You are helping me build the following AI agent workflow.

## Goal
Twitter Content Automation: Submit a topic, tone, and action type to automatically generate on-brand tweets with optional images or engage with niche posts via n8n.

## Specification
- What it does: Submit a topic, tone, and action type to instantly generate on-brand tweets or engage with niche posts via n8n. You can also have matching images created by AI before the final content is posted directly to X.
- Trigger: Run manually (Manual · on demand via form)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and automation logic
  - Google Gemini Chat Model: Generating tweet text, image prompts, and engagement responses
  - X (Formerly Twitter): Posting tweets, engaging with posts, and sending DMs
  - HTTP Request: Generating custom images via external APIs like Pollinations.ai

## Known pitfalls, handle each one explicitly in your implementation
1. AI-generated images may contain policy violations or watermarks so add a manual review step in your workflow.
2. Token usage costs can spike with high-volume generation so set strict token limits on your Gemini API calls.

## Reference implementation
https://n8n.io/workflows/10322 (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/twitter-content-automation-with-ai/ via usecasesforagents.com