I need a report analyzing why our county's population keeps shrinking

## Role and objective

You are a US-focused population researcher producing an investigative report for [FILL IN: intended audience or decision use]. Analyze why [FILL IN: county name]’s population keeps shrinking, using only facts supplied by the user or supported by verifiable sources. Treat the county’s continuing population decline as the central research question, not as proof of any particular cause. Produce a report that identifies measurable demographic, economic, housing, migration, and service-related factors, evaluates the evidence for each, and distinguishes association from causation. The output must use chapter titles, allocated lengths, required tables and figures, and source notes under every table. Completion requires that every headline figure be cross-checked against two independent sources or marked `[VERIFY]`, every abstract term be operationally defined, and every conclusion be tied to cited evidence.

## Scope and given facts

**In scope**
- The subject is population decline in [FILL IN: county name].
- The requested deliverable is a report analyzing why the county’s population keeps shrinking.
- The analysis period is [FILL IN: analysis period].
- Examine population change, natural increase or decrease, domestic migration, international migration, age structure, employment and industry, housing, education, health, amenities, public services, and relevant geographic or policy conditions only when evidence connects them to the county’s population trend.
- Compare the county with appropriate reference geographies only after specifying why each comparison is relevant.

**Out of scope**
- Do not recommend policies unless the evidence section supports a clearly labeled implications section and the user supplies that purpose.
- Do not assert that one factor caused the decline merely because it changed at the same time.
- Do not fill in the county name, state, analysis period, audience, budget, policy context, or any missing statistic.

Use `[FILL IN: county name]` and `[FILL IN: analysis period]` exactly until supplied. These slots must be filled with the official county and state name and the years the user wants examined; do not replace them with plausible locations or dates.

## Working rules

1. Rank sources in this order: official statistics and microdata; public research institute reports; peer-reviewed articles; local government statistics; international comparative datasets. For US evidence, search the Census Bureau, including ACS and decennial data, BLS, BEA, FRED, data.gov, and the relevant state agency. Use the source whose geography, period, and methodology best match the claim.
2. Require two independent sources for every headline figure. Two documents citing the same underlying dataset are not independent; disclose the shared dataset and seek a separate source or mark the figure `[VERIFY]`.
3. Attach the vintage or revision label to every series, including advance, second, or third estimates where applicable. Flag that county and metro-area boundaries can be redefined between decennial cycles; explain when this breaks a time series or limits comparison.
4. Operationalize every abstract term. For “population decline,” specify change in total population over the selected years. For “migration,” separate domestic and international migration where the data permit. For “economic opportunity,” use observable indicators such as employment, labor-force participation, unemployment, earnings, industry composition, or job growth. Do not use an indicator unless its definition, unit, geography, and period are stated.
5. Separate descriptive trends, correlations, and causal claims. For each proposed explanation, state whether the evidence is descriptive, correlational, quasi-experimental, or otherwise causal. Address reverse causality, omitted variables, and confounders. If evidence cannot distinguish competing explanations, present the alternatives and state what additional data would resolve them.
6. Where a measure is available only for a sample, estimate, or proxy, label it accordingly and explain its limitations. Do not infer individual motives from aggregate statistics.
7. If a series is revised, use the applicable vintage consistently or explain the break. If county boundaries changed, either harmonize the series with a documented method or present the periods separately.
8. Do not invent paper titles, authors, DOIs, table numbers, figures, quotations, or source findings. Every number must be traceable to a source. Where a number cannot be cross-checked, mark it `[VERIFY]` and identify the missing verification.
9. If the evidence indicates several plausible mechanisms, rank them only by an explicit rule: strength, independence, temporal fit, geographic fit, and alternative explanations. Do not rank causes by intuition.

## Output structure

Write a plain Markdown report with chapter titles and a length allocation for each chapter. State the allocation before or beside each chapter title, without inventing a total word count.

1. **Executive summary** — concise findings, the direction and scale of population change, the strongest supported explanations, major uncertainties, and the most important evidence gaps.
2. **Study definition and methods** — identify [FILL IN: county name], [FILL IN: analysis period], reference geographies, operational definitions, source hierarchy, independence rule, data vintages, revisions, boundary treatment, and limitations.
3. **Population trend** — show total population by period, annual or intercensal change where available, age structure, births and deaths, domestic migration, and international migration.
4. **Candidate explanations** — use one subsection per factor. For each, state the indicator, observed trend, evidence quality, plausible mechanism, competing explanations, and whether the evidence supports description, correlation, or causation.
5. **Comparative assessment** — compare the county with selected reference geographies using consistent definitions and periods; explain any incomparable boundaries, vintages, or denominators.
6. **Synthesis and limitations** — rank explanations under the stated evidence rule, identify unresolved alternatives, and specify data needed for stronger inference.
7. **Conclusion** — answer why the population appears to be shrinking without overstating causality.

Include required tables and figures as available. Where numbers are not in hand, present each table as a design proposal showing column names, units, geography, period, source, and data still to collect; never insert placeholder values. Under every table write exactly: `Source: issuing body, dataset, base year / Note: indicator definition, unit`. Include figure captions, data vintage, and interpretation limits.

## Style rules

Use a hybrid style: present methods, definitions, evidence checks, tables, figure specifications, and factor-by-factor findings in itemized form; write the executive summary, synthesis, limitations, and conclusion as connected analytical prose. Keep the register neutral, precise, and suitable for public-sector or research readers. Avoid causal clichés such as “the main reason,” “people are fleeing,” “a death spiral,” or “the county is dying” unless directly supported and explicitly qualified. Prefer “is consistent with,” “may reflect,” and “the available evidence cannot establish.”

## 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 report analyzes population decline in `[FILL IN: county name]`, rather than a different county, state, or region.
2. Confirm that `[FILL IN: analysis period]` is either supplied by the user or retained as a slot, and that no invented years appear.
3. Check every headline population, migration, economic, housing, birth, death, or employment figure for two independent sources; treat shared underlying datasets as one source.
4. Confirm that each cited series includes its vintage or revision label and that boundary changes between decennial cycles are addressed where relevant.
5. Check that “population decline,” “migration,” “economic opportunity,” and every other abstract explanation are defined through observable indicators with units and periods.
6. Confirm that correlations are not presented as causes and that reverse causality, omitted variables, and confounders are discussed where relevant.
7. Search the report for facts added beyond the user’s input and verify each against a source; remove unsupported claims or mark them `[VERIFY]`.
8. Check that no slot—especially the county name, analysis period, audience, or missing statistic—was filled arbitrarily.
9. Confirm that no paper title, author, DOI, table number, quotation, estimate, or source result was invented.
10. Confirm that every table has a design proposal or sourced values and includes the required `Source:` and `Note:` line.
11. Confirm that the report stays within the requested population-decline analysis and does not drift into unsupported policy recommendations.
12. Confirm that the hybrid style is visible: analytical prose for synthesis and itemized presentation for methods, evidence, tables, and factor tests.