ChatGPT-Driven Clickstream SEO Analysis Workflow

Data AnalysisCozeUpdated 2026-04-08

Automatically analyze 17 months of clickstream data with AI to uncover search behavior shifts, keyword opportunities, and traffic sources, producing actionable SEO insights.

System Prompt

Use {dataset_path} for raw clickstream data, {analysis_goal} to define the focus, and {output_format} to specify report style.

Variable Dictionary (fill in your AI tool)

This section only explains placeholders. It is not an input form on this website. Copy the prompt, then replace variables in Coze / Dify / ChatGPT.

{dataset_path}

Path to raw clickstream data file or database connection string

Filling hint: replace this with your real business context.

{analysis_goal}

Analysis objective, e.g., "Identify top 5 keyword opportunities"

Filling hint: replace this with your real business context.

{output_format}

Report format, e.g., "Markdown table", "CSV", or "JSON"

Filling hint: replace this with your real business context.

Quick Variable Filler (Optional)

Fill variables below to generate a ready-to-run prompt in your browser.

{dataset_path}

Path to raw clickstream data file or database connection string

{analysis_goal}

Analysis objective, e.g., "Identify top 5 keyword opportunities"

{output_format}

Report format, e.g., "Markdown table", "CSV", or "JSON"

Generated Prompt Preview

Missing: 3

Use {dataset_path} for raw clickstream data, {analysis_goal} to define the focus, and {output_format} to specify report style.

How to Use This Template

Best for

Teams that need faster data analysis output with more stable prompt quality.

Problem it solves

Reduces blank-page time, missing constraints, and inconsistent output structure from ad-hoc prompting.

Steps

Copy the template prompt.
Paste it into your AI tool (Coze / Dify / ChatGPT).
Replace placeholder variables using the dictionary above.
Run and refine constraints based on output quality.

Not ideal when

You need live web retrieval, database writes, or multi-step tool orchestration. Use full workflow automation for that.

Success Case

Input:

dataset_path: 's3://bucket/clickstream_2025.csv', analysis_goal: 'Identify top 5 keyword opportunities', output_format: 'Markdown table'

Output:

| Keyword | Clicks | CTR | Avg. Dwell Time | |---|---|---|---| | ChatGPT | 12000 | 4.5% | 45s | | AI Writing | 9500 | 3.8% | 38s | | ... | ... | ... | ... |

Boundary Case

Input:

dataset_path: '', analysis_goal: 'Identify top 5 keyword opportunities', output_format: 'Markdown table'

Fix:

Make sure {dataset_path} points to an accessible CSV or database.

What to Try Next

Keep exploring with similar templates and matching tools.

Similar Templates

View all templates

Related Tools

View all tools

Continue Where You Left Off

No recent items yet.

Workflow Steps

1. Load {dataset_path} into a Pandas DataFrame.
2. Clean data: drop missing values, normalize timestamps, extract keywords and referrers.
3. Aggregate by session, keyword, and referrer to compute CTR, bounce rate, and average dwell time.
4. Pass aggregated data to OpenAI GPT‑4 with a prompt to generate insights and recommendations.
5. Format results in {output_format} and upload the report to the Coze knowledge base.