Speaker Bio from Book Research - Refine SubAgent & Output

Describe

Describe your task

Refine

Refine the plan

SubAgents

Review all agents

Deploy

Deploy your agent

OVERVIEW OF SUBAGENTS  
1. BookScraper – grabs all needed book data from Amazon → component 1  
2. PaletteMiner – extracts a branded 5-colour palette → component 2  
3. CopyBuilder – crafts headline, bullets, CTA → component 3  
4. SnippetAssembler – merges components 1–3 into the final HTML → component 4

SUBAGENT 1 – BookScraper  
• Name: BookScraper  
• Final output file: book_raw.txt (JSON-formatted plain text)  
• Primary skill(s):  
  – Skill #225: "Crawl 1 Amazon URL"  
• Procedure:  
  1. Fetch HTML from {book-url}  
  2. Parse for: title, author, description, "About the author," and the largest cover-image URL  
  3. Save the extracted fields as JSON ⇒ book_raw.txt  
  4. Return book_raw.txt

SUBAGENT REQUIRED INPUT: {book-url}  
SUBAGENT FINAL OUTPUT: [book-raw-json]

SUBAGENT 2 – PaletteMiner  
• Name: PaletteMiner  
• Final output file: palette.txt (key:value HEX list)  
• Primary skill(s):  
  – Skill #176: "Analyse Image & Return Text"  
• Procedure:  
  1. Read cover_img_url from [book-raw-json]  
  2. Download the image  
  3. Detect 5 dominant colours; label: primary, secondary, accent, light_bg, text (ensure WCAG contrast)  
  4. Save as palette.txt  
  5. Return palette.txt

SUBAGENT REQUIRED INPUT: [book-raw-json]  
SUBAGENT FINAL OUTPUT: [color-palette]

SUBAGENT 3 – CopyBuilder  
• Name: CopyBuilder  
• Final output file: marketing_copy.txt (structured text block)  
• Primary skill(s):  
  – Skill #190: "Write/Re-write Text"  
• Procedure:  
  1. Read [book-raw-json] for milestones, credibility hooks, transformation story  
  2. Distil 5 compelling milestones/events  
  3. Generate:  
     • Headline ≤ 12 words  
     • 4 punchy bullets ≤ 12 words each  
     • CTA text ≤ 3 words  
  4. Output structured text:  
     headline: …  
     bullets:  
       - …  
     CTA: …  
     ⇒ marketing_copy.txt  
  5. Return marketing_copy.txt

SUBAGENT REQUIRED INPUT: [book-raw-json]  
SUBAGENT FINAL OUTPUT: [marketing-copy]

SUBAGENT 4 – SnippetAssembler  
• Name: SnippetAssembler  
• Final output file: hero_section.html (self-contained snippet)  
• Primary skill(s):  
  – Skill #223: "Prompt → Text" (LLM code generation)  
• Procedure:  
  1. Read [color-palette], [marketing-copy], and cover_img_url inside [book-raw-json]  
  2. Generate responsive HTML/CSS per spec:  
     • <section id="hero"> wrapper  
     • Inline <style> that applies light_bg (background), primary (headline), text (body), accent (CTA hover)  
     • Flexbox: text left, 120 px cover image right (stack on mobile)  
     • Insert headline (<h1>), bullets (<ul><li>…), CTA link/button, and <img class="book-thumb">  
  3. Output complete snippet ⇒ hero_section.html  
  4. Return hero_section.html

SUBAGENT REQUIRED INPUT: [color-palette], [marketing-copy], [book-raw-json]  
SUBAGENT FINAL OUTPUT: [hero-section-html]

Final Exact Output You Want ⚠️IMPORTANT⚠️

Expand

Other Possible SubAgents (Consider Adding These Above) ☝️🤔

Expand

#223 - Powerful LLM Prompt-to-Text Response  
DESCRIPTION: This skill uses a very powerful LLM to answer any query. It will return a text response. The LLM can only input text and is not multimodal.  
INPUT NEEDED: Prompt and any other information required to answer the query.  
OUTPUT:  Text response from LLM

#216 - Research Topic (Or Keyword) Deeply  
DESCRIPTION: This skill will research a given topic or keyword deeply. This skill will run a number of searches on various search engines, visit several websites, and collate a large amount of research information, then use a LLM to summarize the research provided, based on the information that has been requested.  
INPUT NEEDED: Keywords and/or topic to research  
OUTPUT: 1000-3000 character summary of researched text

#226 - Extract Structured Data From 1x URL  
DESCRIPTION: Crawls any URL and extracts structured data  
INPUT NEEDED: Requires URL and information to extract from the page  
OUTPUT: Summary of structured data about URL, summarized in text

#174 - Take screenshot of website  
DESCRIPTION: This skill will take a 1400x2400 screenshot of a given website.  
INPUT NEEDED: URL of website to screenshot  
OUTPUT: URL of PNG image (1400x2800)

#187 - Find Relevant Images with Brave Search  
DESCRIPTION: This skill inputs a keyword (and optional use case, aspect ratio of other requirements for the images) and finds searchable images for any keyword. This is a very powerful tool which will search the entire Internet, and so will always return images. This is useful for adding images to an article or video.  
INPUT NEEDED: Type of images I want to get (such as keywords, description of images and aspect ratio)  
OUTPUT: List of 5 most relevant images as URLs

#222 - Make Image (Especially With Text)  
DESCRIPTION: This skill uses an Image AI which is very good at both prompt adherence and generating text. You should use this for any image task which requires text. It can generate images in a range of aspect ratios.  
INPUT NEEDED: Information about the information required (the AI will generate its own particular prompt, so the more information inputted the better).  
OUTPUT: PNG image URL

#186 - Create 2-10 Short MicroCopy Text  
DESCRIPTION: This skill uses an LLM to write several pieces of "micro-copy" (ie small copywriting or creative texts, to be used within a banner or some other asset). The skill will output a list of the requested copy.  
INPUT NEEDED: Info about product/topic to write about  
OUTPUT: Textual response - a list of micro-copy elements

#191 - Resize Image  
DESCRIPTION: Takes an image URL, with required x/y size and returns a new resized image.  
INPUT NEEDED: URL of image + Size required for image  
OUTPUT: Image URL of new resized image

#182 - Create Dalle Image (Transparent Square)  
DESCRIPTION: This skill creates a 1024x1024, square, transparent PNG file, based on a given text prompt. The image created should be of a singular object/scene with a clearly defined edge (so the background remover works particularly well). This skill is especially great at creating icons, vectors, cartoons, physical objects, etc. Once the image is created it is saved to the server as a .png file.  
INPUT NEEDED: A prompt to generate the image (if no prompt is provided, this task will generate one based on whatever text information is inputted)  
OUTPUT: URL of transparent PNG file

#221 - Recreate New Image From Image URL  
DESCRIPTION: This task inputs an image URL and uses a very powerful AI to recreate it.  
INPUT NEEDED: URL of image to recreate/remix, plus ideally a prompt description of any changes or guidance to consider when making the image  
OUTPUT: PNG image URL

#215 - Summarise and Return All Final Output Files
DESCRIPTION: This skill returns a summary of various previous skills that have completed, and is particularly useful when appearing at the end of an entire Agent task, silo or sequence of skills.
INPUT NEEDED: at least one output (perhaps other supplementary ones that may be helpful)
OUTPUT: nice text summary containing 1 or more outputs

Task Summary (You Wrote)

Expand

Diagram Of Entire Task (All SubAgents)

Expand Diagram

Ready To Proceed?

When you are ready to proceed, click the Save button to load the next step...
The next step is SubAgents. It will take around 10 minutes to load this page...
If you are entirely unhappy with this page, click Back to rerun Step 1 again.
Before saving, check the SubAgents and Output fields above (very important!)
The Agent heavily relies on the SubAgents and Output fields to build your task.

-- The LLM has raised some questions to help you clarify the desired final `output` (important - this must be specific) 
-- These ideas are worth scanning briefly (then either amend output/subagents -- or go back to step 1)
-- The first few points regarding how to clarify the `output` are particular important!
-- If you need to make your output more specific, change it (on the previous tab)...

## QUESTIONS RAISED BY THE LLM:

Let me analyze this task:

a) Questions to clarify the final output:
1. What specific format is needed - is this for a website, a document, or a presentation?
2. What's the intended length of the final piece? (Number of bullet points or words)
3. Should this be strictly professional, or can it include personal anecdotes?
4. Is this meant to be a standalone piece, or part of a larger marketing campaign?
5. Who is the target audience specifically? (Industry, position level, etc.)
6. Should there be a specific call-to-action included?
7. Are we looking to highlight specific achievements/milestones from the speaker's journey?
8. Should we include any testimonials or social proof?

b) Required inputs:
1. Access to the book content or a comprehensive summary
2. The book cover image for color scheme reference
3. The speaker's current professional focus and offerings
4. Any existing marketing materials or brand guidelines
5. Target audience demographics
6. Specific speaking topics or areas of expertise
7. Any preferred call-to-action or contact information
8. Any testimonials or social proof that should be included

c) Task segmentation suggestions:
I would suggest segmenting this task into these specialized areas:
1. Content Analysis: Deep dive into the book to extract compelling story elements and key messages
2. Visual Design: Color palette development based on book cover analysis
3. Copy Development: Creating attention-grabbing headlines and bullet points
4. Format Optimization: Testing different formats for maximum impact in the first seven seconds
5. Call-to-Action Development: Crafting compelling next steps that motivate prospects to reach out

Each of these areas requires different expertise and could benefit from focused attention to ensure the final product is cohesive and effective.

Expand

a) Here are some questions that could be asked to clarify the final output of the task:

1. What is the specific goal with the content we are pulling? Is it to inform, educate, engage, or incite specific action from the prospective customers?
2. What kind of format are we looking for the final output? Should it be in the form of a one-page portfolio about the speaker, a brief bio, an article, a blog post, or a social media post?
3. What key aspects of the Speaker's journey are significant? Are there any specific achievements or professional history that should be emphasized?
4. How verbose should the output be? Do you prefer a quick summary style or a more detailed report?
5. How many of these bullet-point lists or articles are needed? Do you want just one or multiple for testing different presentations?
6. What constitutes the "color schemes" for the website? Can you provide specific colors or a branding guide to follow? 
7. What key details from the book should be incorporated? Are there any specific chapters or passages?

b) The AI agent might need the following inputs prior to initiating the task:

1. Specific link to the author's book that needs to be crawled for information. 
2. Access to any existing resources about the Speaker or his journey.
3. Information about the target audience, including details about what they might find appealing or motivational.
4. A clear understanding of any preferred stylistic guides, tone, or voice.
5. Information about the brand or personal image that the final content should align with, including any specific color schemes.
6. Any specific goals or objectives that the content should achieve.

Research Links

Tony Robbins Speaking Page Hero Section

Simon Sinek Leadership Speaker Bureau Bio

Gary Vaynerchuk Speaking Page Personal Brand

Brendon Burchard High Performance Institute Speaker Page

Mel Robbins Motivational Speaker Landing Page

☝️ Like These? Consider Bringing These Ideas Into Output Or SubAgents (on previous page)

-- The LLM has suggested possible templates that could be useful to build this agent. 
-- Consider preparing these now...(you can upload them as `pre-prompts` in the next stage).
-- These prompts must be text, HTML or a URL (eg of an image or some folder).

## TEMPLATE IDEAS FROM THE LLM:

Given the end goal is a website "hero section" that showcases a speaker's journey in an attention-grabbing way, here are valuable templates we could collect:

1. Professional Speaker Websites
- Search for top professional speakers in personal development/motivation
- Capture screenshots and HTML/CSS of their above-the-fold sections
- Particularly speakers who have written books and feature them alongside their story
- Examples: Tony Robbins, Simon Sinek, Mel Robbins

2. Book Landing Pages
- Landing pages for bestselling personal development books
- Focus on how they present the author's journey/credentials
- Examples: Amazon's "About the Author" sections for top business/motivation books
- Publisher websites featuring author bios

3. Speaker Bureau Listings
- How professional speaking bureaus present their top speakers
- The bullet-point format they use to highlight speaker credentials
- Examples: Washington Speakers Bureau, Leading Authorities

4. Conference Speaker Pages
- How major conferences present their keynote speakers
- The format used to quickly communicate speaker value
- Examples: TED speaker pages, major business conference sites

For each template, we'd want to capture:
- Screenshot of the full hero section
- HTML/CSS source code
- Color schemes used (especially those derived from book covers)
- Bullet-point structures
- Call-to-action placement and wording

Specific Tasks for the Agent:
1. Search for and screenshot 5 professional speaker websites
2. Extract color palettes from these sites
3. Analyze bullet-point formats used to present credentials
4. Note common patterns in how speaker journeys are presented
5. Review HTML/CSS patterns for hero sections

This would give us a strong foundation of real-world examples to inform our output format and ensure we're aligned with industry best practices.

Would you like me to suggest specific websites/URLs for the Agent to analyze as templates?

Final Points Before Saving!

If you are at all unsure about this step, consider returning to step 1 (having taken new ideas from this Step 2 page)
DO NOT proceed to Step 3 if the information on this page has raised fundamental problems with your initial task
If the original description you wrote on Step 1 is largely correct, and this page has not really changed your mind about anything, then simply tweak the Output and SubAgents fields and Save (you can always hit BACK later)
IMPORTANT: If your initial description (Step 1) and Subagent & Output (Step 2) are flawless then the Agent will take it from here and your task will be easy to build. BUT if you are already seeing problems, consider hitting BACK and starting again.
It is MUCH easier to go back a step than to try to refine and imperfect task down the line. Final chance to start again!
Remember - the initial description on Step 1, along with the SubAgent summary & Output spec on Step 2, are the foundation on which all remaining steps and Agents run. This step is here for a reason, so please consider hitting back. It will save time later!

Need To Start Afresh?

BACK TO DESCRIBE

Speaker Bio from Book Research - Refine SubAgent & Output

Describe

Refine

SubAgents

Deploy

Final Exact Output You Want ⚠️IMPORTANT⚠️

Expand

Other Possible SubAgents (Consider Adding These Above) ☝️🤔

Expand

Task Summary (You Wrote)

Expand

Diagram Of Entire Task (All SubAgents)

Expand Diagram

Ready To Proceed?

More Questions & Research Ideas (LLM #2)

Expand

Research Links

☝️ Like These? Consider Bringing These Ideas Into Output Or SubAgents (on previous page)

Final Points Before Saving!

Need To Start Afresh?

Tweaked & Good To Go?