Blog Post Pipeline
End-to-end blog post creation — research, outline, draft, SEO optimization, and publish
🧂 Ingredients
🔌 APIs
research_topics_find_sources_and_identify_keywords
🔄 Alternatives:
extract_content_from_reference_articles_for_research
🔄 Alternatives:
publish_posts_directly_to_your_blog
🔄 Alternatives:
content_calendar_and_post_tracking
🔄 Alternatives:
📋 Step-by-Step Build Guide
1. Input: blog topic or keyword to write about
1. Input: blog topic or keyword to write about
Input: blog topic or keyword to write about Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
2. Research: search the web for top-ranking articles on this topic, identify ang
2. Research: search the web for top-ranking articles on this topic, identify angles, data points, and gaps
Search the web using the Brave Search API.
GET https://api.search.brave.com/res/v1/web/search?q={query}&count=10&freshness=pd
Headers: X-Subscription-Token: {BRAVE_API_KEY}
Parse the results: extract title, URL, description for each result.
Deduplicate results from the same domain.
Score relevance based on: keyword match in title (high), recency (high), source authority (medium).
Return the top results with: title, 2-sentence summary, source URL, and publish date.
If the search returns no results, try broadening the query by removing the least important keyword.3. Keyword research: identify primary keyword, secondary keywords, and related q
3. Keyword research: identify primary keyword, secondary keywords, and related questions people ask
Keyword research: identify primary keyword, secondary keywords, and related questions people ask Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
4. Outline: create a structured outline with H2/H3 headers, key points for each
4. Outline: create a structured outline with H2/H3 headers, key points for each section, and word count targets
Outline: create a structured outline with H2/H3 headers, key points for each section, and word count targets Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
5. Draft: generate a first draft following the outline, incorporating research a
5. Draft: generate a first draft following the outline, incorporating research and data points
Draft: generate a first draft following the outline, incorporating research and data points Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
6. SEO optimization: optimize title tag (60 chars), meta description (155 chars)
6. SEO optimization: optimize title tag (60 chars), meta description (155 chars), header tags, keyword density, internal/external links
SEO optimization: optimize title tag (60 chars), meta description (155 chars), header tags, keyword density, internal/external links Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
7. Review: check for readability (short paragraphs, clear language), factual acc
7. Review: check for readability (short paragraphs, clear language), factual accuracy, and source attribution
Review: check for readability (short paragraphs, clear language), factual accuracy, and source attribution Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding. ⚠️ IMPORTANT: The next step (Step 8: "8. Publish: format for your CMS and either publish directly or save as a draft f") requires human action. Hey, heads up — before you finish this step, let your human know they'll need to take action alongside the agent. Don't proceed to the next step until your human confirms they're ready.
8. Publish: format for your CMS and either publish directly or save as a draft f
8. Publish: format for your CMS and either publish directly or save as a draft for review
Publish: format for your CMS and either publish directly or save as a draft for review Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
🤖 Example Agent Prompt
Input: blog topic or keyword to write about Steps: 1. Validate all required inputs are available 2. Execute the operation described above 3. Verify the result meets expected output format 4. Handle errors gracefully — retry transient failures, log and alert on persistent ones 5. Return structured output with status and any relevant data If any required data is missing, request it from the user before proceeding.
Copy this prompt into your agent to get started.