You are helping me build the following AI agent workflow.

## Goal
Job Application Replies: Monitors Gmail for job applications and uses an AI agent to generate and send personalized HR replies via SMTP.

## Specification
- What it does: You receive instant, personalized rejection or acknowledgment emails for every job application in your Gmail inbox without manual effort. This automation filters incoming messages, drafts professional HR responses using an AI agent, and sends them directly via SMTP to keep candidates informed immediately.
- Trigger: Triggered by an event (Event · on new email)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Gmail: Monitor incoming job applications
  - OpenAI Chat Model: Generate professional responses
  - Structured Output Parser: Parse AI output reliably
  - Send Email: Send replies via SMTP

## Known pitfalls, handle each one explicitly in your implementation
1. Generic prompts can lead to repetitive responses so include dynamic variables for each applicant's unique details in the template.
2. The parser might fail if the LLM returns malformed JSON so implement error handling to retry or log failed generations.
3. Privacy regulations require careful data handling so ensure you do not store sensitive applicant PII in your workflow logs.

## Reference implementation
https://n8n.io/workflows/14267 (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/automate-job-application-replies/ via usecasesforagents.com