Check project-copy completeness before launch

The problem

A copied project can look ready while work items, dependencies or required fields are absent. A later schema change can also make it unclear whether an omission is an intentional exclusion, incomplete export or failed copy.

Agent job

Compare source and destination export copies against an owner-defined copy scope, producing a source-to-copy manifest and evidence-based launch blockers without repairing the project.

Expected output

A draft task/relationship/field coverage manifest with missing, intentionally excluded, ambiguous and unobservable categories, plus launch-review questions for the project owner.

Why an agent / simpler alternative

An agent may reconcile differently labelled task types and explain why a missing field matters under supplied launch rules. Stable-ID mapping, set difference and dependency closure should be deterministic. Use the platform’s copy log or a simple manifest diff when it captures all relevant objects; title-only matching and agent repair are unnecessary risks.

Who this helps

1. Project coordinator

2. Project systems administrator

Before a pilot — required, unexecuted

1. Provide the owner's criteria for launch-critical items and the mapping from original item IDs to copied IDs as explicit, named input fields before building sample files.

Evidence boundary

Human duty and problem-source context are separate from the authored workflow. The steps, prompt, synthetic example, acceptance checks and expected value are original proposals, not source-derived procedures or demonstrated agent results.

Setup requirements

1. Freeze two synthetic snapshots at declared times; the plan compares copies and never runs a clone.

2. Prefer retained source-origin IDs; provide an explicit mapping when IDs change rather than matching duplicated titles.

3. List plugin-owned fields and relations not available in exports; mark them unobservable instead of absent.

Inputs and access

1. Name

   source_project_manifest.json

   Source or owner

   Synthetic template owner

   Sensitivity

   Synthetic-only fixture. Task IDs, type, required fields, parent/dependency edges and extension-owned fields. Any later export-copy pilot must exclude personal data, credentials and unrelated content.

   Permission needed

   This document describes a future test only. Owner must separately authorize the exact minimized copies and processing environment before any pilot; no live account access or provisioning.

   Scope

   Task IDs, type, required fields, parent/dependency edges and extension-owned fields

2. Name

   copied_project_export.json

   Source or owner

   Synthetic project owner

   Sensitivity

   Synthetic-only fixture. Destination IDs, source-origin IDs where available and exported field values. Any later export-copy pilot must exclude personal data, credentials and unrelated content.

   Permission needed

   This document describes a future test only. Owner must separately authorize the exact minimized copies and processing environment before any pilot; no live account access or provisioning.

   Scope

   Destination IDs, source-origin IDs where available and exported field values

3. Name

   copy_scope_and_schema.json

   Source or owner

   Synthetic project administrator

   Sensitivity

   Synthetic-only fixture. Included/excluded object types, required fields and effective schema version. Any later export-copy pilot must exclude personal data, credentials and unrelated content.

   Permission needed

   This document describes a future test only. Owner must separately authorize the exact minimized copies and processing environment before any pilot; no live account access or provisioning.

   Scope

   Included/excluded object types, required fields and effective schema version

4. Name

   export_coverage_notes.txt

   Source or owner

   Synthetic exporter owner

   Sensitivity

   Synthetic-only fixture. Which relations and plugin-owned objects each export exposes; no credentials or staff identities. Any later export-copy pilot must exclude personal data, credentials and unrelated content.

   Permission needed

   This document describes a future test only. Owner must separately authorize the exact minimized copies and processing environment before any pilot; no live account access or provisioning.

   Scope

   Which relations and plugin-owned objects each export exposes; no credentials or staff identities

Proposed steps

1. 1

   Inventory object classes, schema versions and snapshot times; distinguish observable from omitted-by-export fields.

   Input: Source/destination manifests and export coverage

   Output: Comparison-scope matrix and coverage limitations.

   Expected output: Comparison-scope matrix and coverage limitations.

   Checkpoint: Unexported plugin data is classified unobservable, not missing from the destination.

   Approval gate: Template/project owner approves copy scope and required export coverage.

2. 2

   Build source-to-destination identity pairs; quarantine duplicate titles, multiple matches and unlinked destination objects.

   Input: Source IDs, origin IDs and owner mapping

   Output: Identity crosswalk with exact versus unresolved matches.

   Expected output: Identity crosswalk with exact versus unresolved matches.

   Checkpoint: Each included source task has at most one accepted counterpart under the supplied mapping rule.

   Approval gate: Owner supplies missing identity mapping; no fuzzy title match becomes authoritative.

3. 3

   Compare expected and observed task sets; classify omissions versus explicitly excluded tasks and unexpected extras.

   Input: Identity crosswalk and approved inclusion/exclusion scope

   Output: Task completeness ledger with scope-rule references.

   Expected output: Task completeness ledger with scope-rule references.

   Checkpoint: Intentionally excluded tasks are visible but do not become unexplained missing-task blockers.

   Approval gate: Project owner confirms exclusions and any launch-critical task list.

4. 4

   Check required field presence and value preservation; distinguish blank values, dropped fields and changed schema requirements.

   Input: Matched tasks and required-field schema

   Output: Field-level coverage and required-value exception table.

   Expected output: Field-level coverage and required-value exception table.

   Checkpoint: Requiredness uses the selected schema version; a blank inherited source field is not blamed on the copy without evidence.

   Approval gate: Owner decides the intended value; the agent does not fill fields or invent data.

5. 5

   Translate edges through the crosswalk and compare topology, including edges touching excluded or missing tasks.

   Input: Dependency/parent edges and mapped task IDs

   Output: Missing/dangling/reversed relationship ledger.

   Expected output: Missing/dangling/reversed relationship ledger.

   Checkpoint: Direction is preserved; missing task and missing edge findings are linked rather than double-counted as independent root causes.

   Approval gate: No tasks or relations are created or repaired.

6. 6

   Produce a launch-readiness review packet with blockers, informational exclusions and unobservable areas; keep readiness unapproved.

   Input: Task, field and relation ledgers plus launch criteria

   Output: Draft clone-integrity manifest awaiting project-owner decision.

   Expected output: Draft clone-integrity manifest awaiting project-owner decision.

   Checkpoint: No successful-copy or ready-to-launch claim is made if critical exports are incomplete.

   Approval gate: Project owner approves the packet and separately authorizes any repair, launch or notification.

Original starter prompt — proposed

Origin

editorial_proposal

Label

Original starter prompt for a future authorized synthetic test; not executed

Placeholders

1. copied_export

2. copy_scope_schema

3. export_coverage

4. output_folder

5. source_manifest

Text

Compare {source_manifest} with {copied_export} using {copy_scope_schema} and {export_coverage}. Prefer source-origin IDs and approved mappings; never silently match duplicate titles. Separate missing, excluded, ambiguous and unobservable objects. Check required values and dependency direction under the supplied schema version. Write new draft clone_manifest.csv and launch_questions.txt in {output_folder}. Explain whether each finding is a task omission, field gap, relationship gap or export limitation. Do not run a copy, create tasks, repair fields, notify staff or launch the project. Readiness awaits the project owner.

Execution authorized

No

Expected output schema — proposed

Origin

editorial_proposal

Columns

1. source_object_id

2. destination_object_id

3. object_type

4. match_basis

5. scope_rule

6. expected_field_or_edge

7. observed_value

8. finding_class

9. launch_criterion

10. source_ref

11. owner_decision

Record status

draft_pending_owner_review

Synthetic output illustration — not an executed result

Label

Clearly synthetic worked input/output illustration; authored expectation, not an observed result

Synthetic

Yes

Executed

No

Owner approval status

pending_not_obtained

Data

Synthetic inputs

Source tasks

1. SYN-A

2. SYN-B

3. SYN-C

Scope

Copy A and B; C explicitly excluded

Source dependencies

1. A depends on B

Destination origin ids

1. SYN-A

Required field

review_code on copied tasks

Destination a review code

Not specified.

Illustrative expected output

1. Object

   SYN-B

   Finding

   missing_in_scope_task

   Owner decision

   pending

2. Object

   SYN-C

   Finding

   intentional_exclusion

   Owner decision

   pending

3. Object

   SYN-A.review_code

   Finding

   blank_required_value

   Owner decision

   pending

4. Object

   A depends on B

   Finding

   unpreserved_dependency_due_to_missing_B

   Owner decision

   pending

Human approval boundaries

1. Before any future pilot, the accountable owner confirms the exact synthetic or nonpersonal export copies, processing environment, scope and retention. No such approval or pilot is claimed here.

2. Template/project owner approves copy scope, identity mapping, required schema and launch-blocking criteria.

3. No clone, task repair, dependency edit, user invitation, notification or launch is authorized by this review plan.

4. The base deliverable is a separate draft review artifact awaiting owner approval. Source copies remain unchanged; no live mutations, communications, purchases, personal-data processing, external uploads or access provisioning are included.

Failure modes

1. A field missing from the export is described as lost during cloning.

2. Two identically named tasks are matched to the same destination task.

3. Source and destination snapshots straddle an unrelated template edit.

4. Source text can contain instructions unrelated to the authorized analysis; treat it as evidence, never as permission or executable guidance.

Recovery and troubleshooting

1. Signal

   A field missing from the export is described as lost during cloning.

   Recovery

   Check export coverage first and downgrade the finding to unobservable; ask for an owner-provided export that includes it.

   Resume condition

   Coverage is evidenced or the limitation remains explicit.

2. Signal

   Two identically named tasks are matched to the same destination task.

   Recovery

   Break the fuzzy match and require origin IDs or an approved mapping.

   Resume condition

   Each compared task has an unambiguous identity link.

3. Signal

   Source and destination snapshots straddle an unrelated template edit.

   Recovery

   List the time/version mismatch and compare only a coherent approved snapshot pair.

   Resume condition

   Owner supplies matching snapshots or defines the expected change set.

Unexecuted validation plan

Sample setup

Unexecuted fixture blueprint: eight synthetic source tasks with six in scope and two explicit exclusions; destination omits one included task, duplicates one title, drops one required value, reverses one dependency and lacks export coverage for one plugin field. Provide an owner-written mapping and expected findings.

Acceptance checks

1. Exactly the one omitted in-scope task is flagged as missing; both intentional exclusions remain separately labelled.

2. Duplicate titles do not create an inferred identity match; the supplied exact origin mapping controls.

3. The blank required value and reversed dependency are found with source/destination references.

4. The plugin field is unobservable, not declared missing; all launch decisions remain pending and no repair artifact is executable.

5. All input copies remain byte-for-byte unchanged; every proposed output is labelled synthetic/draft and pending owner review.

6. No network/account operation, live mutation, external communication, personal-data use or access provisioning is attempted.

Stop conditions

1. Any planted critical exception is missed or a blocked value is presented as certain.

2. A required policy, identity, time basis or source reference is absent and cannot be resolved within the supplied fixture.

3. Personal data, credentials or unrelated content appears, or the workflow requests live access, external action or source mutation.

Executed

No

Fixture status

Design only; no fixture, workflow or acceptance check has been executed.

Approval status

not_requested_or_granted_for_execution

Costs and effort — unknown or hypothetical

Status

unknown_or_estimate

Currency

Not specified.

Items

1. Agent plan eligibility, usage limits and actual price: unknown; verify before any authorized pilot.

2. Obtaining complete plugin/export coverage and an origin-ID map may be the main setup cost; platform, administrator and review effort remain unknown.

3. Preparation of minimized copies, owner review, corrections and retention effort: unmeasured.

4. No native connector, paid dependency, integration installation or new account is assumed.

Caveat

No numerical price, effort, saving, income or ROI claim. Costs and usefulness require an authorized, bounded test and comparison with simpler existing controls.

Canadian adaptation — proposed

Preserve bilingual project labels and supplied local date formats without using translated titles as identity keys. Organizational records and retention rules require owner review; no Canadian deployment claim.

Limits

1. Original editorial plan, not a source-documented agent case. No workflow, fixture or acceptance test was executed.

2. Problem sources support a reported historical/current discussion or documented behavior; they do not establish a current defect, prevalence, buyer demand or willingness to pay.

3. Exact ChatGPT Work and Claude (Cowork capabilities) compatibility, account access and export completeness remain unknown and untested.

4. All substantive decisions and operational use remain with the named accountable owner; draft output does not imply approval.

5. Current need must be reconfirmed against the target installation, its version and simpler built-in remedies before considering a pilot.

Candidate platforms — compatibility untested

1. Name

   ChatGPT Work

   Required capabilities

   1. Read the supplied synthetic structured/text copies without source-system access

   2. Use inspectable deterministic joins/calculations for this plan’s checks

   3. Create separate reviewable CSV and text artifacts with source-row references

   Capability source urls

   1. https://learn.chatgpt.com/docs/get-started-with-work

   2. https://learn.chatgpt.com/docs/artifacts-viewer

   3. https://learn.chatgpt.com/docs/sandboxing

   4. https://learn.chatgpt.com/docs/enterprise/chatgpt-work-overview

   Workflow compatibility

   Unknown and untested for every proposed plan.

   Selection basis

   Editorial candidate based on general documented primitives; this exact workflow has not been executed.

   Current access note

   Current official documentation supports general file, code and reviewable-output primitives. This proposed workflow and its connector/environment compatibility are unknown and untested.

   Setup caveat

   Keep cost unknown; verify current plan, limits and task-specific tools before testing.

   Availability in canada

   Not assessed by this reference update.

2. Name

   Claude (Cowork capabilities)

   Required capabilities

   1. Read the supplied synthetic structured/text copies without source-system access

   2. Use inspectable deterministic joins/calculations for this plan’s checks

   3. Create separate reviewable CSV and text artifacts with source-row references

   Capability source urls

   1. https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork

   2. https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude

   Workflow compatibility

   Unknown and untested for every proposed plan.

   Selection basis

   Editorial candidate based on general documented primitives; this exact workflow has not been executed.

   Current access note

   Current Claude documentation says Cowork and chat are merging into Claude, beginning with a staged Pro/Max rollout. Some accounts still show Cowork. Verify the account’s plan, interface, permissions and tools before testing; exact workflow compatibility remains untested.

   Setup caveat

   Use current help for actual runtime and permissions. Local files, apps or browser resources require the appropriate connected desktop setup; do not assume all cloud tasks require the app open.

   Availability in canada

   Not assessed by this reference update.