Engineering
Watch the workflow once; turn every exception into a numbered rule
The same automation breaks every night, and you patch it by hand again.
What hurt
iOlld (@EvgeniyIolld) has Grok Bot watch one full workflow, then run it on the bot's computer. Not affiliated with xAI.
What to install or create
Night 1 stops on each new exception (404→archive, paywall→cache, no date→drop) and writes R01/R02/R03. Night 2 hits the same exceptions with zero human minutes. Approve only irreversible steps.
Bots
No new bot. Follow the first-run steps.
Plugins
None on day one. Follow the first-run steps.
Routines
None on the first run. Watch one manual pass first.
The prompt
Watch-once exception rules (author-quoted)
Quoted from @EvgeniyIolld — as published. Do not invent a second system prompt.
Watch me complete this workflow once: [DESCRIBE THE WORKFLOW] 1. While you watch, record: - the steps, the tools and the order - every decision I make and why - the points where something breaks or needs my approval 2. Turn what you saw into a routine: - a numbered checklist with the tool, input, output and failure condition for each step - mark every step that needs my approval 3. Write one rule for every exception I handled: - format: if [problem] then [action] - show me each rule before you save it
First run
- 1Read https://x.com/EvgeniyIolld/status/2109358998428299384 (credit @EvgeniyIolld).
- 2Pick one repeat workflow and run it once while the bot watches.
- 3Approve the checklist and each if-then rule it proposes.
- 4Rerun the next day and count human minutes; add rules for anything new.
- 5Leave irreversible actions on approval; automate the rest.
Approval fence
Shipping, spending and public posts stay behind your yes.
What to tweak
Night 1 writes the rules; night 2 should need no babysitting.
Source
iOlld @EvgeniyIolld · Original post
Not affiliated with xAI. We did not write this prompt. Third-party template terms still apply.
Pro pack
Want the full setup, not just the idea?
Pro packs give you the job text, prompts, schedules and pitfalls for popular use-cases.