How Moncho has built a scalable market sizing pipeline

November 16, 2026
Shazzad Hossain MukitFounder, Moncho.ai
How Moncho has built a scalable market sizing pipeline
Building market intelligence · Part 2 of 3

How Moncho has built a scalable market sizing pipeline

“How big is potato in Bangladesh?” can mean farm sales, factory sales, what households spend, or what customs records as imports. Those can all be true. They are still different questions.

Moncho research notes11 min readHow the system works

Ask for a market size too early and you get a confident dollar with no shared meaning. Take potato in Bangladesh. One person may mean the value of the crop leaving farms. Another means what processors book as revenue. A third means what households spend in wet markets and shops. A fourth means import value at the border. Each reading can be useful. They answer different questions. This post explains how Moncho turns that mess into a reviewed number: lock the question, gather sources, clean them so they can be found again, pick a method the evidence can support, then publish only after a Moncho analyst decides. We call that last gate Human in the Loop (HITL).

The shape of the work

Define, then evidence, then a reviewed size

We keep the story in order on purpose. First we say what we are measuring. Then we collect source material and clean it so the same fact can be reused for sizing and for Sherpa. Only after that do we pick a method, draft a number, and ask an analyst to publish.

That work hangs on Moncho’s market model first: how countries, landscapes, segments, needs, organizations, and products relate. Without that shared map, a size has nowhere stable to live. Learn how the market model works.

01 · Define the question

“How big is the market?” is not yet measurable

Before anyone opens a spreadsheet, say what kind of economic activity the estimate represents. For potato, farm-gate value, processor revenue, household spending, and import value sit at different points on the same chain. If two people publish different dollars without naming that difference, they are usually arguing about scope, not about who is “right.”

So we pin six choices beside every serious size: where, what, who pays or produces, which money flow, when, and on what accounting basis. Without those, a formula is just algebra looking for a home.

Scope before calculationSix questions
Where?Country, region or city
What?Products, services or activities
Who?Buyer, payer or producer
Which flow?Sales, spending, output or fees
When?Reference year and frequency
On what basis?Currency, prices, tax and coverage
These choices travel with the number. They are how a later reader can tell whether two estimates are comparable.
Why “market value” is easy to misuse

Revenue is what a seller receives. Value added is what remains after intermediate inputs. Household spending is what buyers pay. A sizing method has to name which of those it is estimating, or the dollar will be read as something it is not.

02 · The pipeline

From documents to a published size

Once the question is clear, the work becomes a pipeline you can inspect. AI agents do repeatable research labor. Tools hold catalogs, parsers, and calculators. A Moncho analyst locks scope, settles ambiguous facts, and decides what becomes official. That human gate is HITL.

Agent / AI Tools & data Human in the Loop
03 · Methods

Different evidence, different equations

Back to potato. If the yearbook already prints a sales total that matches your scope, start there. If you have harvest tonnes and a sourced farm-gate price, multiply them and label the result. If you only have customs, publish import value as import value. The method family should match what you actually have.

Availability decides the equation. Scope decides whether readings can be added.

Farm-gate output, factory sales, and household spending can describe different stages of the same market. Adding them may count the same product more than once. Keep each reading labeled, and combine only when the market definition justifies it.

04 · Agents and sources

Four agents do the repeatable work. Analysts still control the output.

Each card below is an agent: AI-assisted research labor with a defined job. Agents use tools. They do not replace a clear source trail or Human in the Loop.

🤖

Agent 01 · Harvest

Finds reports and pulls relevant tables from official portals, surveys, and documents.

Uses tools: source locators, PDF and table parsers.
🤖

Agent 02 · Clean and tag

Normalizes units, years, definitions, and geography so each fact is searchable later.

Uses tools: validation rules, reusable evidence store.
🤖

Agent 03 · Product mapping

Suggests links between trade or product classifications and Moncho segments for review.

Uses tools: product catalogs, segment lists.
🤖

Agent 04 · Sizing draft

Builds a labeled working estimate from saved evidence, names missing inputs, and runs basic checks.

Uses tools: evidence retrieval, targeted search, calculators.
Official statistics

Yearbooks, household surveys, industry and SME publications, and ministry portals.

Trade and customs

Import and export flows, read with their valuation basis and coverage limits in mind.

Global and comparable sources

Useful when local evidence is thin. External or proxy inputs stay labeled as such.

Reusable evidence store

The cleaned observations that both market sizing and Sherpa read from the same place.

  • Fed by Agent 02 (clean and tag).
  • Not the same thing as a published market size.
05 · Why a pipeline, not a chatbot

A market size has to survive the next question, the next user, and the next year

Ask a generic chatbot “how big is potato in Bangladesh?” and you may get a confident dollar. Ask again tomorrow, or ask a colleague to check the work, and you often get a different number with a different story. Chat is good at improvisation. It is weak at keeping a durable, shared reading of a market.

That is why sizing runs as a pipeline. Facts are cleaned once and stored. Methods are chosen against evidence. Drafts stay labeled. A Moncho analyst publishes. Later sizing work, and Sherpa, can reuse that memory instead of rebuilding the market from scratch every time.

  • Memory, not a transcript: cleaned facts and published sizes outlive any one chat session.
  • Stateful across uses: the same potato reading can be inspected months later with the same scope, method, and sources.
  • Shared across users: one analyst’s reviewed size becomes available to the next teammate, not locked in a private thread.
  • Compounds over years: each sourced fact and each published card makes the next market cheaper to size.
  • Honest limits: inventing a fee, or mixing farm-gate with household spend, is a process failure, not a clever answer.
  • Quality under control: evals and human review check whether drafts still obey scope, method, and source rules when models or prompts change.
  • Cost under control: we track LLM API use and token consumption across harvest, tagging, and draft steps, so spend stays visible and controllable.
06 · Publish, then answer

When a number becomes official

A working estimate can still help an internal review. It is not the official Moncho size until an analyst has checked scope, method, inputs, sources, and limits. That gate is Human in the Loop, not a public vote.

Working estimateAmount, inputs, assumptions, known gaps
Analyst reviewApprove, request more evidence, or withhold

We will not ship a count times an invented fee. Import value is not automatically the whole domestic market. When someone asks Sherpa to size a market, it should prefer a published card that matches the question. If the evidence cannot support a defensible figure, it should say so. That user journey is Part 3.

Market intelligence on Moncho is reviewed by Moncho analysts before publication.

Related Topics

agentic-workflowmarket-sizinghuman-in-the-loopsourced-factsbackend-research