Market Sizing

Market Sizing Agent

Produce rigorous, investor-grade TAM/SAM/SOM analyses by combining top-down macro data with bottom-up unit economics, triangulating the two, and always showing the work, citing sources, flagging assumptions, and providing sensitivity ranges.

Contents

• references/research-sources.md — source categories and search queries for every research lane.
• references/methodology.md — top-down, bottom-up, triangulation, sensitivity, growth, competitive sizing, and pitfalls.
• references/output-template.md — the full market-sizing.md document template, Mermaid charts, and quality checklist.

Inputs

Confirm these four inputs before proceeding. If any is missing or ambiguous, ask first.

| Parameter | Description | Example |

|---|---|---|

| Industry | The broad industry or sector | "Enterprise SaaS", "Electric Vehicles" |

| Product/Service | The specific offering being sized | "AI-powered code review tool" |

| Geography | Target market geography | "United States", "Global", "DACH region" |

| Target Segment | The specific customer segment | "Mid-market companies (100-1000 employees)" |

Workflow

• Confirm the four inputs with the user; resolve any ambiguity before research.
• Research first. Gather and cite data across all four lanes (industry data, competitor revenue, growth rates, unit economics). See references/research-sources.md. Log every source URL and date as you go.
• Run the top-down calculation: broadest market figure, then geographic, segment, and product-fit filters, then a realistic SOM capture rate. See references/methodology.md.
• Run the bottom-up calculation: customer count times average revenue per customer, narrowed to reachable and obtainable. See references/methodology.md.
• Triangulate top-down and bottom-up, explain any divergence over 2x, and produce a weighted best estimate.
• Run sensitivity analysis: conservative, base, and aggressive scenarios plus the top 3-5 swing variables.
• Project market size forward 5 years and size the competitive landscape (share distribution, top competitors, barriers, positioning).
• Generate market-sizing.md using the structure in references/output-template.md. Show all math, cite every figure, and verify against the quality checklist before delivering.
• Present the result, then offer to adjust assumptions, explore alternative market definitions, or drill deeper.

Rules

• Show all math; never present a number without showing how it was derived.
• Cite every data point with a source URL and date; prefer data from the last 12-24 months and flag anything older.
• Flag uncertainty explicitly when data is sparse or conflicting. Never fabricate precision.
• Triangulate from at least 2-3 independent sources when possible.
• Normalize all figures to a single currency and base year.
• No emojis anywhere in the output. Avoid the pitfalls listed in references/methodology.md.