ai-visibility

Files (2)

• README.md
• SKILL.md

SKILL.md (first lines)

# AI Visibility Workflow

AI brand monitoring — see how LLMs perceive and recommend brands using YepAPI endpoints.

## Endpoints Used

| Endpoint | Cost | Purpose |
|----------|------|---------|
| `POST /v1/seo/ai/chatgpt` | $0.05 | What ChatGPT says about a brand or query |
| `POST /v1/seo/ai/gemini` | $0.05 | What Gemini says about a brand or query |

## Workflow

### Step 1: ChatGPT Brand Check

Run `POST /v1/seo/ai/chatgpt` with the brand query.

```json
{
  "query": "What is ExampleBrand?"
}
```

Returns: ChatGPT's response about the brand — sentiment, accuracy, competitor mentions.

### Step 2: Gemini Brand Check

Run `POST /v1/seo/ai/gemini` with the same query.

```json
{
  "query": "What is ExampleBrand?"
}
```

Returns: Gemini's response about the brand — compare with ChatGPT for differences.

### Step 3: Compare Responses

Compare ChatGPT vs Gemini responses:
- **Sentiment** — positive, neutral, or negative tone
- **Accuracy** — are the facts correct?
- **Competitor mentions** — does the AI mention competitors in your brand query?
- **Recommendations** — does the AI recommend your brand or alternatives?

### Step 4: Test Branded Variations

Run additional queries to map the full AI perception:

```json
{ "query": "ExampleBrand alternatives" }
{ "query": "ExampleBrand vs CompetitorBrand" }
{ "query": "best [category] tools" }
{ "query": "ExampleBrand review" }
```

Each variation reveals a different aspect of AI visibility.

### Step 5: Present AI Visibility Report

- **Brand perception** — what each AI says, sentiment analysis
- **Accuracy issues** — factual errors to correct (update website, Wikipedia, etc.)
- **Competitor threats** — competitors mentioned in your brand queries
- **Optimization opportunities** — content gaps that would improve AI citations

## Rules

- Test multiple query formats: brand name, "best [category]", "[brand] review", "[brand] alternatives"
- Compare ChatGPT vs Gemini — they often have different opinions and data freshness
- Track competitor mentions in AI responses — if competitors appear in your brand queries, that's a threat
- AI visibility is a new SEO frontier — changes in AI responses lag behind website changes by weeks/months

## Error Handling

- `NO_CREDITS` (402) — Tell the user to add credits at https://yepapi.com/dashboard
- `UPSTREAM_ERROR` (502) — Retry once; AI endpoints may occasionally timeout
- `VALIDATION_ERROR` (400) — Check query format; must be a non-empty string
- `RATE_LIMITED` (429) — Wait and retry; respect the `Retry-After` header

From YepAPI/skills, MIT.

More from YepAPI/skills