The AI ran his errands on Telegram for months under two rules: low-risk it does itself, high-risk it asks first
2026), blogger Tony Xu describes running the AI Agent on Telegram since April 2026 as his personal errand-runner: persistent memory, skills, terminal/file/browser/GitHub/Gmail/Calendar tools and cron jobs, with morning and evening briefings, email sorting and follow-up, and calendar work. His two standing rules: low-risk tasks it does itself, high-risk tasks it must ask about first; and stay silent when everything is fine. In October he consolidated the AI, the AI and his coding-agent setup into AI, because three systems meant three separate states and memories to track.
How it works
- Run the AI on Telegram with memory, skills and Gmail/Calendar/GitHub tools
- Set morning and evening cron briefings
- The AI sorts and follows up email and runs errands under risk tiers
- User makes decisions, the AI executes
- In October he migrates the whole arrangement to the AI
Why it’s worth knowing
He governed a consumer agent with two plain rules (risk tiers and 'stay silent when healthy') and ran his errands on it for half a year before folding it into AI.
Where it’s from
Summarized from a public post on tonyxu.io. See the original ↗