### Providing Context Example

Source: https://profound-knowledge-base.help.usepylon.com/articles/5556357652-how-to-write-great-prompts

Example of how to specify context using a variable for YouTube video transcript output.

```text
Based only on this content:
{{YouTube Video Transcript Output}}

```

--------------------------------

### Providing Context Example

Source: https://profound-knowledge-base.help.usepylon.com/articles/5556357652

This example shows how to provide context to the LLM by referencing previous steps, such as YouTube video transcript output.

```text
Based only on this content:
{{YouTube Video Transcript Output}}
```

--------------------------------

### Example Prompt Structure

Source: https://profound-knowledge-base.help.usepylon.com/articles/5556357652-how-to-write-great-prompts

An example prompt demonstrating the core structure: Role, Task, Context, Requirements, and Output Format.

```text
You are an expert content strategist. Summarize the following research into 5 concise insights for a B2B marketing audience.

Context:
{{Web Page Scrape Output}}

Requirements:
- Focus only on key trends
- Avoid duplicate points
- Keep each insight under 20 words

Output Format:
- Bullet points only

```

--------------------------------

### Example Headline Formats

Source: https://profound-knowledge-base.help.usepylon.com/articles/5556357652-how-to-write-great-prompts

Illustrates good headline examples for AI-generated content.

```Text
For example, a good headline looks like:
- “How AI Improves Inventory Forecasting”
- “The Future of Predictive Supply Chains”

```

--------------------------------

### API Key Authentication Example

Source: https://profound-knowledge-base.help.usepylon.com/articles/2527960262

Configure API Key authentication by providing the Header Name and API Key Value expected by the target API.

```text
Header Name: `X-API-Key`
API Key Value: `<your_key_here>`
```

--------------------------------

### Prompt LLM Node Example

Source: https://profound-knowledge-base.help.usepylon.com/articles/7933790024-keyword-performance-node

Example prompt for the Prompt LLM node to generate a cross-channel visibility audit report based on cross-referenced keyword data.

```text
Produce a cross-channel visibility audit report from {{cross_reference_result}}.

Sections:
- Executive Summary — overlap % of paid spend vs. organic AI 
wins + headline recommendation.
- Spend at Risk — table: Total Paid Spend | Overlap Spend | Overlap %.
- Top Overlap Keywords — table of top 15: Keyword | Cost | Clicks | 
Conversions | Matched Asset | AI Visibility. Follow with 3–5 callouts for strongest 
cut candidates (high cost + high AI visibility + low conversions).
- Recommended Actions — 4–6 prioritized bullets with specifics 
(e.g. "Pause exact-match on [keyword] — savings: $X/period").
```

--------------------------------

### Specifying Output Format in JSON

Source: https://profound-knowledge-base.help.usepylon.com/articles/5556357652-how-to-write-great-prompts

Example of a prompt that requests the output in a specific JSON format with defined fields.

```text
Return your answer in JSON with fields:
- insight
- supporting_quote
- source_url

```

--------------------------------

### Example Perplexity Search Prompt

Source: https://profound-knowledge-base.help.usepylon.com/articles/6411432882

Example of a direct text prompt for Perplexity Search to gather information on a specific topic and cite sources.

```text
Explain the latest changes to Google’s AI Overviews and cite sources.
```

--------------------------------

### Slack Message Node Example

Source: https://profound-knowledge-base.help.usepylon.com/articles/7121289335-slack-integration

Use this example to send a message to a Slack channel. You can include dynamic variables from earlier workflow steps by typing '/'.

```text
New visibility report is ready!
Visibility Score: /visibility_score
Share of Voice: /share_of_voice
```

--------------------------------

### Example Query Fanout Output

Source: https://profound-knowledge-base.help.usepylon.com/articles/9723781244-query-fanout-estimator

This is an example of the structured text output from the Query Fanout Estimator node, representing likely search queries.

```text
what is query fan-out in ai search, how do llms expand user prompts into multiple web searches, impact of query fan-out on brand visibility, examples of query fan-out in google ai overviews,how to optimize content for query fan-out
```

--------------------------------

### Example Gamma Presentation Prompt

Source: https://profound-knowledge-base.help.usepylon.com/articles/9150935685-gamma-integration

Use this prompt structure to instruct Gamma's AI on generating a presentation. It includes specifying the audience, goal, and data sources, along with desired slide types.

```text
Create a 10-slide executive summary presentation based on the following visibility report.

Audience: Marketing leadership
Goal: Highlight key changes in Answer Engine visibility and recommend next steps.

Data:
Visibility Score: /visibility_score
Share of Voice: /share_of_voice
Top Performing Topics: /top_topics

Include a title slide, summary slide, data breakdown slides, and a recommendations slide.
```

--------------------------------

### Example Perplexity Search Prompts

Source: https://profound-knowledge-base.help.usepylon.com/articles/6411432882

Illustrates different types of queries that can be used with the Perplexity Search node, including direct questions and requests for summarized information with source links.

```text
What are the latest pricing updates for HubSpot Enterprise?
```

```text
Summarize the top three competitors to {{brand_name}} and provide source links.
```