All use cases

Work

Audit recurring workflows with your strongest model

Old workflows still run steps the new model can do natively — or shouldn't do at all.

Share

What hurt

@AIGuide_ tip for Claude/ChatGPT/Grok Bot: audit every recurring workflow with your strongest model on high effort. Grade 0–10 on trigger quality, correctness, handoffs, unnecessary steps, tool choice, human bottlenecks, safety, future-proofing; say what to merge/automate/cut because the model can do it natively; propose fixes for every workflow; map current vs proposed — don't execute yet. Author-quoted. Not affiliated with xAI.

What to install or create

Strongest model → grade/rank every recurring workflow → map proposed simpler version → approve before edits.

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

Grade and map recurring workflows (author-quoted)

Quoted from @AIGuide_ — as published. Do not invent a second system prompt.

Last line is our approval fence: Never send, post, spend, or buy without my explicit yes.

Grade, rank, and score every recurring workflow in my current AI setup 0-10 on trigger quality, correctness, number of handoffs, unnecessary steps, tool choice, human bottlenecks, safety and future-proofing. Also determine which steps should be merged, automated, or cut entirely because the model can now do them natively. Propose the highest-confidence fixes for every workflow, not just the worst ones. Aim for the simplest version that preserves or improves output quality. Don't execute the edits yet, just map the current workflow and proposed version so the audit is as accurate as possible with the least chance of breaking anything.

Never send, post, spend, or buy without my explicit yes.

First run

  1. 1Read https://x.com/AIGuide_/status/2117381038724841697 (credit @AIGuide_).
  2. 2Open your strongest model / Grok Bot on high effort.
  3. 3Paste the author audit prompt; require map-only, no edits.
  4. 4Review grades and proposed merges/cuts.
  5. 5Approve the highest-confidence fixes one workflow at a time.

Approval fence

Map only — do not edit, pause, or delete any workflow until you approve the report.

What to tweak

Steal the grade-and-map-only audit; models changed, your prompts may be solving ghosts.

Source

Grant Miller @AIGuide_ · Original post

Not affiliated with xAI. We did not write this prompt. Third-party template terms still apply.

Browse templates

Browse team blueprints

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.

See Pro