Trend Seeker

View saved version →

---
name: compare-opportunities
description: Compare two to five business opportunities using Trend Seeker data and supporting evidence. Use when the user is choosing between ideas, niches, or opportunity IDs.
---

# Compare business opportunities

Compare two to five opportunities on a consistent evidence basis.

## Resolve the candidates

- If the user supplies Trend Seeker business idea IDs, use them directly.
- If the user supplies names or descriptions, use `search_business_ideas` to resolve each one. When a description maps to multiple materially different candidates, show the ambiguity before choosing.
- Don't substitute a merely similar idea without telling the user.

## Retrieve comparable data

1. Call `compare_business_ideas` with the resolved IDs.
2. Call `get_supporting_evidence` for each candidate.
3. Compare only fields available across the candidates. Mark missing data instead of treating it as zero.

Use these dimensions when supported by the returned data:

- Target audience and problem specificity.
- Evidence strength and number of supporting posts.
- Validation score and confidence tier.
- Evidence recency.
- Why-now rationale.
- Solution clarity and unresolved assumptions.

## Report

Start with a compact comparison table. Follow it with the strongest case for each option, the main risk for each option, and a recommendation tied to the user's stated priorities. Include dated source links for the evidence that drives the recommendation.

Treat Trend Seeker scores as research signals, not forecasts. Don't create a composite score or weighting unless the user requests one. Clearly separate retrieved facts from inference, and never invent missing metrics or evidence. Use other external research tools only when the user asks for broader research beyond Trend Seeker.

View saved version →

---
name: find-opportunities
description: Find evidence-backed business opportunities for a market, audience, problem, or category using Trend Seeker. Use for opportunity discovery and niche exploration, not for validating one already-defined idea.
---

# Find business opportunities

Use the Trend Seeker MCP tools to find opportunities that match the user's request.

## Research

1. Extract the market, audience, problem, constraints, and desired number of results from the request.
2. Use `list_idea_categories` only when category discovery would materially improve the query.
3. Use `search_business_ideas` for a specific market, audience, problem, or keyword. Use `list_business_ideas` when the user wants to browse recent or highly ranked opportunities without a specific query.
4. Inspect the best candidates with `get_business_idea` when the search result doesn't contain enough detail.
5. Call `get_supporting_evidence` for each finalist. Prefer candidates with dated evidence from more than one source when the data supports that distinction.

Keep the result set focused. Don't broaden the query merely to fill a requested count. If nothing relevant is returned, say so and suggest a more general query.

## Report

For each opportunity, provide:

- The title and target user.
- The concrete problem.
- Why it appears timely, if the returned data supports that claim.
- The relevant Trend Seeker scores or confidence tier, with their scale.
- One or two dated evidence points with direct source links.
- The largest unresolved assumption.

End with a short comparison explaining why the leading candidates fit the user's constraints. Treat scores as research signals, not forecasts or guarantees. Clearly separate retrieved facts from your interpretation. Never invent market size, revenue, growth, source links, or missing fields.

Use other external research tools only when the user asks for broader research beyond Trend Seeker.

View saved version →

---
name: validate-idea
description: Test an existing business or product idea against Trend Seeker's market evidence. Use when the user has a defined concept and wants evidence, adjacent demand, risks, or validation gaps.
---

# Validate a business idea

Evaluate the user's concept against Trend Seeker data. This is an evidence review, not a prediction that the business will succeed or fail.

## Frame the concept

Extract the target user, problem, proposed solution, geography or industry constraints, and business model when supplied. If a critical detail is missing, state the assumption you use rather than silently filling it in.

## Gather evidence

1. Call `search_business_ideas` with the core user problem. Search by the problem people experience, not only by the proposed product name.
2. If needed, make one narrower search for the target audience or workflow. Deduplicate candidates by business idea ID.
3. Use `get_business_idea` for the closest candidates.
4. Use `get_supporting_evidence` for the strongest two or three candidates. Preserve source URLs and publication dates.

Don't treat a lack of Trend Seeker results as proof that there is no demand. It only means this dataset didn't return matching evidence.

## Assess the idea

Classify the result as one of:

- `supported`: direct evidence matches both the audience and problem.
- `adjacent evidence`: demand exists, but the audience, problem, or solution differs materially.
- `weak evidence`: few or low-confidence matches were returned.

Explain the classification using retrieved facts. Include:

- The closest matching opportunities.
- Evidence for the problem, with dated source links.
- Relevant scores or confidence tiers and their scale.
- Important contradictions or mismatches.
- What the dataset cannot establish.
- Three concrete customer-research or market tests that would reduce the largest uncertainties.

Don't invent a market size, competitor claim, revenue estimate, or numeric probability of success. Clearly label all inference. Use other external research tools only when the user asks for broader research beyond Trend Seeker.