AI Revision Workflow Template 1
Purpose: [x]. Audience: [x]. Diagnose the 5 highest-impact revision issues in this draft. Do not rewrite yet.
Start with structure, then replace every placeholder with information that is true, relevant, and natural for your context. These templates are intentionally skeletal so your final writing does not sound mass-produced.
Effective AI-assisted revision keeps the original draft and writer's intent visible, requests diagnosis before rewriting, applies changes selectively, and verifies that revised language has not changed facts, citations, voice, or commitments.
Purpose: [x]. Audience: [x]. Diagnose the 5 highest-impact revision issues in this draft. Do not rewrite yet.
Review only for [structure/clarity/tone/consistency]. Quote the affected passage and explain the issue briefly.
For this selected passage, propose 3 revisions that preserve these facts and constraints: [list].
Compare original vs revised wording for changes in certainty, responsibility, numbers, dates, or commitments.
Publication-readiness audit for AI Revision Workflow: claim/advice/example → [ ]; strongest available source tier → [ ]; important disagreement or uncertainty → [ ]; what would change the conclusion → [ ]; publish now / qualify / revise / hold → [ ]; final verifier or source of truth → [ ].
Provenance and classification audit for AI Revision Workflow: draft statement/example → [ ]; classify as fact / interpretation / recommendation / convention / original example → [ ]; source or internal provenance → [ ]; source date / version / checked date → [ ]; attribution needed → [ ]; recency risk → [ ]; final publishable wording → [ ].
Source-record and update audit for AI Revision Workflow: statement / example → [ ]; external fact, project fact, interpretation, recommendation, convention, or original example → [ ]; controlling first-party / primary source → [ ]; secondary source if used → [ ]; source record / locator → [ ]; date or version checked → [ ]; update trigger → [ ]; publish / qualify / revise / hold → [ ].
Source-ledger and revision-history audit for AI Revision Workflow: claim / recommendation / example → [ ]; source or project record ID → [ ]; source status active / superseded / corrected / retracted / retired → [ ]; claim-level last verified date/version → [ ]; event that triggered recheck → [ ]; correction / withdrawal action → [ ]; reader-facing disclosure needed? → [ ]; what changed and why → [ ]; prior wording/version retained at → [ ].
Claim/source status audit: Item [claim/source/example] | Status [active / review due / stale / corrected / retracted / superseded] | Controlling source/version [x] | Last verified [date/version] | Stale trigger [x] | Correction severity [0–3] | Reader disclosure [none / note / correction / withdrawal] | Changelog entry [what changed + why].
Dependency and propagation audit: Claim / example / recommendation [x] | Controlling source / project record [x] | Dependency strength [direct / shared / advisory / independent] | Review trigger / reason code [x] | Needs-review scope [local / direct dependents / cluster] | Replacement source requirements [x] | Carry-forward decision [x] | Propagation targets [x] | Reader disclosure / changelog action [x].
Persistent editorial registry audit: Topic slug → [ ]; claim UID/key → [ ]; source UID/key → [ ]; dependency UID + strength → [ ]; source status/version → [ ]; open review UID/reason/priority → [ ]; replacement source if any → [ ]; reviewer + resolution → [ ].