Cuiar
Sign inDownload

Estimate the size of a market

A top-down and a bottom-up estimate, with the source for each number and each step of the math.

  • You start it: When you start it
  • Odyssey deep research
Use in CuiarRun from your AI agent

What it does

The task

Estimate the yearly market size for product in region. Make a top-down estimate from official statistics, industry reports and the annual reports of the largest sellers. Make a bottom-up estimate: the number of buyers times the average yearly spend of each buyer. Read at least 12 sources, and give each number with its source and year. Put both calculations in a new Google Sheet named Market size, one row for each step. Then write a summary of 8 lines or fewer: the two estimates, the gap between them, and the 3 assumptions with the most effect.

  • It works in any government site, Google Scholar and Google Sheets, in the workspace you pick, and signs in with passwords from your Cuiar vault.
  • It runs once, when you start it.
  • It uses Odyssey, the deep-research mode of the Pro and Team plans, and keeps a citation for each fact.

What you give it

BlankWhat to giveExample
productThe product or service, as a buyer names itHeat pumps for single-family homes
regionA country or a regionGermany

What you get back

An example run with the example values above. Your run uses your own data.

Market size: heat pumps for single-family homes, Germany, 2025

Top-down: 4.1 billion EUR (industry association: 290,000 units x 14,200 EUR average with installation)

Bottom-up: 3.6 billion EUR (15.9 million houses x 2.1% yearly heating replacement x 10,800 EUR)

Gap: 12%. The top-down number includes some two-family houses.

Assumptions with the most effect:

  • Yearly replacement rate (1.8% to 2.5%)
  • Share of new heating systems that are heat pumps (38% to 52%)
  • Average price after subsidies

Sheet: Market size, 14 rows, 16 sources

Run it in Cuiar

  1. 01

    Open it

    Click Use in Cuiar on this page. The side panel opens with the task in the composer.

  2. 02

    Fill in 2 blanks

    Type product and region. Tab moves to the next blank.

  3. 03

    Run it

    Run sends it to the agent. Follow each step in the panel, and stop it at any time.

From the terminal

cuiar exec --odyssey "Estimate the yearly market size for Heat pumps for single-family homes in Germany. Make a top-down estimate from official statistics, industry reports and the annual reports of the largest sellers. Make a bottom-up estimate: the number of buyers times the average yearly spend of each buyer. Read at least 12 sources, and give each number with its source and year. Put both calculations in a new Google Sheet named Market size, one row for each step. Then write a summary of 8 lines or fewer: the two estimates, the gap between them, and the 3 assumptions with the most effect."

Run it from your AI agent

Claude Code, Codex, Cursor and other MCP clients reach Cuiar at https://mcp.cuiar.com/mcp. Add the server one time, then ask for the task in plain words, or call run_task yourself.

1. Add Cuiar to Claude Code

claude mcp add --transport http cuiar https://mcp.cuiar.com/mcp

2. Ask your agent

Use the Cuiar tool run_task to run my "Estimate the size of a market" template with product = Heat pumps for single-family homes; region = Germany.

Setup for other agents: AI agents.

The tool call

{
  "name": "run_task",
  "arguments": {
    "task": "Estimate the yearly market size for Heat pumps for single-family homes in Germany. Make a top-down estimate from official statistics, industry reports and the annual reports of the largest sellers. Make a bottom-up estimate: the number of buyers times the average yearly spend of each buyer. Read at least 12 sources, and give each number with its source and year. Put both calculations in a new Google Sheet named Market size, one row for each step. Then write a summary of 8 lines or fewer: the two estimates, the gap between them, and the 3 assumptions with the most effect.",
    "mode": "odyssey"
  }
}

Related templates

All research templates

  • Data

    Extract study results into a table

    Design, sample size, outcome and effect size with confidence interval from each paper, in one sheet.

    You start it: When you start it
    • PubMed
    • Google Scholar
    • Google Sheets

  • ResearchOdyssey

    Research a topic into a cited report

    Many sources, compared, in one report with a citation for each claim.

    You start it: When you start it
    • Google Scholar
    • Wikipedia
    • Google Docs

  • ResearchOdyssey

    Write a literature review on a research question

    Recent studies grouped by theme, what they agree on, where the evidence is weak, and a full reference list.

    You start it: When you start it
    • Google Scholar
    • Semantic Scholar
    • PubMed
    • +1 more: Google Docs

  • Research

    Fact-check the claims in a draft

    Each claim marked true, false, partly true or unclear, with a primary source and the correct version.

    You start it: When you start it
    • Google Docs
    • Wikipedia
    • Any government site
    • +1 more: Google Scholar

  • ResearchOdyssey

    Map the competitors in a market

    Each competitor with its product, target customer, price, funding and size, and the gaps no one covers.

    You start it: When you start it
    • Crunchbase
    • G2
    • Google Sheets

  • ResearchOdyssey

    Search for prior art before you file a patent

    The closest patents and papers, ranked, with the claims that overlap and how your idea differs.

    You start it: When you start it
    • Google Patents
    • Google Scholar