Scheduled agent runs
Agents run on a schedule and work through your inbox and task board. They fix what they can. You get only the decisions.
Konstantin's verdict: Trial
Six times each weekday, a scheduled agent run works through my two inboxes and my task board. It also reads my answers to earlier questions. A voice memo or a note to myself starts an extra run.
Each run fixes what it can with small helper agents. It checks each result in the live product or account. What needs me becomes one decision card: a short note with one question, the choices and the agent's recommendation.
Last week there were 36 runs. A quiet run costs little because it only reads what changed. The Friday run closes the week. Since this edition, a separate Friday run writes this radar.
It sits in Trial because this design is one week old.
What moved
On other radars
No community radar places this yet.
Sources
No outside source. The verdict comes from Konstantin's own work.
Share and embed
Makers: show where your product sits. The badge updates when the radar does.
Share this entry
Also in Practices · Trial
- Check every path through a user flowDrawing a user flow, such as a booking, as a chart of steps. A program then tries every order of steps, including retries and delays, to find where the user flow breaks.
- Give agents narrow keysGiving each agent the narrowest access key and spending limit that does the job. One mistake or breach then reaches little.
- Guardrails, not manual reviewYou set the tests and limits once. Then agents ship without you checking each result.
- Let agents reach you by pushAgents bring questions and results to you, by text message, phone call or podcast, instead of leaving them in notes you must open.
- Pick a direction before agents build creative workFor creative work, agents first show several storyboards or directions. You pick one, then they build a rough version for fast feedback before any polish.