Guide

Email Analytics with Manus AI

Use Manus AI to analyze your email patterns — volume by sender, response times, busiest hours, and unread trends. Nylas CLI pulls the data, Manus generates the report.

Why email analytics

Understanding your email patterns helps you prioritize, delegate, and set boundaries. Which senders consume the most attention? When does your inbox spike? How long do messages sit unread? These are questions that raw inbox views cannot answer, but a few CLI commands and an AI agent can.

Manus can pull your inbox data through the Nylas CLI, analyze it in its sandbox, and generate structured reports — tables, ranked lists, or even downloadable spreadsheets — without you writing any code.

Prerequisites

  • A Manus account — sign up at manus.im. Free and paid plans both work for analytics prompts.
  • Nylas CLI Skill installed in Manus — follow the Manus AI Skills guide to set up the Skill that gives Manus email and calendar access.
  • A connected mailbox — at least one grant (Gmail, Outlook, or IMAP) configured in your Nylas dashboard.

Pull inbox data

The foundation of every analytics prompt is the nylas email list command. It returns structured JSON with sender, date, subject, read status, and more.

nylas email list --limit 100 --json

Manus runs this inside its sandbox and receives the full JSON array. From there, it can slice and group the data any way you ask. Increase --limit for broader analysis, but keep in mind that larger datasets use more Manus credits.

Volume by sender

Ask Manus who emails you the most:

Prompt: "Show me who emails me the most this month. Rank the top 10 senders by message count."

Manus runs nylas email list, groups by the from field, counts occurrences, and presents a ranked table. This quickly reveals which senders dominate your inbox — newsletters, colleagues, or automated notifications.

Busiest days and hours

Timing patterns help you plan when to check email and when to focus on deep work:

Prompt: "When do I receive the most emails? Break it down by day of the week and hour of the day."

Manus analyzes the date field from each message, bins by day and hour, and reports the peaks. You might discover that Monday mornings account for 30% of your weekly volume, or that a specific sender always writes at 11pm.

Unread messages are a proxy for inbox pressure. The --unread flag filters to only unread messages:

nylas email list --unread --json

Ask Manus to analyze the results:

Prompt: "How many unread emails do I have, and how old are the oldest ones? Group by sender."

This surfaces the messages you've been avoiding and helps you decide what to read, archive, or delegate.

Generate a report

Manus's report generation is one of its strongest features. You can ask for a comprehensive summary in a single prompt:

Prompt: "Create a weekly email report with:
- Total volume (received and sent)
- Top 10 senders by count
- Busiest day and hour
- Unread count and oldest unread
- Response time estimates for my replies

Format it as a downloadable spreadsheet."

Manus runs multiple nylas email list commands with different filters, compiles the data, and generates a structured document — a CSV, an HTML table, or a Markdown report depending on what you request.

Contact analytics

Cross-referencing email data with your contacts adds context. Pull your contact list:

nylas contacts list --json

Then ask Manus to combine the two datasets:

Prompt: "Match my top email senders to my contacts list. Show me who is in my contacts and who isn't. For unknown senders, suggest which ones I should add."

This is useful for identifying frequent correspondents who are missing from your CRM or address book.

Tips for better analytics

  • Be specific with time ranges — "this week" and "last 30 days" give Manus clear boundaries for filtering.
  • Request specific formats — ask for "a table", "a CSV", or "a bullet list" to control how Manus presents results.
  • Combine prompts — batch multiple analytics questions into one prompt to reduce credit usage and get a unified report.
  • Save as a Skill — if you run the same analytics weekly, package your prompts as a Manus Skill so you can trigger them with a slash command.

FAQ

How accurate are Manus AI email analytics?

Manus works with the raw data returned by the Nylas CLI. Counts and timestamps are exact. Derived metrics like estimated response times depend on how well Manus can match replies to originals, which is reliable for direct threads but less precise for forwarded or merged conversations.

Does Manus store or share my email data?

Manus processes data inside an isolated sandbox that is destroyed after each session. Email content is not persisted or used for training. Your Nylas API credentials remain in the sandbox and are not accessible outside of it.

Can I schedule recurring email analytics reports?

Manus does not have built-in scheduling. However, you can save your analytics prompts as a Manus Skill and re-run them on demand. For automated recurring reports, pair the Nylas CLI with a cron job or CI/CD pipeline instead.

Next steps