You are helping me build the following AI agent workflow.

## Goal
Research Assistant via Slack: Ask any research question in Slack; the agent searches Perplexity, drafts a Google Doc with findings, and shares the link.

## Specification
- What it does: Ask any research question in your Slack channel, and you'll instantly receive a summary of findings from Perplexity inside a new Google Doc. The agent handles gathering information and formatting the results so you can share the link with your team immediately.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - Slack: User interaction and notifications
  - Perplexity: Web research
  - Google Docs: Document creation and storage

## Known pitfalls, handle each one explicitly in your implementation
1. Perplexity API responses can vary in length so you must implement truncation logic to prevent token limit errors when creating documents.
2. Slack event verification will fail if your webhook URL does not correctly handle the challenge response during setup.
3. Google Docs permissions default to private so you need to explicitly set the sharing settings to anyone with the link before posting it in Slack.

## Reference implementation
https://www.youtube.com/watch?v=nO3frWOMpok (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/research-assistant-via-slack/ via usecasesforagents.com