In the final episode of Zero to Agent in 30 Minutes, AI engineer Sajal Sharma demonstrated building a personal assistant on OpenClaw that tracks tasks and notes and can autonomously execute scheduled work.
Why this matters
A practical personal assistant must be reachable when you are away from your computer and must continue running to perform scheduled tasks. OpenClaw supports these requirements and allows the developer to choose where the agent runs, which models it uses, and how it accesses data.
From fresh install to scheduled automations — step by step
-
Install your OpenClaw instance
Sharma recommended starting with a local install while learning how the system works, then moving the instance to an always-on machine or hosted environment if continuous availability is required.
-
Connect the channels you use
Add a messaging channel such as Telegram, WhatsApp, or Slack so you can reach the assistant away from your desk. In his demo, Sharma used Telegram to send requests and receive notifications from the same assistant.
-
Set up the assistant’s workspace
Provide a workspace for the agent to store tasks, notes, skills, and memory, along with guidance files that define its behavior and how it should interact with files in that workspace.
-
Use it in daily workflows
In the demo, Sharma asked the assistant for an overview of current projects and checked progress toward a reading goal. He also had the assistant search the web for a book series and add discovered titles to his reading list.
-
Add proactive automations
Schedule work the assistant should handle independently. Sharma added a Telegram reminder and a morning briefing designed to pull information from tasks, a calendar, and recent email. Recurring checks and webhooks can also trigger the agent when something changes in another system.
Series closure and next steps
This episode closed out Zero to Agent in 30 Minutes. The producers thanked viewers who followed and built along with the presenters throughout the series.
To continue following agent development, a new series called The Monday Morning Agent debuts Monday, October 12 at 8:00 a.m. PT / 11:00 a.m. ET. The eight-episode series will follow the development of an increasingly autonomous data agent working with real play-by-play data.
For more information and to reserve a spot, interested viewers can learn more or follow along on Radar.
