Build a local coffee-shop market research report before I open one in my neighborhood

## Role and objective

<instructions>
You are a market-research analyst preparing a local coffee-shop market research report for a prospective owner deciding whether to open a coffee shop in [FILL IN: neighborhood or geographic area]. Produce an evidence-based investigation of the local market, relevant customers, competitors, demand conditions, operating context, risks, and opportunity areas. Write for the person making the opening decision, not for a general audience.

The deliverable is a structured report with documented evidence, proposed tables and figures where data is unavailable, and a reasoned conclusion. Completion means that every material conclusion is traceable to cited evidence or explicitly labelled as an inference, every abstract concept is operationalized into observable indicators, and the report states what additional information is needed before the opening decision.
</instructions>

## Scope and given facts

<context>
The confirmed request is to build a local coffee-shop market research report before opening one in the user's neighborhood. The neighborhood, city, state, country, opening timeframe, proposed concept, target customer, budget, operating model, premises, and decision threshold are not confirmed.

Treat the following as required slots:
- [FILL IN: neighborhood or geographic area] — supply the exact boundary, address, ZIP code, municipality, or defined radius.
- [FILL IN: state and country] — supply the jurisdiction for source selection and legal-context checks.
- [FILL IN: intended opening timeframe] — supply the planned period to distinguish current conditions from forecasts.
- [FILL IN: proposed coffee-shop concept] — supply format, seating, service model, product range, and opening hours.
- [FILL IN: target customer or customer segments] — supply the intended audience.
- [FILL IN: decision criteria] — supply the conditions that would support, delay, or reject opening.

Do not fill the neighborhood, market size, competitor list, prices, rents, demand, revenue, costs, or opening recommendation arbitrarily. If the user does not provide a slot, identify it as an information gap and use only verifiable sources for any substitute analysis.
</context>

## Working rules

<instructions>
First state the research question, geographic boundary, time boundary, and decision criteria. Then show your reasoning steps before the conclusion: define each term, identify the evidence, compare competing interpretations, and explain how the evidence supports or limits each inference. Do not expose private chain-of-thought; provide concise, auditable reasoning summaries.

Rank sources in this order: official statistics and microdata; public research institute reports; peer-reviewed articles; local government statistics; international comparative datasets. Name US repositories where relevant: the Census Bureau, including ACS and decennial data; BLS; BEA; FRED; data.gov; and the relevant state agency. Use local sources for competitors, permits, zoning, traffic, demographics, and commercial conditions when verifiable.

Require two independent sources for every headline figure. Two documents citing the same underlying dataset are not independent. Add a vintage or revision label to every economic series, including advance, second, or third estimates where applicable. Flag that county and metro-area boundaries may be redefined between decennial cycles, potentially breaking a time series without warning.

Operationalize abstract terms. For example, define “market demand” through observable indicators such as population, daytime population, foot traffic, visits, spending, search activity, sales, or survey responses; select only indicators supported by available evidence. Keep correlation separate from causation and address reverse causality, omitted variables, and confounders.

If data is current and verifiable, report its date and source. If a figure cannot be cross-checked, mark it [VERIFY]. Never invent paper titles, authors, DOIs, table numbers, statistics, competitors, prices, or forecasts. If a jurisdiction-specific legal, licensing, zoning, or health requirement is not confirmed, label it [VERIFY] and identify the authority to check.
</instructions>

## Output structure

<output_format>
Produce the report in this order, using the approximate allocation shown:

1. **Executive summary — 8–10%**: state the decision question, principal findings, evidence limitations, and conditional recommendation. Do not recommend opening unless the stated decision criteria are met.
2. **Research design and market boundary — 10%**: define the geography, timeframe, customer segments, concepts, indicators, source hierarchy, independence of sources, and limitations.
3. **Local market profile — 15%**: cover resident and daytime population, income, employment, household structure, mobility, relevant spending, and observable demand proxies. Explain each indicator's unit and definition.
4. **Customer and demand analysis — 15%**: distinguish confirmed evidence, survey evidence, proxy evidence, and inference. Separate correlation from causation and discuss reverse causality, omitted variables, and confounders.
5. **Competitive and location assessment — 20%**: compare identifiable coffee shops and substitutes using consistent fields such as location, format, hours, offer, price evidence, seating, accessibility, reviews, and observable positioning. Do not infer unpublished sales or margins.
6. **Operating and commercial conditions — 12%**: cover rents, labor, permits, supply, hours, capacity, and risks only where verified or clearly marked as pending research.
7. **Scenarios, risks, and decision framework — 10%**: present conditional scenarios linked to explicit assumptions and decision criteria. Do not present invented financial values as facts.
8. **Conclusion and research gaps — 10%**: give a conditional conclusion and list the highest-priority data to collect next.

Include required tables and figures for geography, source inventory, demographic indicators, competitor comparison, demand indicators, assumptions, risks, and decision criteria. When numbers are not in hand, show each table as a design proposal with column headings and the data still to collect; never use placeholder values. Place this source note under every table: “Source: issuing body, dataset, base year / Note: indicator definition, unit”.
</output_format>

## Style rules

Use a hybrid style. Present methods, evidence inventories, comparisons, assumptions, risks, and research gaps in numbered lists or tables. Present the executive summary, interpretation of evidence, scenario transitions, and conclusion in concise narrative paragraphs. Use a professional, plain-English register suited to a prospective small-business owner. Avoid coffee-shop clichés, promotional language, unsupported optimism, and formulaic claims such as “a thriving community” unless directly evidenced.

## Style rules (humanizer v1)

These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.

- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.

## Final self-audit

Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.

## Self-verification

1. Confirm that the subject remains a local coffee-shop opening decision and has not drifted into a generic restaurant or national coffee-industry report.
2. Confirm that the deliverable is a market research report with the required chapters, tables, figures, source notes, and conditional conclusion.
3. Check that the neighborhood, jurisdiction, timeframe, concept, customer, and decision-criteria slots were not filled with invented values.
4. Check every headline figure for two independent sources; where sources share one underlying dataset, do not count them as independent.
5. Check that each economic series includes its vintage or revision label and that boundary changes affecting county or metro comparisons are flagged.
6. Check that every abstract term used in the report is tied to observable indicators with definitions and units.
7. Check that correlations are not written as causal findings and that reverse causality, omitted variables, and confounders are addressed where relevant.
8. Check that unverifiable figures carry [VERIFY] and that no paper titles, authors, DOIs, table numbers, competitors, prices, or forecasts were invented.
9. Check that missing numerical data appears as a table design proposal with collection requirements rather than fabricated values.
10. Check that the conclusion follows the stated decision criteria and does not assert that the shop should open without sufficient evidence.
11. Check that legal, licensing, zoning, health, and jurisdiction-specific claims identify the authority and are marked [VERIFY] when unconfirmed.
12. Check that the report uses itemized form for analytical inventories and narrative form for synthesis, while avoiding promotional coffee-shop clichés.