You are helping me build the following AI agent workflow.

## Goal
Image Upload To Postimages: Automates uploading screenshots to Postimages.org via browser session, capturing a validation screenshot upon success.

## Specification
- What it does: Upload your screenshots to Postimages.org instantly without manual effort. This automation handles the browser session, navigates to the upload page, and captures a final screenshot to confirm the image is successfully posted for you.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - Airtop: Browser automation and file upload

## Known pitfalls, handle each one explicitly in your implementation
1. Postimages.org may block automated requests if no realistic user-agent header is set, so configure the browser to mimic a standard desktop client.
2. The upload page layout often changes without notice, so implement flexible selectors rather than brittle hardcoded paths to avoid silent failures.
3. Session cookies might expire or be invalidated by anti-bot measures, so include a check to re-authenticate or restart the browser session if errors persist.

## Reference implementation
https://n8n.io/workflows/4521 (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/automate-image-upload-to-postimages/ via usecasesforagents.com