Proposal Generation
Submit business challenges via form; GPT-4 generates a branded Google Slides proposal and emails it to the prospect.
What it does
Turn business challenges and requirements into a professional, customized Google Slides proposal sent directly to prospects. The system analyzes your input via AI, populates your branded template with personalized content, and delivers the presentation link via email without manual effort.
Step by step
- Parse the JSON response from OpenAI to extract structured fields like title, body paragraphs, and image suggestions.
- Use the Google Slides API to create a new presentation based on a pre-defined template ID.
- Map extracted text fields to specific slide elements using their known element IDs within the template.
Where the LLM does the work
- Generate persuasive proposal copy that aligns with the user's input and your company's brand voice.
- Determine which sections of the pre-built template should be populated or hidden based on the specific business challenge provided.
- Refine the generated text to ensure it fits within character limits for slide text boxes without breaking layout.
Watch out for
Tools that fit
The agent brief
You are helping me build the following AI agent workflow. ## Goal Proposal Generation: Submit business challenges via form; GPT-4 generates a branded Google Slides proposal and emails it to the prospect. ## Specification - What it does: Turn business challenges and requirements into a professional, customized Google Slides proposal sent directly to prospects. The system analyzes your input via AI, populates your branded template with personalized content, and delivers the presentation link via email without manual effort. - Trigger: Triggered by an event (Manual · on form submission) - Autonomy: Fully hands-off - Expected setup effort: under an hour - Tools/services involved: - OpenAI: Analyze input and generate proposal text - Google Slides: Create presentation with personalized content - Gmail: Send proposal email to prospect ## Known pitfalls, handle each one explicitly in your implementation 1. Template element IDs change if the design is edited, so pin your template version or use a script to validate IDs before deployment. 2. Long text blocks will overflow slide placeholders so truncate or summarize content that exceeds the box dimensions. 3. OpenAI tokens can be consumed quickly by verbose prompts so set strict token limits and cache common responses. ## Reference implementation https://n8n.io/workflows/5082 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/automated-proposal-generation/ via usecasesforagents.com
Frequently asked questions
Can I use a different LLM than OpenAI?
Yes. OpenAI is only the example LLM in this recipe. The same flow works with Anthropic, Cohere, DeepSeek and Google Gemini. Swap the LLM connection and keep the rest of the setup as written.
Want this running in your business?
Who it's for
Built for founders and execs who need sales handled without hiring for it.
Freelancers and consultants can run this per-client with no changes beyond the source data.