Hire an AI market size research report writer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A bottom-up size estimate with every input shown and the working behind it
• The public facts found for each input, with source and date, or a line saying none was found
• Each input marked finding or guess, with the guesses ranked by how much they move the total
• A market report with a range, every number labelled and the first guess to test

How it does the job well

• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

Mistakes it avoids

• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.
• Over-generalising across places, periods or groups.

What a good result looks like

An example, not your task: You are writing a plan or a deck and need a market size that holds up to questions.

• Estimate. Who has the problem, how many could buy and what they would pay, with the size as a range.
• Public facts. The public data found for each input, with source and date, and the inputs with none.
• Findings and guesses. Each input marked finding or guess, ranked by how much it moves the total.
• Market report. The range, every number labelled fact or guess, and the first guess to test.
• Hand-back summary. Each saved file, every MISSING line and the checks that could not run.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line, and no public fact appears without a source and a date.
• The report gives a range, and every number says fact or guess.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Carl Sagan and Charles Darwin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Estimate from the bottom up. Builds the market size from who has the problem, how many could buy and what they would pay, with every input and assumption shown. Hands step 2 the list of inputs.
• Find the public facts. Looks for public data for each input, such as census, trade statistics and filings, and records the source and date. Says so when nothing is found. Hands step 3 the facts.
• Separate findings from guesses. Marks each input as a finding with its source or a guess with its reasoning, and ranks the guesses by how much they move the total. Hands step 4 the split.
• Write the report. Writes the report with every number labelled, a range instead of one figure, and the guess to test first.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id size-a-market-and-separate-facts-from-guesses only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/size-a-market-and-separate-facts-from-guesses/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The market and who you would sell to, in one or two sentences
• What you already know or believe about its size
• Your price, or an idea of it
• The country or area you care about (optional)
• Your own data, such as sales or survey results, or a report you already have (optional)

Helpful context (optional)

• Your own sales or survey data
• Industry reports you have, with their methods
• Competitor filings or public numbers

Tools and access

• A chat AI that can browse the web: Step 2 looks up public data. Without browsing it lists where to look and marks each gap.
• Official statistics sites: Census, trade and health statistics are the facts behind the inputs.
• A spreadsheet: Holds the estimate so you can change an input and see the range move.
• Any good chat AI: Sorting and testing claims in text is work any strong chat AI does with this skill.
• A spreadsheet: Lets you check a proven line against the figures behind it.

Functions and deliverables

• Market size research report writer: Share the market, buyer problem and product idea. Get a bottom-up estimate, public sources, labelled assumptions and a market report.
  • A bottom-up size estimate with every input shown and the working behind it
  • The public facts found for each input, with source and date, or a line saying none was found
  • Each input marked finding or guess, with the guesses ranked by how much they move the total
  • A market report with a range, every number labelled and the first guess to test
• Market size estimator: Share your idea, customer counts and pricing. Get market-size estimates and a possible share, with sources and assumptions.
  • TAM, SAM and SOM estimates
  • Top-down and bottom-up workings
  • A willingness-to-pay view
  • Assumptions and sources list
  Source: sickn33.
• Public database fact finder: Name a fact and database. Get a dated result with its source, query and limits.
  • Retrieved records
  • Source, query and date
  • Record count check
  • A log someone else can rerun
  Source: K-Dense.
• Research evidence checker: Paste a report and find out which lines are proven, likely or just guesses. Get a clean version and a list of open questions.
  • A list of the key terms and what they mean in this report.
  • Every claim marked proven, likely or guess, with the observation behind it.
  • A rewritten report with the guesses taken out.
  • A separate list of open questions.
• Market research report writer: Name the market and decision. Get a source-linked report with market-size scenarios, assumptions and gaps made clear.
  • A sourced report
  • A claim and source table
  • Market size with assumptions
  • Forecast ranges
  • A list of limits
  Source: K-Dense.
• Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
  • A research folder with claims, methods and results
  • Every claim linked to its supporting table or log
  • Results tables copied with exact numbers
  • A record of dead ends and decisions
  • A short report on what was filled in and what was missing
  Source: Orchestra Research.
• Carl Sagan: Check a claim or explain a hard idea using Carl Sagan’s recorded approach. Stay curious, compare explanations and ask what the evidence can show.
  • Your problem worked on the way Carl Sagan would: their questions, their method, their push-back
  • The answer or the work, in Carl Sagan's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Charles Darwin: Build a case using Charles Darwin’s recorded approach. Keep facts that challenge your idea, face the hardest objections and show where the evidence stops.
  • Your problem worked on the way Charles Darwin would: their questions, their method, their push-back
  • The answer or the work, in Charles Darwin's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are writing a plan or a deck and need a market size that holds up to questions.
• Two sources give you numbers a factor of five apart.
• An investor or buyer asks where a market size figure came from.
• You want to know which inputs to test first, because they are guesses.

Limits to check before starting

• You cannot yet say who would buy. Use the Target market and pricing reviewer workflow first, then come back.
• You want to know whether your idea can win its market, not how large it is. Use the Business idea market reviewer workflow.
• A source you trust already sized the market and you only need it written up. Use the Market research report writer.
• You need survey sample sizes or a plan to test the guesses. Use the Market size and survey planner.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to your AI, such as Claude, and say "Follow HANDOFF.md". Use one that can browse the web, or tell it step 2 will be a list of where to look.
• Paste the market, who you would sell to and your price. Add any sales or survey data you have.
• After step 1, check that every input has a number and a reason. After step 2, open one source yourself to check it says what the AI says it does.
• Read the findings and guesses split. Test the top guess first, and update the report when it becomes a finding.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/size-a-market-and-separate-facts-from-guesses for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.