RecipeChatGPT Ads
Validate and reconcile ChatGPT Ads bulk changes
Run ChatGPT Ads bulk changes with native validation, explicit confirmation, job tracking and individual operation results.
IntentValidate bulk campaign operations, confirm the exact job and reconcile every outcome before declaring completion.
- 4
- Steps
- 9
- Tools
- 2
- Rules
- 2
- Failure modes
When to use it
Use it when
- The user requests a batch of campaign, ad-group or ad changes.
Do not use it when
- Treating an accepted job or a completed status as proof that every operation succeeded.
What it needs first
Required
Preconditions
- The selected account has native Bulk API access and the workspace permits writes.
- The account is ticked in the dashboard, confirmed via list_accounts.
Inputs
window- Analysis window.Default: last 30 days.
Procedure
In order. Every tool named is one the gateway ships, and links to its reference.
Read the bulk schema and account prerequisites. Use the distinct bulk operation bodies and dependency keys, not single-resource payloads.
Prepare validation-only, show the exact proposal, and submit only the confirmed job with stable request and operation keys.
Read job status, then every page of operation outcomes. Keep created, updated, validated, failed and skipped results separate.
Read affected campaigns, groups and ads and use the saved mutation receipt to reconcile uncertain responses.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
A job is accepted or still processing
Conclude
Keep it in progress; report completion only after terminal status, operation outcomes and native entity readback.
When
Some operations fail or a result is uncertain
Conclude
Explain successful and unresolved operations separately. Partial failures do not roll back successful changes; never resubmit the original uncertain job.
Evidence every conclusion must carry
- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.
Where the agent stops
- The human confirms the exact bulk proposal before submission. Campaign creation stays paused; activation needs a separate confirmed action.
How it goes wrong quietly
The cases where the analysis is wrong and still looks right. Read them before trusting a number.
- Validation-only outcomes are not created entities. Keep validation and application results distinct.
- Bulk access is controlled by the native account; the existence of a tool does not grant that access.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.