You are helping me build the following AI agent workflow.

## Goal
HR Resume Screening & Interview Prep: New application? The agent screens the resume against job requirements, logs the score.

## Specification
- What it does: You save time on initial recruitment by having this agent automatically screen new applications against your job requirements in Google Sheets. It logs scores for every candidate and instantly sends tailored interview questions to your team via Telegram for shortlisted applicants.
- Trigger: Triggered by an event (Manual · on new application via form)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - n8n Form Trigger: Capture candidate details and CV upload
  - Google Drive: Store uploaded resume files
  - OpenAI Chat Model: Provide LLM capabilities for screening and question generation
  - Google Sheets: Store job requirements, log results, and manage applicant data
  - Telegram: Send real-time alerts to the hiring team

## Known pitfalls, handle each one explicitly in your implementation
1. Resume parsing can fail on complex layouts so add error handling to log failed extractions and notify HR manually.
2. PII data in resumes must be handled securely so ensure the n8n workflow runs over HTTPS and restricts access to sensitive sheets.

## Reference implementation
https://n8n.io/workflows/9528 (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-hr-resume-screening-interview-prep/ via usecasesforagents.com