LaunchFast Full Research Loop

Inputs

If needed, ask once for:

• keyword or keyword list
• target selling price
• first order quantity
• optional competitor ASINs
• optional report path

Default report path:

./artifacts/launchfast/reports/launchfast-report-[keyword]-[YYYY-MM-DD].html

Workflow

1. Product research

• Run research_products for each keyword with focus="balanced" and product_limit=20.
• Score each keyword using the same logic as launchfast-product-research.
• Pick winners for deeper analysis.

2. IP check

For promising keywords, run:

text
ip_check_manage(action="ip_conflict_check", keyword="<keyword>")
ip_check_manage(action="trademark_search", keyword="<keyword>")

Extract:

• conflict level
• notable active marks
• patent concerns if present
• final risk posture: CLEAR, CAUTION, or BLOCKED

3. Supplier research

For the strongest keyword, run:

text
supplier_research(keyword="<keyword>", goldSupplierOnly=true, tradeAssuranceOnly=true, maxResults=10)

Summarize the top suppliers with:

• company name
• quality score
• price band
• MOQ
• years in business
• trust signals

4. PPC research

If you have competitor ASINs, or can responsibly infer 2-3 strong ASINs from product research, run:

text
amazon_keyword_research(asins=[...], limit=20)

Summarize:

• keyword count
• top search-volume terms
• high-intent terms by purchase rate
• indicative CPCs
• suggested campaign structure

If there are no usable ASINs, state that this phase was skipped.

5. Build the report

Create a standalone HTML report with:

• executive verdict banner
• market scorecard
• product findings
• IP findings
• supplier findings
• PPC findings
• concise recommendation section

Design should match the existing LaunchFast visual language:

• clean light theme
• neutral palette
• card layout
• compact tables
• clear GO / INVESTIGATE / PASS styling

Write the file to the requested path and report the final file location.

Output

Always return:

• overall verdict
• key blockers or strengths
• report path if the file was written

Do not pad the response with generic “next steps” unless the evidence clearly supports a specific recommendation.