You are helping me build the following AI agent workflow.

## Goal
Multimodal Slack AI Assistant: Monitors a Slack channel for mentions and uses AI to analyze voice, images, video, or text inputs before posting a response back.

## Specification
- What it does: Get instant, intelligent replies in your Slack channel whenever you mention the bot with voice, images, videos, or text. The system automatically analyzes your multimodal inputs using advanced AI models to generate a helpful response right back in the conversation.
- Trigger: Triggered by an event (Event · on new Slack message)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Slack: Message trigger and response posting
  - OpenAI: Voice and text analysis
  - Google Gemini: Image and video analysis
  - Anthropic Chat Model: Alternative LLM processing

## Known pitfalls, handle each one explicitly in your implementation
1. Multimodal content often exceeds token or file size limits, so implement a pre-processing step to resize images or truncate long transcripts before sending them to the LLM.
2. Bot mentions in threads may not trigger the same event payload as channel messages, verify your Slack event subscription settings include thread events.

## Reference implementation
https://n8n.io/workflows/9149 (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/multimodal-slack-ai-assistant/ via usecasesforagents.com