# Ad creative research workflow

Ad creative research workflow. Follow concrete contracts, examples and reviewable steps using Meta Ad Library, Google Ads.

Canonical page: https://datanavoapi.com/en/skills/ads/

This is a local simulation. Program-generated samples are not live platform data and do not establish provider availability.

## Inputs, goal and deliverable

Start with advertisers and keywords, then inspect creatives, observed dates and destinations.

Inputs consist of explicit platforms, keywords or object identifiers. Preserve the samples, request IDs, classifications and unresolved questions in the deliverable. The task does not schedule itself or paginate indefinitely.

## Step-by-step plan

| Step | Capability | Input | Output |

| --- | --- | --- | --- |

| 1 | meta.ads.search | query, sort | ad / items |

| 2 | google.advertisers.search | query | advertiser / items |

- [Meta Ad Library search](https://datanavoapi.com/en/apis/meta/ads/search/)
- [Google advertiser search](https://datanavoapi.com/en/apis/google/advertisers/search/)

## Reusable task prompt

Ask the client to present a plan before you confirm each execution. This prompt bounds the sample; it does not call an external service for you.

```text
Goal: Ad creative research workflow
Use only DataNavoAPI local demo/simulated mode.
Planned capabilities: meta.ads.search → google.advertisers.search
Describe inputs and output fields and propose a bounded request count first.
Execute explicitly, retaining request IDs. Stop on failures or unknown outcomes.
Return a table, missing fields and sampling limits; never present fictional samples as market facts.
```

## Plan, run and export

This bounded example has 2 steps. Successful customer simulation costs 3 TEST; anonymous demo costs zero. Provide each required identifier before generating a fixed plan; search results do not expand the request list automatically.

Use data.items[].id for the matching platform and object detail, account IDs for account content and comment IDs for replies. Check object types before reusing an ID. Fixture IDs do not establish a real relationship. The workbench exports per-step JSON and source-labelled CSV.

| Workbench field | Meaning | Example |

| --- | --- | --- |

| query | 研究关键词 | 户外咖啡 |

| step1_region | 步骤 1 · region | US |

| step2_region | 步骤 2 · region | US |

```json
{
  "schemaVersion": 1,
  "templateId": "ads",
  "runId": "00000000-0000-4000-8000-000000000001",
  "inputs": {
    "query": "户外咖啡",
    "step1_region": "US",
    "step2_region": "US"
  },
  "maxTotalCredits": 3,
  "estimatedCredits": 3,
  "priceVersion": "test-credit-v1",
  "steps": [
    {
      "id": "step-1",
      "title": "Meta 广告库搜索",
      "capability": "meta.ads.search",
      "params": {
        "query": "户外咖啡",
        "region": "US",
        "sort": "popular"
      },
      "maxCredits": 2,
      "idempotencyKey": "wf:00000000-0000-4000-8000-000000000001:step-1"
    },
    {
      "id": "step-2",
      "title": "Google 广告主搜索",
      "capability": "google.advertisers.search",
      "params": {
        "query": "户外咖啡",
        "region": "US"
      },
      "maxCredits": 1,
      "idempotencyKey": "wf:00000000-0000-4000-8000-000000000001:step-2"
    }
  ]
}
```

- [Open this task in the workbench](https://datanavoapi.com/tools/workflow-runner/?template=ads)
- [Download Skill instructions](https://datanavoapi.com/downloads/skills/ads.md)

## Review and stop conditions

- Each conclusion links back to a sample and request ID.
- Pagination stops at the agreed bound.
- Missing fields remain missing rather than being invented by the model.
- External writes, scheduled monitoring and automatic top-ups are not enabled by this workflow.

## Related pages

- [Meta Ad Library search](https://datanavoapi.com/en/apis/meta/ads/search/)
- [Meta ad detail](https://datanavoapi.com/en/apis/meta/ads/get/)
- [Google advertiser search](https://datanavoapi.com/en/apis/google/advertisers/search/)
- [Google advertiser's ads](https://datanavoapi.com/en/apis/google/advertisers/ads/list/)
- [Ad fields](https://datanavoapi.com/en/docs/objects/ad/)
- [Which data tools fit a marketing research task?](https://datanavoapi.com/en/answers/chinese-social-media-marketing-data-tools/)
- [How do I organize Google advertising transparency data?](https://datanavoapi.com/en/answers/google-ads-transparency-center-api/)
- [How do I research Meta ads through an API?](https://datanavoapi.com/en/answers/meta-ad-library-api/)
- [Competitor content research workflow](https://datanavoapi.com/en/skills/competitors/)

[中文](https://datanavoapi.com/skills/ads/)
