You are helping me build the following AI agent workflow.

## Goal
Email AI Agent for Auto-Responses: An AI agent that automatically drafts and sends replies to incoming emails using an LLM, requiring no manual intervention.

## Specification
- What it does: Get instant replies to your emails without lifting a finger. This agent uses an LLM to draft and send responses on autopilot as soon as messages arrive. It is perfect for you if you are building your first AI automation tool.
- Trigger: Triggered by an event (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - LLM: Generate auto-responses

## Known pitfalls, handle each one explicitly in your implementation
1. Spam filters may block automated emails if you do not properly authenticate your domain with SPF and DKIM records.
2. Unbounded email volume can cause excessive API costs so implement a daily cap on the number of processed messages.
3. Sensitive personal data could be exposed in logs so ensure you sanitize or redact PII before sending prompts to the LLM.

## Reference implementation
https://www.youtube.com/watch?v=UIf-SlmMays (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/email-ai-agent-for-auto-responses/ via usecasesforagents.com