Efficient solution to process with low cost for reading high volume emails (5,000/day) to assess sentiment?

[Steve_Jensen]

Describe the problem/error/question

We are looking to process 5,000+ emails daily and have AI determine sentiment and on negative sentiment to evaluate and categorize these emails for manager review and action.
Trying to do this with most effective code for processing and reduced costs of plugin components. Having some challenge with HTML format and break down of email for reading and want to minimize or find the best AI engine for this work based on volume. Additionally, challenged with the chain of emails within an email that trigger another instance of negative sentiment.

What is the error message (if any)?

What recommendations might you all have regarding optimal flow to accomplish based on use?

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

## Share the output returned by the last node
<!-- If you need help with data transformations, please also share your expected output. -->

## Information on your n8n setup
- **n8n version:** Latest stable
- **Database (default: SQLite):**
- **n8n EXECUTIONS_PROCESS setting (default: own, main):**
- **Running n8n via (Docker, npm, n8n cloud, desktop app):** CLOUD
- **Operating system:**

[bartv]

We’ve created a new category for help with designing workflows, and I’ve moved your question there: Help me Build my Workflow. Find out how this category works by reading this topic.