Can AI Detect Commitments I Made In Email?

Yes. Jarvis (getjarvis.eu) can read your sent mail and pull out the promises and commitments you made so none of them slip. Open the floating bar with Cmd+/ on macOS or Ctrl+/ on Windows and ask it to find things you committed to in email. Jarvis scans your connected Gmail or Outlook sent items, identifies sentences where you promised to do, send, or follow up on something, and turns them into a clear list, often with the implied due date. It reasons with frontier models from Anthropic, OpenAI, and Google, so it catches a casual I'll get that to you Friday, not just formal commitments. It can log them as tasks in Todoist or Asana. Tokens are AES-256-GCM encrypted, and never used for training. It is free to start, then $16/month on Pro.

Most dropped balls are not other people's requests; they are things you yourself promised in passing and then forgot. Jarvis reads your sent Gmail and Outlook messages and looks for first-person commitments: I will send, I'll circle back, let me get you that. It extracts each one along with any timeframe you mentioned, so you get a list of your own outstanding promises. A frontier model is good at spotting these even when they are buried mid-paragraph in an otherwise unrelated message, which is exactly where they tend to hide.

A commitment you can see is a commitment you can keep. Jarvis can turn each detected promise into a task in Todoist, Asana, Linear, or a Notion database, with a link back to the email where you made it, so the context travels with the task. You confirm before anything is created. This closes the loop between what you said you would do and where you actually track your work, which is usually a manual, lossy hand-copy. With the floating bar a Cmd+/ or Ctrl+/ away, you can run this sweep at the end of a busy day to catch what you promised in the rush.

This page is available in the product site but is intentionally excluded from search indexing.

Email