You are helping me build the following AI agent workflow.

## Goal
Job Application Email Sender: Send a job post screenshot to Telegram and get a personalized email draft cached for review before sending with your resume attached.

## Specification
- What it does: Send a job post screenshot to Telegram to instantly receive a personalized email draft tailored to the role and ready to send with your resume attached after you review it.
- Trigger: Triggered by an event (Manual · on new job post screenshot)
- Autonomy: You stay in control
- Expected setup effort: a few focused days
- Tools/services involved:
  - Telegram: User input and interaction interface
  - OpenAI: Analyzing job posts and drafting emails
  - Gmail: Sending personalized application emails with attachments
  - Google Drive: Storing and retrieving resume files
  - Redis: Caching AI-generated email drafts for user confirmation

## Known pitfalls, handle each one explicitly in your implementation
1. OCR accuracy on screenshots can be poor so add a step to validate extracted text quality before sending it to the LLM for analysis.
2. Resume files may exceed Gmail's 25MB limit so check file size early and compress or warn the user if the attachment is too large.

## Reference implementation
https://n8n.io/workflows/13077 (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-job-application-email-sender/ via usecasesforagents.com