources were supplied”.
Conflicting Information – List both versions with their sources, and add a comment in “Risk Assessment” describing the conflict. Do not choose one version without justification.
Additional Notes – If the user’s optional “Additional Notes” request focus on a specific area (e.g., “emphasize recent partnership”), ensure the “Investment Summary” and “Risk Assessment” address that request.
Large Number of Articles – If more than ten news PDFs are supplied, limit the summary to the five most recent, or those that contain unique information not already covered.
Currency Conversion – If any financial figures are in a foreign currency, note the original currency and provide a conversion note stating “Values converted to USD using the exchange rate in effect on the date of the financial statement, if available”. If no rate is given, report in the original currency and flag for clarification.
Failure to Open a File – If a file cannot be opened (corrupt or unsupported format), halt the process and flag the specific file for manual review. No partial output should be generated.
Duplicate Files – If the same PDF appears more than once, use only the first instance and ignore duplicates. Document the removal of duplicates in the “Sources” section.

9. Example

Input (for a single run)

Company Name: Acme AI
Pitch Deck: AcmeAI_PitchDeck.pdf (slides 2‑12 contain core information)
Financial Statements: AcmeAI_Financials_Q1_2024.xlsx (income statement, balance sheet, cash‑flow statement)
News Articles:
- AcmeAI_FundingAnnouncement.pdf (press release, 2024‑03‑15)
- AcmeAI_PartnershipNews.pdf (tech blog, 2024‑04‑02)
Additional Notes: “Emphasize revenue growth and any upcoming product launches.”

Expected Output – Diligence Report (excerpt)

Company Overview

Name: Acme AI
Founded: 2019, San Francisco, CA.
Mission: To democratize artificial‑intelligence‑powered data analytics for mid‑size enterprises.

Business Model

SaaS subscription model, three pricing tiers (Basic, Professional, Enterprise).
Recurring revenue from 120 enterprise customers, average contract value $45,000 per year.

Market Opportunity

Total Addressable Market (TAM): $15 B (global AI‑analytics market).
Serviceable Available Market (SAM): $3 B (U.S. mid‑size firms).
Growth Rate: 22 % CAGR (2021‑2024).

Product / Technology

Cloud‑based platform, uses proprietary “Auto‑Insight” engine.
Current version 2.1, released 2023‑09‑30.
Planned feature: real‑time anomaly detection (Q4‑2024).

Competitive Landscape

Primary competitors: DataVision, InsightWorks, and Analytica.
Differentiator: “Auto‑Insight” reduces data‑prep time by 50 % vs. competitors.

Traction & Milestones

2023‑2024 Revenue Growth: 48 % YoY (from $6.2 M to $9.2 M).
Recent Funding: $12 M Series B (2024‑03‑15) – led by Capital Partners.
Partnership: Integrated with CloudX Platform (2024‑04‑02).

Financial Summary

Metric	FY2023 (USD)	FY2022 (USD)	YoY %
Revenue	$9,200,000	$6,200,000	48%
Gross Profit	$4,500,000	$2,900,000	55%
EBITDA	$1,200,000	$800,000	50%
Cash Balance (end of period)	$3,600,000	$2,400,000	–
Burn Rate (monthly)	$150,000	$150,000	0%
Runway (months)	24	16	–

Risk Assessment

Market Risk: Slower adoption in non‑tech sectors could limit growth.
Product Risk: Upcoming feature “real‑time anomaly detection” is not yet released; timeline risk.
Regulatory Risk: None identified in the provided documents.
Financial Risk: Cash burn is stable but the runway (24 months) requires additional financing if growth slows.

Investment Summary

Strong revenue growth and a high‑margin SaaS model.
Recent $12 M Series B funding adds credibility and runway.
Competitive advantage through proprietary “Auto‑Insight” engine.
Risks are manageable; recommend proceeding to deeper technical due‑diligence and valuation.

Sources

AcmeAI_PitchDeck.pdf – Slides 2‑12.
AcmeAI_Financials_Q1_2024.xlsx – Income statement, balance sheet, cash‑flow.
AcmeAI_FundingAnnouncement.pdf – Page 1, date 2024‑03‑15.
AcmeAI_PartnershipNews.pdf – Page 1, date 2024‑04‑02.

Appendix A – FAQ

1. What if the pitch deck does not contain a financial summary?

Use the Financial Statements document to extract all financial metrics. If the pitch deck mentions different figures, note the discrepancy in the Risk Assessment.

2. How should I handle a financial statement that uses a different currency?

Keep the original currency in the report and note the conversion status. If a conversion rate is known, include a footnote with the exchange rate used and the source of the rate.

3. What if two news articles provide contradictory information?

List both versions, cite each source, and flag the inconsistency in the Risk Assessment. Do not make a judgment about which is correct unless supported by a third source.

4. Can I include screenshots from the PDFs?

No. The output must be plain‑text; the “Sources” section should reference page or slide numbers instead of embedding images.

5. How do I format large numbers (e.g., millions)?

Use standard US formatting: $1,234,567.00. For millions, use $1.23M only if the original document expresses the number in that format; otherwise use the full amount.

6. What if a financial line is missing (e.g., cash balance)?

Indicate “Data not provided” in the Financial Summary table and note the missing information in the Risk Assessment.

7. How should I handle multiple versions of a pitch deck?

Use the most recent version (indicated by the file date or version number). If uncertain, ask for clarification in the “Additional Notes” field before proceeding.

8. Should I include the analyst’s name in the report?

No. The report should be anonymous and focus only on the company data.

9. How do I ensure the tone stays neutral?

Avoid adjectives like “excellent” or “poor”. Use factual statements (e.g., “Revenue grew 48 % YoY") and keep the language objective.

10. What if the financial statements are in a spreadsheet with multiple sheets?

Identify the sheet name and cell range for each metric in the Sources section (e.g., “Income Statement – Cells B5:B7”).

Appendix B – Glossary

Term	Definition
Pitch Deck	A concise presentation (usually PDF) used by startups to summarize their business, product, market, and financials for prospective investors.
Financial Statements	Formal reports (income statement, balance sheet, cash‑flow statement) that show a company’s financial performance and position.
Revenue	Total amount of money earned from selling products or services before any deductions.
Gross Profit	Revenue minus cost of goods sold (COGS); measures profit after direct production costs.
EBITDA	Earnings before interest, taxes, depreciation, and amortization; a measure of operating performance.
Burn Rate	The rate at which a company spends cash on a monthly basis; negative cash flow.
Runway	The number of months a company can continue operating at its current burn rate before cash runs out.
TAM (Total Addressable Market)	The total revenue opportunity available for a product or service if 100 % market share is achieved.
SAM (Serviceable Available Market)	Portion of the TAM that a company’s products or services can realistically target.
SOM (Serviceable Obtainable Market)	The share of SAM that a company realistically expects to capture.
Series A / B / C	Rounds of equity financing for a company; each “Series” represents a distinct funding round.
Risk Assessment	A systematic evaluation of potential risks that could affect the success of the investment.
Investment Summary	A brief, bullet‑pointed synthesis of the key reasons for and against investing.
Citation	Reference to the exact source (document name, page/slide number, or cell) where a piece of data originates.

Appendix C – Reference Material

C.1 Financial Metrics Definitions

Metric	Definition
Revenue	Total earnings from the sale of goods or services before any deductions.
Cost of Goods Sold (COGS)	Direct costs of producing goods or delivering services (e.g., materials, labor).
Gross Profit	Revenue minus COGS. Indicates the profitability of core operations.
Operating Expenses	Expenses incurred from normal business activities (e.g., R&D, sales, marketing, general and administrative).
EBITDA	Earnings before interest, taxes, depreciation, and amortization. Shows operating profitability without accounting and financing effects.
Net Income	Profit after all expenses, taxes, interest, and other items have been deducted.
Cash Balance	Total cash and cash equivalents on the balance sheet.
Cash Burn Rate	Average monthly cash outflow. Calculated as cash balance at start of period minus cash at end, divided by number of months.
Runway	Cash balance divided by monthly burn rate (in months).
Revenue Growth Rate (YoY)	((Current Year Revenue – Prior Year Revenue) / Prior Year Revenue) * 100.
Gross Margin %	(Gross profit / Revenue) * 100.
Operating Margin %	(EBITDA / Revenue) * 100.
Net Margin %	(Net income / Revenue) * 100.
Current Ratio	Current assets / current liabilities.
Debt‑to‑Equity Ratio	Total debt / shareholder equity.

C.2 Risk Categories

Risk Category	Description
Market Risk	Risk that the market size, growth, or adoption may be lower than projected.
Product Risk	Risk that product development will be delayed, features may not meet expectations, or the technology becomes obsolete.
Regulatory Risk	Risk of new laws, regulations, or compliance requirements that could affect the business.
Financial Risk	Cash shortfall, high burn rate, insufficient runway, or adverse financing terms.
Team Risk	Key personnel turnover, lack of relevant experience, or inadequate leadership.
Execution Risk	Operational challenges, inability to meet milestones, or scaling issues.
Competitive Risk	New entrants or existing competitors gaining a superior position or technology.
Liquidity Risk	Inability to meet short‑term financial obligations due to insufficient cash or credit lines.

C.3 Style Guide for the Diligence Report

Tone: Neutral, professional, and concise.
Headings: Bold and capitalized (e.g., ## Company Overview).
Paragraphs: 1‑3 sentences each; avoid long blocks of text.
Bullets: Use for lists (e.g., product features, market drivers).
Numbers: Use commas for thousands, two decimal places for currency.
Dates: Format as YYYY‑MM‑DD.
Currency: All monetary values in USD unless otherwise noted. Use the $ symbol.
Tables: Use only for the Financial Summary; keep tables simple with clear column headings.
References: Use the format DocumentName.pdf – Page X or SpreadsheetName.xlsx – Sheet “XYZ” – Cell A1 for each data point.
Spelling & Grammar: Proofread for spelling errors and consistent use of terminology (e.g., “company” not “Company”).
No Jargon: Avoid technical terms such as “API”, “JSON”, “object”, “code”, etc. Use plain language.
No New IDs: Do not invent new identifiers (e.g., “ReportID-001”).
Consistent Terminology: Use “Company” to refer to the target, “Investor” for the analyst/VC.

C.4 Sample Diligence Report Template

Section	Content Description
Company Overview	Company name, location, founding year, mission statement, and brief description of the business.
Business Model	Revenue streams, pricing model, customer base, and any subscription or licensing details.
Market Opportunity	TAM, SAM, SOM values, market growth rate, target customer segment.
Product / Technology	Core product description, technology stack, development stage, roadmap highlights.
Competitive Landscape	Major competitors, differentiation points, barriers to entry.
Traction & Milestones	Number of customers/users, revenue milestones, product releases, major contracts.
Financial Summary	Table of financial metrics (Revenue, Gross Profit, EBITDA, Cash, Burn Rate, Runway).
Risk Assessment	List of key risks (market, product, regulatory, financial, team) with brief explanation.
Investment Summary	3‑5 bullet points summarizing why the investment is attractive or not.
Sources	List each source (document name, page/slide number) used to compile the report.

C.5 List of Prohibited Items

Personal identification information (e.g., social security numbers, personal phone numbers) of any individuals.
Any proprietary or confidential information that is not explicitly provided in the inputs.
External URLs, live web links, or references to online sources that have not been supplied as PDFs.
Generation of new system IDs, reference numbers, or any identifier that does not exist in the input data.

C.6 Citation Format

Document citations: DocumentName.pdf – Page X (or “Slide X” for a pitch deck).
Spreadsheet citations: FileName.xlsx – Sheet “Name” – Cell <Column><Row> (e.g., AcmeAI_Financials_Q1_2024.xlsx – Sheet “Income Statement” – Cell B7).
Multiple citations: Separate with a semicolon (e.g., AcmeAI_PitchDeck.pdf – Slide 5; AcmeAI_FundingAnnouncement.pdf – Page 2).
Date format in citations: YYYY‑MM‑DD.
Currency: Always include the currency symbol (e.g., $2,500,000.00).

C.7 Additional Reference Materials

C.7.1 List of Prohibited Content

Any content that violates privacy regulations (e.g., GDPR, CCPA).
Information that is not directly related to the company’s financial or business evaluation (e.g., unrelated personal anecdotes).
Any content that encourages or suggests illegal activity.

C.7.2 Style Guide for Numbers & Units

Numbers: Use comma separators for thousands (e.g., “$1,000,000”).
Percentages: Use % without spaces (e.g., “48%”).
Units: Use “USD” for currency; “%” for percentages; “months” for time durations.
Rounding: Round to two decimal places for monetary values, whole numbers for percentages unless the figure is less than 1% (then two decimal places).

C.7.3 Sample Citation in Text

“Revenue grew to $9,200,000 in FY2023, representing a 48% YoY increase (see AcmeAI_Financials_Q1_2024.xlsx – Sheet ‘Income Statement’ – Cell B4).”

Additional Notes

Always double‑check that the final report reflects the most up‑to‑date versions of the input files. If there are newer versions of a document, ask the requestor for clarification before finalizing.
Keep a log of any manual decisions (e.g., which conflicting number was chosen) for future audit purposes.
The SOP is designed for a single company per execution; do not combine multiple companies in a single report.

Benefit	Impact
Faster turnaround	Enables analysts to evaluate more opportunities in the same period
Higher accuracy	Reduces the chance of overlooking critical numbers or statements
Better alignment	Creates a common reference that all stakeholders can rely on
Increased confidence	Source citations and neutral tone reinforce credibility

Accelerate Investment Due Diligence