You are helping me build the following AI agent workflow.

## Goal
Sales Development Representative Pipeline: Automates your sales outreach by sending AI-personalized follow-ups via Gmail, pausing sequences when prospects book calls.

## Specification
- What it does: Save time managing leads while your agent pulls fresh prospects from Google Sheets and sends AI-personalized follow-ups via Gmail. It automatically pauses these sequences when you book calls on Google Calendar and handles no-shows by sending rescheduling emails and updating statuses for you.
- Trigger: On a schedule (Scheduled · daily and every 6 hours; Event · on new calendar booking)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration platform
  - Google Sheets: CRM and lead list data storage
  - Gmail: Sending personalized follow-up emails
  - Google Calendar: Tracking meeting bookings and no-shows
  - OpenAI Chat Model: Generating personalized email copy via LLM chain

## Known pitfalls, handle each one explicitly in your implementation
1. Gmail API quotas can exhaust quickly with high volume, so add a delay node between sends to stay within limits.
2. OpenAI token costs accumulate rapidly if prompts are too verbose, so keep input variables concise and strip unnecessary whitespace.
3. Calendar checks might miss overlapping events due to timezone mismatches, so explicitly set the timezone parameter in the calendar node.
4. Google Sheets read nodes can return empty arrays for new runs, so add a filter node to skip processing if no leads are found.

## Reference implementation
https://n8n.io/workflows/13529 (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/automated-ai-sales-development-representative-pipeline/ via usecasesforagents.com