Shadow prompt loop
Run a new prompt in the shadows against real traffic alongside the current one; the disagreements decide whether to switch.
/loop cadence: continuous or per-batch. For real traffic [SOURCE], run the candidate prompt in shadow alongside the live prompt without exposing shadow output to users. Append disagreements (input, live output, shadow output, which was better by [CRITERIA]) to state-file shadow-prompt.md. Each round, summarize where they diverge and whether the candidate wins. Never serve shadow output to a user or change the live prompt automatically. Stop after the batch; log errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
claude-code
Implementation note
ADAPTED, not verbatim. No tool named. Yellow loop: evaluation only; a human promotes the winner.
More research loops
Repeat-offender digest
Read every loop's run ledger and find the one root problem showing up across multiple workflows.
/loop cadence: weekly. Read every loop's state/ledger file [DIR]. Append recurring failure patterns (which loops, symptom, frequency) to state-file repeat-offenders.md. Each round, identify the SINGLE root problem appearing across the most workflows and draft a fix-once recommendation. Read + own-file writes only; change no other loop. Stop after one root problem; log errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
researchlow risk
Kill-criteria loop
Make every live option declare the single fact that would disqualify it upfront, then hunt for that evidence.
/goal for each live option [LIST], state its ONE disqualifying condition upfront, then run an evidence hunt for that disqualifier. Done when: for every option, the state-file kill-criteria.md contains either PASTED evidence the disqualifier is true (kill it) or a documented search showing it isn't (keep it). No option stays undecided. Paste the evidence table as proof, or paste what's still missing and stop. Judge: a second smaller model checks each verdict cites evidence. Budget: cap $[X]. Hard cap: stop after 1 iteration per run.
researchlow risk
Regulatory / source digest
Digest only what materially changed in the sources you must track, each with a plain-language 'so what.'
/loop cadence: weekly. Using the Firecrawl MCP, diff tracked regulatory/authoritative sources [LIST] against the last snapshot. Append only material changes to state-file source-digest.md. Each round, write a plain-language 'what changed / so what / who it affects' for each material change; ignore cosmetic edits. Read + own-file writes only. Stop after the digest; log errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
researchlow risk