# Keep a bundle consistent when facts change Published and revised: October 13, 2026 · Version 1.0.0 Trace one approved change through a knowledge pack, dependent drafts, and delivery copies before assembling a release. ## Goal and proposed time Repair a bounded cross-artifact inconsistency while preserving source history, unknowns, and the release decision. Allow 100–140 minutes, including selected reading, making the outputs, and review. This is a proposed study budget, not measured completion time. Split the path across sessions if needed; stop at a checkpoint rather than rushing an evidence check. ## Prerequisites and inputs - Complete the inspectable-pack path, or bring a source ledger with stable claim IDs - Know which person controls factual approval and which audience will receive each output Use only the linked guides and their public or synthetic fixtures. A text editor, calculator, and timer are enough. No provider connection, account change, publication, or outside communication is required. ## Work through the path ### 1. Coordinate several artifacts from one fact set Read [the guide](/workspace-development/design-multi-artifact-workflow/). Give each intended output its own reader, fact dependencies, and required checks. Name deliberate omissions rather than assuming every document repeats everything. Carry forward: A dependency-first manifest for the three capstone outputs. ### 2. Audit a bundle for factual consistency Read [the guide](/workspace-development/audit-cross-artifact-consistency/). Freeze the before-state and log exact factual and semantic failures. Do not alter canonical facts merely to make the drafts agree. Carry forward: An issue log that distinguishes supported differences from real drift. ### 3. Decide what a workspace change should trigger Read [the guide](/workspace-development/triage-change-impact-maintenance/). Identify the approved change, unchanged fields, affected derivatives, and consequences of using the old version. Apply only the authorized synthetic repair. Carry forward: A scoped repair plan and evidence-linked candidate revisions. ### 4. Assemble a release people can actually use Read [the guide](/workspace-development/assemble-release-user-guide/). Assemble the candidate only after the capstone checks. Write a first-use note and make source revision, required copies, and remaining review visible. Carry forward: A draft manifest, known limits, and explicit release decision field. ## Worked practice Complete [Repair fact drift across a knowledge pack and its outputs](/workspace-development/practice/repair-cross-artifact-fact-drift/). Trace one approved change through facts, derived claims, three drafts, and a stale export without corrupting valid inventory. The capstone changes 28 to 24 seats per session and replaces a false visitor claim with 48 seat opportunities. It leaves 56 usable chairs intact and keeps the date undecided. A global number replacement would hide drift by creating a new error. ## Output A candidate fact set, three corrected excerpts, dependency map, issue log, and a draft release manifest with a visible hold or review decision. ## Exit checks - Source correctness is checked independently of artifact agreement - Indirect claims and derived totals are included in the impact map - Unchanged inventory is preserved during a capacity repair - Every required delivery copy is checked against its editable version - The retained old bundle is not treated as a safe fallback when its facts are obsolete ## Decide what happens next Keep the result when the checks pass. Revise a specific failed check in a new draft, preserving the first attempt. Hold any part that needs missing evidence or authority; an honest hold can complete this learning path even though the wider real-world task remains unfinished. Do not call an authored answer key an observed result. IIEN means infer intent and extrapolate needs here: use it to notice a useful next question and label assumptions. It does not authorize new actions, expand access, or tune model weights. ## Sources and scope This is an editorial sequence of the linked existing guides. Their source sections support the individual methods; the sequence, checkpoints, and study budget are original teaching choices. This path does not claim certification, deployed capability, or measured performance improvement.