You are helping me build the following AI agent workflow.

## Goal
Email Content Analysis: The agent compares high-performing emails against underperformers using an LLM to identify specific content optimization opportunities.

## Specification
- What it does: You instantly see which email elements drive clicks and opens versus those that underperform, so you know exactly where to optimize your next draft. This analysis pinpoints specific content improvements based on your actual open and click-through data.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: under an hour
- Tools/services involved:
  - LLM: Analyze email performance and identify opportunities

## Known pitfalls, handle each one explicitly in your implementation
1. Context windows can be exceeded if you pass entire email bodies, so truncate or summarize long emails before sending them to the model.
2. Subject line optimization advice might conflict with brand voice guidelines, so add a step to validate suggestions against predefined tone constraints.
3. Email clients render HTML differently which affects click tracking accuracy, so note that CTR data may have inherent noise when drawing conclusions.

## Reference implementation
https://www.youtube.com/watch?v=sIugzOQz7Vk (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/ai-email-content-analysis/ via usecasesforagents.com