You are helping me build the following AI agent workflow.

## Goal
Market Research & Business Case Generator: Send a market topic via chat to generate a structured business case study with live research, saved directly to Google Docs.

## Specification
- What it does: Define your market research topic in chat to instantly generate a structured business case study with live industry data and trends. This process synthesizes the findings into a detailed report that saves directly to your Google Docs for immediate use.
- Trigger: Run manually (Manual · on chat prompt)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - OpenAI: Research scope definition
  - Perplexity: Live web research and data retrieval
  - Anthropic Chat Model: Synthesizing findings into case study
  - Google Docs: Saving final output

## Known pitfalls, handle each one explicitly in your implementation
1. Google Docs API permissions may fail if the service account lacks write access, verify OAuth scopes before deployment.
2. Context window overflow from large research dumps can degrade writing quality, chunk the Perplexity results before sending to Anthropic.

## Reference implementation
https://n8n.io/workflows/5430 (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/market-research-business-case-generator/ via usecasesforagents.com