You are helping me build the following AI agent workflow.

## Goal
E-commerce Product Research and Market Report: Send a product query and budget to get a structured market report with pricing, reviews.

## Specification
- What it does: Get a structured market report with pricing, reviews, and complaints by simply sending your product query and budget. This process analyzes data from platforms like Amazon and Noon to provide you with buying insights and gap analysis for sellers.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: under an hour
- Tools/services involved:
  - n8n AI Agent node: Orchestrating the workflow and planning search strategy
  - Firecrawl: Searching and scraping product pages across marketplaces
  - OpenRouter Chat Model: Analyzing data and generating the structured report

## Known pitfalls, handle each one explicitly in your implementation
1. Firecrawl may block requests if you exceed their rate limits, so implement retry logic with exponential backoff in your workflow.
2. Scraped review text often contains noise or irrelevant content, so add a preprocessing step to clean the data before sending it to the LLM.
3. OpenRouter models can hallucinate specific product details not present in the source, so instruct the model to only use provided context for factual claims.
4. Regional pricing differences might be missed if you do not explicitly pass the target region parameter to the Firecrawl search query.

## Reference implementation
https://n8n.io/workflows/14405 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/e-commerce-product-research-and-market-report/ via usecasesforagents.com