You are helping me build the following AI agent workflow.

## Goal
Generate Job Application Icebreakers: Scans your job application sheet for empty icebreakers and uses GPT-4 to generate a five-line personalized email opener based on the...

## Specification
- What it does: Get personalized email openers instantly by having this agent scan your job application sheet for missing icebreakers. It uses GPT-4 to craft a five-line opener tailored to each company's context and writes the result directly back into your Google Sheets.
- Trigger: Triggered by an event (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Google Sheets: Store job data and update icebreakers
  - OpenAI: Generate personalized email icebreakers

## Known pitfalls, handle each one explicitly in your implementation
1. The model may exceed the line count so add a strict instruction to stop generating after five lines.
2. Google Sheets API quotas can be hit quickly during testing so implement a small delay between requests.
3. Special characters in job titles might break the JSON payload so sanitize all string inputs before formatting.

## Reference implementation
https://n8n.io/workflows/6113 (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/generate-job-application-icebreakers/ via usecasesforagents.com