AI Agents July 24, 2026 · 7 min read

How to Run an AI Email Automation Agent with OE Runtime

Read your Gmail inbox, prioritise what needs a reply, and send professional follow-up emails automatically. OE Runtime connects to Gmail via the REST API using OAuth — no SMTP configuration, no app passwords, and no SDK required.

📧

Step 1

Read Inbox

Fetch the 10 most recent unread emails with sender, subject, date, and a one-sentence summary.

Step 2

Draft & Send Reply

Identify the most urgent email and send a professional acknowledgement reply via the Gmail REST API.

Step 3

Report

Summarise emails found, which was replied to, and confirm delivery with timestamp.

The Agent YAML

Create a file called agent.yaml inside an email/ directory:

name: Email Assistant
description: Summarize inbox and send a follow-up email
instructions: |
  You are an email assistant. Read the inbox and send emails via the Gmail REST API.
  Draft professional, concise messages. Never send without confirming recipient and subject.
  Complete all steps fully before writing your report.
steps:
  - name: Read Inbox
    content: |
      Call the Gmail connector:
      GET /messages with params: { "labelIds": "UNREAD", "maxResults": "10" }
      Then for each message id returned, call:
      GET /messages/<id> with params: { "format": "metadata", "metadataHeaders": "From,Subject,Date" }
      Collect sender, subject, date, and snippet for each email.
  - name: Draft and Send Reply
    content: |
      From the unread emails, identify the one that most urgently needs a reply.
      Draft a professional acknowledgement reply. Then send it by calling:
      POST /messages/send
      with body: { "raw": "<base64url-encoded RFC 2822 message>" }
      Construct the raw field as: base64url("From: me\r\nTo: <sender>\r\nSubject: Re: <subject>\r\n\r\n<body>")
  - name: Report
    content: |
      Summarize what was done:
      - Number of unread emails found
      - Brief summary of each email (sender, subject, urgency level)
      - Which email was replied to and why
      - Confirm the reply was sent successfully
connectors:
  - connection_name: My Email
    connection_type: gmail-rest

The Config File

Create oe-config.json in the same directory:

{
  "llm": {
    "provider": "openai",
    "model": "gpt-4o",
    "apiKey": "YOUR_OPENAI_API_KEY"
  },
  "server": {
    "enabled": false,
    "port": 3333,
    "apiKey": "your-secret-api-key"
  },
  "connectors": [
    {
      "connection_name": "My Email",
      "connection_type": "gmail-rest",
      "bearerToken": "YOUR_GOOGLE_ACCESS_TOKEN",
      "baseUrl": "https://gmail.googleapis.com/gmail/v1/users/me"
    }
  ]
}

Get your bearerToken from the Google OAuth Playground: select the scope https://www.googleapis.com/auth/gmail.modify, authorize with your Google account, exchange the code for tokens, and copy the Access Token. Tokens expire after 1 hour — for long-running use, generate a refresh token and exchange it for a new access token as needed.

Download OE Runtime

OE Runtime — Direct Downloads

⊞ Windows (.exe)  macOS 🐧 Linux 📮 Postman Collection

Run the Agent

Windows

oe-runtime-win.exe email/agent.yaml --config email/oe-config.json

macOS

chmod +x oe-runtime-macos

oe-runtime-macos email/agent.yaml --config email/oe-config.json

Linux

chmod +x oe-runtime-linux

oe-runtime-linux email/agent.yaml --config email/oe-config.json

macOS Gatekeeper: On first run, macOS may block the binary. Go to System Settings → Privacy & Security → click "Allow Anyway" next to oe-runtime-macos.

Running as an API Server

Add --serve to start OE Runtime as an HTTP server on port 3333:

oe-runtime-win.exe --serve --config email/oe-config.json

Then send a request:

curl -X POST http://localhost:3333/run \
  -H "Content-Type: application/json" \
  -d '{"yaml": "email/agent.yaml", "params": {}}'

Or import the Postman collection (download above) to test all endpoints visually.

Use Cases

Inbox triage and prioritisation — Automatically scan your inbox each morning, rank unread emails by urgency, and send acknowledgement replies to the most time-sensitive ones. This ensures nothing falls through the cracks even during busy periods without requiring you to manually process every message.
Sales follow-up automation — Send personalised follow-up emails to prospects after demos, proposal submissions, or trial sign-ups without manual copywriting. Configure the agent to run on a schedule and tailor each message based on the recipient's context and the stage of the conversation.
Customer support triage — Route and acknowledge incoming support requests automatically so customers know their issue has been received and is being reviewed. The agent can classify urgency, send an appropriate holding reply, and log the interaction for your support team.
Invoice and payment reminders — Automatically send payment reminder emails to clients with overdue invoices by querying your invoicing data and drafting personalised messages. The agent can escalate the tone for older overdue invoices while keeping initial reminders polite and professional.
Event and meeting confirmations — Send booking confirmations, calendar invites, and pre-event reminders for webinars, consultations, or interviews without manual effort. The agent can be triggered by a new booking event and personalise each confirmation with the attendee's name and specific event details.
Internal status reporting — Automatically email weekly status summaries, project updates, or metric reports to stakeholders without anyone needing to write them manually. The agent compiles data from connected sources and delivers a formatted email digest to the relevant distribution list.
Lead nurturing sequences — Run drip email campaigns for new leads by sending a series of educational or value-add emails over time. Each email is personalised with the lead's name and the product or topic they expressed interest in, maintaining engagement without manual intervention.
Post-purchase follow-up — Send automated thank-you emails, onboarding guides, and check-in messages to new customers after a purchase or sign-up event. Thoughtful post-purchase communication improves retention and reduces churn by making customers feel supported from day one.

Build your own agents with OE Runtime

Download OE Runtime and run any AI agent locally or as a server — no cloud required.

Get OE Runtime →

Series OE Runtime Agent Guides — 21 Connectors

Series overview →