Step 2: Connect Google Gemini

Configure the Gemini language model used by the AI agent to draft the post and image prompt.

1. Open Gemini Chat Engine and set Model Name to models/gemini-2.0-flash.
2. Credential Required: Connect your googlePalmApi credentials.
3. Confirm Gemini Chat Engine is connected as the language model for Content Draft Agent (credentials should be added on Gemini Chat Engine, not the agent).

Step 3: Set Up Input Mapping and AI Drafting

Map form data into a single prompt and use the AI agent to generate the LinkedIn post and image prompt JSON.

1. Open Map Input Fields and add an assignment: Name chatInput, Type string, Value {{ $json.Topic }}.
2. Open Content Draft Agent and set System Message to =I need help creating a professional LinkedIn post for the topic: "{{ $json.chatInput }}". The output should include: 1. **LinkedIn Post Content**: - Write an engaging and informative LinkedIn post on the topic " {{ $json.chatInput }}". - Start with an attention-grabbing hook that entices readers to read further. - Provide valuable insights or actionable tips related to the topic. - The tone should be professional, clear, and concise, using language that's easy to understand. - End with a call to action (CTA) encouraging the audience to engage, reflect, or share their thoughts. - Include relevant hashtags to increase engagement and visibility on LinkedIn. Make sure these hashtags are specific to the topic and aligned with trending keywords for LinkedIn posts. 2. Image Generation Prompt: Visual Aesthetic: The image should align with LinkedIn's professional and corporate atmosphere. Make sure it conveys sophistication, modernity, and relevance to the topic. Avoid overly busy designs. Color Palette: Stick to corporate tones such as blues, whites, and grays to maintain a professional and clean look. Consider using gradients for depth or subtle contrasts to highlight key elements. Imagery: Focus on visualizing the topic of the post. For AI in Business, this could involve: A futuristic office or workspace setting, highlighting cutting-edge technologies. Icons or symbols that represent data analysis, AI, or automation. Visuals of humans interacting with AI systems (e.g., robots working alongside humans or using AI tools). Abstract representations of neural networks or digital data flows. No Text Overlay: Do not include any text in the image, ensuring it remains clean and focuses solely on the visuals. Text overlays or titles are not necessary in this case to keep the professional look intact. Style and Tone: The design should be minimalist, modern, and sleek. Use a balanced layout with a focus on professional imagery that resonates with business-minded audiences. Avoid overly complex or distracting backgrounds—keep it clean and visually appealing. Font Style (if applicable): If any text were used in future visuals or branding (though none should appear in this image), use clean, modern fonts like Helvetica, Arial, or Roboto—sans-serif fonts that are readable and professional. image prompt can be like this short and simple A modern co-working space where AI assistants and human employees brainstorm around a digital whiteboard. The scene shows innovation and teamwork, with a multicultural group, smart gadgets, and subtle futuristic elements. Warm natural lighting and a balanced, professional layout ideal for a LinkedIn audience. the JSON output would look like this: { "post_content": { "text": "The Future of AI in Business: How It is Transforming Industries 🚀\n\nAI in Business is no longer just a buzzword; it's revolutionizing the way businesses operate today. From improving efficiency to driving innovation, AI is an essential tool for modern companies.\n\nHere are some key insights on how AI in Business is shaping the future of industries:\n1. Enhanced Data Analytics: AI helps businesses make data-driven decisions with greater accuracy.\n2. Automation of Tasks: AI is automating repetitive tasks, improving operational efficiency.\n3. Personalized Experiences: AI is enabling personalized customer experiences in real-time.\n\nIs your business ready to embrace AI in Business? Let's discuss how it can help drive growth and innovation.\n\n#AIinBusiness #Innovation #FutureOfWork #BusinessGrowth #TechnologyTrends #DigitalTransformation" }, "image_prompt": { "description": "Create an image for a LinkedIn post on the topic of AI in Business. The image should:\n- Feature modern, sleek visuals that align with the corporate tone of LinkedIn.\n- Visualize AI in Business through elements like a futuristic office, AI-powered systems, or human-robot collaboration.\n- Use a professional color palette like blues, whites, and grays.\n- The optional text overlay (if relevant) could be something like 'The Future of AI in Business' or 'Driving Innovation with AI'.\n- The design should use clean, modern fonts that are easily readable and match the professional style of LinkedIn posts." } }.
3. Ensure the flow is Map Input Fields → Content Draft Agent → Clean Output Data.

Step 4: Configure Image Generation and Data Cleanup

Convert the AI output into structured fields, generate an image, and decode the resulting image data.

1. Open Clean Output Data and keep the Code as provided to parse $input.first().json.output and return post_content and image_prompt.
2. Open Generate Image Request and set URL to https://gen-imager.p.rapidapi.com/genimager/index.php.
3. Set Method to POST, Send Body to true, and Content Type to multipart-form-data.
4. Add a body parameter Prompt with value {{ $json.image_prompt }}.
5. Enable Send Headers and add header parameters: x-rapidapi-host = gen-imager.p.rapidapi.com and x-rapidapi-key = [CONFIGURE_YOUR_API_KEY].
6. Open Decode Image Buffer and keep the Code as provided to parse the response and return decoded_image_buffer.
7. Confirm the flow Clean Output Data → Generate Image Request → Decode Image Buffer.

Step 5: Configure the LinkedIn Posting Action

Publish the drafted post and generated image to LinkedIn.

1. Open Post to LinkedIn Feed and set Text to {{ $('Clean Output Data').item.json.post_content }}.
2. Set Binary Property Name to {{ $json.decoded_image_buffer }}.
3. Set Share Media Category to IMAGE.
4. Ensure the connection is Decode Image Buffer → Post to LinkedIn Feed.

Step 6: Test and Activate Your Workflow

Run a full test to verify the AI draft, image generation, and LinkedIn posting steps.

1. Click Execute Workflow and submit the Form Entry Trigger with a sample Topic.
2. Verify Content Draft Agent returns valid JSON, Clean Output Data extracts post_content and image_prompt, and Generate Image Request responds with image data.
3. Confirm Post to LinkedIn Feed publishes a post with the generated image and drafted text.
4. Once successful, toggle the workflow to Active to use it in production.