Day 30: is it still running?
Build-along · ~12 min at your own keyboard
Most personal systems die quietly around week three. This check is optional, and it is the one that tells you the truth. Come back thirty days after your full run and answer one question: is it still running without you pushing it? If not, you probably hit one of three causes: it was too big, it broke and nobody noticed, or the review stopped. Name which one, fix that, and restart small.
Ladder · Level 6The long version: The day-30 check ↗
Do this
0/7Checkpoints
- ▸You have real counts, not impressions.
- ▸You named one cause if it is not running.
The three ways this goes wrong
- You cannot find run history to count from. — Use the Log lines as the count. Then add a Log line to every run so the next count is easy.
- The system stopped at day 12 and you did not notice. — That is the silent break. Add a daily check, on its own schedule, that alerts you when there's no Log line by a set time.
- Every run logged, but you rarely used the output. — That's not running, it's busy. Count it as stalled, name why the output wasn't usable, and fix that one thing.
Dated facts in this lesson: Claude Cowork scheduled tasks ("Scheduled" in the sidebar) run a saved prompt in the cloud with the laptop off. They need Pro or above (researched Oct 4, 2026, not yet confirmed by a person: check the source before you rely on it); ChatGPT has agent, Projects (project-only memory, files, instructions), memory toggles in Settings > Personalization, and Scheduled Tasks at chatgpt.com/schedules. Workspace agents ("ChatGPT Work", July 2026) are on Business and Enterprise. Agent quotas: Plus 40 messages a month, Pro 400. Secondary source (researched Oct 4, 2026, not yet confirmed by a person: check the source before you rely on it); Gemini "Personal context" is on by default and needs "Keep Activity". "Saved info" also holds facts. Gems are being replaced by Skills in Q4 2026. Reported dates conflict (rollout around Oct 13, migration around Nov 17, 2026; Workspace March 2027) (researched Oct 4, 2026, not yet confirmed by a person: check the source before you rely on it); Microsoft 365 Copilot has Notebooks, Agent Builder agents, Pages, Copilot Cowork and Researcher and Analyst agents. Personal Copilot has Memory and Personalization settings, and Notebooks with Microsoft 365 Personal, Family or Premium. Secondary source (researched Oct 4, 2026, not yet confirmed by a person: check the source before you rely on it); Grok has Projects (files and instructions), "Personalize with Memories" under Data Controls, and Automations on a paid tier. SuperGrok Heavy ($300) runs parallel agents. Secondary source (researched Oct 4, 2026, not yet confirmed by a person: check the source before you rely on it); Perplexity has Memory (also on Free), Spaces (files and instructions; Pro allows 50 files per Space; not on Free), Tasks (at most hourly) and Computer on Max. Secondary source (researched Oct 4, 2026, not yet confirmed by a person: check the source before you rely on it).
Share what happened
Paste your day-30 status in about five lines: runs expected vs logged vs used, reviews done, fix-up time, status, cause if stalled, next step.
Strip API keys, passwords, and tokens before you paste. Swap them for [KEY].
🔒 Don't paste confidential, personal-health, or payment info.