You are helping me build the following AI agent workflow.

## Goal
Log And Analyze Job Postings: Send job postings via Telegram to log them in Sheets with extracted details or request a market trends report.

## Specification
- What it does: Receive job postings via Telegram to automatically extract key details like company, role, and salary into your Google Sheets for easy tracking. You can also request a market trends report anytime by sending a specific command, which generates insights based on the stored data.
- Trigger: Triggered by an event (Manual · on new Telegram message or /report command)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Telegram: Receive job postings and send reports
  - Anthropic: Extract structured data and generate trend analysis
  - Google Sheets: Store logged job details

## Known pitfalls, handle each one explicitly in your implementation
1. Salary data often appears as text ranges rather than numbers so you must add a normalization step to convert strings like '100k-120k' into numeric averages for analysis.
2. Telegram message lengths can exceed limits or contain special characters so implement robust error handling and sanitization before sending data to the extraction model.
3. Google Sheets API quotas are strict so add caching logic to batch updates or check remaining quota to avoid runtime failures during high-volume ingestion.

## Reference implementation
https://n8n.io/workflows/15931 (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/log-and-analyze-job-postings/ via usecasesforagents.com