Menu
NEW AGENT
MY AGENTS
ASSISTANTS
Step 1:
Funny birthday cards from niche topic
1️⃣
Perfect output
- scan ALL
2️⃣ Add
output numbers
, then...
3️⃣ Add
Subagent Numbers
(work backwards
from output number!
)
4️⃣ Add
ACTUAL Skills
to subagent
✅ DONE..Copy x4 to Step 3...
SETTINGS
LOGOUT
What Shall We Build Next?
1
Describe
Describe your task
2
Refine
Refine the plan
3
SubAgents
Review all agents
4
Deploy
Deploy your agent
Sub Agent 1
Sub Agent 2
Sub Agent 3
Sub Agent 4
Sub Agent 5
Sub Agent 6
Sub Agent 7
Sub Agent 8
A) SUBAGENT SUMMARY: The Niche Researcher subagent gathers insights about a given niche topic, including keywords, phrases, trends, and visual style insights, and compiles them into a structured JSON file. B) FINAL TASK OUTPUT: A JSON file containing a list of keywords, phrases, trends, and visual style insights related to the given niche. The JSON file will have the following structure: { "niche_topic": "string", "research_summary": "string (1000 characters)", "related_keywords": [ { "keyword": "string", "relevancy_score": "integer", "comments": "string" } ], "relevant_domains": [ { "url": "string", "relevancy_score": "integer", "comments": "string" } ] } C) SUBAGENT INPUT: A text description of the niche topic to research (10-100 characters). E) SUBAGENT TASK SUMMARY: 1. Receive niche topic input from the user 2. Run skill #181 (Research Topic (Or Keyword) Deeply) to gather deep research about the niche topic - Input: Niche topic description - Output: 1000 character summary of the research 3. Run skill #184 (Brainstorm Related Keywords) to generate a list of related keywords - Input: Niche topic description - Output: List of 4 related keywords, listed in order, with comments 4. Run skill #185 (Brainstorm Most Relevant Domains/Websites) to identify relevant websites - Input: Niche topic description - Output: List of 4 related domains, listed in order, with comments 5. Use skill #178 (Rewrite Text Based On Instructions) to compile the findings into a structured JSON file - Input: Research summary, related keywords, and relevant domains, along with instructions to format the data into a JSON file - Output: JSON file containing the niche insights 6. Pass the JSON file to the Slogan Generator subagent F) SILOS: This subagent does not have any silos, as it follows a linear sequence of tasks to gather and compile niche insights.
SubAgent #1 - Diagram
Expand Diagram
A) SUBAGENT SUMMARY: The Slogan Generator subagent creates humorous, niche-specific slogans for birthday cards based on insights provided by the Niche Researcher subagent. B) FINAL TASK OUTPUT: A JSON file containing a ranked list of the top 3 humorous, niche-specific slogans, each slogan being a string of text no longer than 50 characters. C) SUBAGENT INPUT: The niche insights JSON file from the Niche Researcher subagent, containing a list of keywords, phrases, trends, and visual style insights related to the given niche. E) SUBAGENT TASK SUMMARY: 1. Receive the niche insights JSON file from the Niche Researcher subagent 2. Use skill #178 (Rewrite Text Based On Instructions) to generate a list of 10 humorous, pun-based slogans tailored to the niche, using the niche insights as input 3. Use skill #193 (Create 2-10 Short MicroCopy Text) to create 5 additional short, catchy phrases related to the niche 4. Combine the outputs from steps 2 and 3 into a single list of 15 slogans and phrases 5. Use skill #178 (Rewrite Text Based On Instructions) to rank the combined list of slogans and phrases based on relevance, humor, and originality 6. Select the top 3 slogans from the ranked list 7. Use skill #180 (Rewrite JSON (or other code) Based On Instructions) to compile the top 3 slogans into a JSON file 8. Pass the JSON file containing the top 3 slogans to the Image Creator subagent F) SILOS: Silo 1: Slogan Generation - Input: Niche insights JSON file - Action: Use skill #178 to generate 10 humorous, pun-based slogans - Output: List of 10 slogans Silo 2: Additional Phrase Generation - Input: Niche insights JSON file - Action: Use skill #193 to create 5 additional short, catchy phrases - Output: List of 5 phrases Silo 3: Ranking and Selection - Input: Combined list of 15 slogans and phrases from Silos 1 and 2 - Actions: - Use skill #178 to rank the combined list based on relevance, humor, and originality - Select the top 3 slogans from the ranked list - Output: List of top 3 slogans Silo 4: JSON Compilation - Input: List of top 3 slogans from Silo 3 - Action: Use skill #180 to compile the top 3 slogans into a JSON file - Output: JSON file containing the top 3 slogans
SubAgent #2 - Diagram
Expand Diagram
A) SUBAGENT SUMMARY: The Image Creator subagent generates a set of 3 AI-generated images in JPEG format, each corresponding to one of the top 3 slogans provided by the Slogan Generator subagent. B) FINAL TASK OUTPUT: 3 AI-generated images in JPEG format, each with a resolution of 1792x1024 pixels, corresponding to the top 3 slogans for the given niche topic. C) SUBAGENT INPUT: - A JSON file containing the top 3 slogans generated by the Slogan Generator subagent - The niche topic description provided by the user E) SUBAGENT TASK SUMMARY: 1. Extract the top 3 slogans from the input JSON file 2. For each slogan: a. Combine the slogan with the niche topic description to form a text prompt b. Use skill #169 (Create Dalle Image - Rectangle) to generate a 1792x1024 image based on the text prompt c. Save the generated image in JPEG format 3. Compile the 3 generated images into a folder 4. Pass the folder path to the Layout Designer subagent Detailed subagent flow: - Subagent input: [top-3-slogans-json], [niche-topic-description] - Action 1: Extract slogans from JSON using skill #178 (Rewrite Text Based On Instructions) - Action 2: Generate image for slogan 1 using skill #169 (Create Dalle Image - Rectangle) - Action 3: Generate image for slogan 2 using skill #169 (Create Dalle Image - Rectangle) - Action 4: Generate image for slogan 3 using skill #169 (Create Dalle Image - Rectangle) - Action 5: Compile images into a folder using skill #175 (Zip Internal URLs) - Subagent output: [slogan-image-set] F) SILOS: This subagent does not require silos as the tasks are sequential and do not involve parallel processing or complex branching logic. The subagent focuses on generating images for each slogan and compiling them into a single output folder.
SubAgent #3 - Diagram
Expand Flow
Here is the complete subagent flow for the Layout Designer subagent: A) SUBAGENT SUMMARY: The Layout Designer subagent combines the generated slogans and images into visually appealing birthday card designs. B) FINAL TASK OUTPUT: 3 complete birthday card designs in JPEG format, each featuring a unique slogan and image. The designs should be 2000x2000 pixels in size and optimized for print and digital use. C) SUBAGENT INPUT: - Niche insights JSON file from the Niche Researcher subagent - Folder path containing the generated images from the Image Creator subagent - JSON file with the top 3 slogans from the Slogan Generator subagent E) SUBAGENT TASK SUMMARY: 1. Extract niche insights, slogans, and image URLs from the input files 2. For each slogan-image pair (repeated 3 times, once for each card design): a. Use skill #213 to find additional relevant images for the card background and decorative elements b. Use skill #228 to resize and optimize the main image and additional images for the card layout c. Use skill #237 to combine the slogan, main image, additional images, and decorative elements into a professional-looking birthday card layout d. Use skill #228 to resize the final card design to 2000x2000 pixels e. Save the completed birthday card design in JPEG format 3. Use skill #175 to zip the 3 birthday card designs into a single file 4. Pass the zip file path to the Quality Controller subagent F) SILOS: Silo 1: Prepare design elements - Extract niche insights, slogans, and image URLs from the input files - Use skill #213 to find additional relevant images for the card background and decorative elements - Use skill #228 to resize and optimize the main image and additional images for the card layout Silo 2: Create card designs (repeated 3 times) - Use skill #237 to combine the slogan, main image, additional images, and decorative elements into a professional-looking birthday card layout - Use skill #228 to resize the final card design to 2000x2000 pixels - Save the completed birthday card design in JPEG format Silo 3: Package and deliver designs - Use skill #175 to zip the 3 birthday card designs into a single file - Pass the zip file path to the Quality Controller subagent
4 Template & Links
Expand Flow
A) SUBAGENT SUMMARY: The Quality Controller subagent ensures that the generated birthday card designs meet the required quality standards and are relevant to the given niche topic. B) FINAL TASK OUTPUT: A collection of 3 high-quality, niche-specific birthday card images in JPEG format, each with a resolution of 2000x2000 pixels and a file size not exceeding 1MB. C) SUBAGENT INPUT: - The designed cards folder path from the Layout Designer subagent - The niche insights JSON file from the Niche Researcher subagent E) SUBAGENT TASK SUMMARY: 1. Receive the designed cards folder path and niche insights JSON file 2. For each card design: a. Use skill #228 to resize the image to 2000x2000 pixels b. Use skill #198 to analyze the resized image for quality and accuracy to the niche topic c. If the image meets the quality standards and is relevant to the niche, save it to the approved images folder d. If the image does not meet the quality standards or is not relevant to the niche, discard it and log the issue 3. Repeat steps 2a-2d for all card designs 4. If fewer than 3 card designs meet the quality standards, log the issue and request the Layout Designer subagent to generate additional designs 5. Once 3 approved card designs are obtained, optimize the images to ensure the file size does not exceed 1MB each 6. Return the file path of the approved images folder Detailed subagent flow: subagent final input(s) > #228 - Resize Image > #198 - Analyze An Image With GPT Vision & Return Text > IF/ELSE decision to keep or discard image > Repeat for all images > Return approved images folder path > subagent final output(s) F) SILOS: Silo 1: Image Resizing and Analysis - Resize each image to 2000x2000 pixels using skill #228 - Analyze each resized image for quality and accuracy to the niche topic using skill #198 Silo 2: Image Approval - Based on the analysis results, decide whether to keep or discard each image - Save approved images to a designated folder Silo 3: Image Optimization - Optimize the approved images to ensure the file size does not exceed 1MB each - Return the file path of the optimized, approved images folder
5 Template & Links
Expand Flow
A) SUBAGENT SUMMARY: The Output Manager subagent stores and delivers the generated birthday card images to the user through a user interface or an API response. B) FINAL TASK OUTPUT: A system for storing and delivering the generated birthday card images to the user, either through a user interface (an HTML selector file displaying the images and a shareable download link) or an API response (a zipped file containing all the JPEG images, with internal and external download links). C) SUBAGENT INPUT: The approved images folder path from the Quality Controller subagent. E) SUBAGENT TASK SUMMARY: The Output Manager subagent receives the approved images folder path from the Quality Controller subagent. It then uses skill #175 to zip the images and generate a shareable link. Next, it uses skill #216 to create an HTML selector file displaying the images and the shareable link. Finally, it delivers the images to the user via the HTML selector file or an API response. Detailed subagent flow: 1. Receive the approved images folder path from the Quality Controller subagent 2. Use skill #175 to zip the images and generate a shareable link - Input: Internal URLs of the approved birthday card images - Output: A zipped file containing all the JPEG images, with internal and external download links 3. Use skill #216 to create an HTML selector file displaying the images and the shareable link - Input: List of the approved birthday card image URLs along with a description - Output: URL of the selector HTML file 4. Deliver the images to the user via the HTML selector file or an API response - Output: A system for storing and delivering the generated birthday card images to the user, either through a user interface (an HTML selector file displaying the images and a shareable download link) or an API response (a zipped file containing all the JPEG images, with internal and external download links) F) SILOS: This subagent does not require silos as it focuses on a single task of storing and delivering the generated birthday card images to the user.
6 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
7 Template & Links
Expand Flow
Questions & Research Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
8 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
9 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
10 Template & Links
Expand Flow
Questions & Research Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
11 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
12 Template & Links
Expand Flow
Need To Start Afresh?
BACK TO REFINE
Tweaked & Good To Go?
PROCEED TO DEPLOY