You are helping me build the following AI agent workflow.

## Goal
Email Triage and Alert System: Automatically triages your Gmail inbox using AI to filter noise, summarize newsletters.

## Specification
- What it does: You reclaim control of your Gmail inbox as AI automatically filters noise, summarizes newsletters into actionable insights, and sends instant Telegram alerts for high-priority messages. The system handles replies, drafts, and archiving based on context so you can focus on what matters most.
- Trigger: Triggered by an event (Event · on new email)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - Gmail: Email input and management
  - Telegram: Real-time priority alerts
  - OpenAI Chat Model: Email classification and summarization
  - n8n: Workflow orchestration

## Known pitfalls, handle each one explicitly in your implementation
1. Email bodies often exceed token limits so you must implement a truncation strategy or chunking logic before sending to the LLM.

## Reference implementation
https://n8n.io/workflows/3968 (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-email-triage-and-alert-system/ via usecasesforagents.com