AI Pitch Deck Creator for Google Slides

Automatically generate professional pitch decks in Google Slides using AI and live web research. This workflow gathers user input, searches Google for relevant information, retrieves content from URLs, and builds a tailored presentation—ideal for startups, sales, or marketing teams needing instant, data-driven pitch decks.

How the AI Flow works

User Input Collection

Collects the subject and brief description from the user as the basis for the pitch deck.

AI Language Model Setup

Configures an OpenAI language model to generate content and guide the workflow.

Automated Web Research

Uses Google Search and URL content extraction to gather relevant, up-to-date information from the web.

AI Agent-Driven Pitch Deck Creation

An AI agent organizes the research and user input, using tools to create a structured pitch deck in Google Slides.

Presentation Delivery

Displays or shares the generated pitch deck with the user for immediate use.

Prompts used in this flow

Below is a complete list of all prompts used in this flow to achieve its functionality. Prompts are the instructions given to the AI model to generate responses or perform actions. They guide the AI in understanding user intent and generating relevant outputs.

Tool Calling Agent

Agent with custom system prompt for LLM to generate professional pitch decks in Google Slides.

                the user will provide you with a subject and a brief description (optional) and your duty is to create a professional pitch deck in google slides.


you can use google as a source for the information you provide in the pitch deck.

Components used in this flow

Below is a complete list of all components used in this flow to achieve its functionality. Components are the building blocks of every AI Flow. They allow you to create complex interactions and automate tasks by connecting various functionalities. Each component serves a specific purpose, such as handling user input, processing data, or integrating with external services.

ChatInput

The Chat Input component in FlowHunt initiates user interactions by capturing messages from the Playground. It serves as the starting point for flows, enabling ...

LLM OpenAI

FlowHunt supports dozens of text generation models, including models by OpenAI. Here's how to use ChatGPT in your AI tools and chatbots.

Tool Calling Agent

Explore the Tool Calling Agent in FlowHunt—an advanced workflow component that enables AI agents to intelligently select and use external tools to answer comple...

Create Google Presentation

Easily automate the creation of Google Slides presentations with the Create Google Presentation component in FlowHunt. Define your presentation title, first sli...

GoogleSearch Component

FlowHunt's GoogleSearch component enhances chatbot accuracy using Retrieval-Augmented Generation (RAG) to access up-to-date knowledge from Google. Control resul...

URL Retriever

Unlock web content in your workflows with the URL Retriever component. Effortlessly extract and process the text and metadata from any list of URLs—including we...

Chat Output

Discover the Chat Output component in FlowHunt—finalize chatbot responses with flexible, multi-part outputs. Essential for seamless flow completion and creating...

Flow description

Purpose and benefits

Workflow Overview

This workflow automates the generation of a professional pitch deck in Google Slides, leveraging AI and real-time web research. It is designed to receive a subject and optional description from the user, gather relevant information from Google Search, retrieve and process web content, and assemble the findings into a structured presentation—all with minimal manual intervention.

Such automation is highly valuable for scaling repetitive tasks like creating business decks, sales presentations, or research summaries. It ensures up-to-date, data-driven content and saves significant time compared to manual research and presentation building.

Step-by-Step Flow Description

1. User Input

Node: ChatInput
Function: Captures the user’s input, which is the subject and optionally a brief description for the pitch deck.
Output: The user’s message is forwarded as the main prompt for the workflow.

2. Language Model Initialization

Node: LLM OpenAI
Model Used: GPT-4.1 (customizable to other OpenAI models)
Settings:
- Max Tokens: 3000
- Temperature: 0.7 (for balanced creativity and coherence)
- Use Cache: Enabled for efficiency
Function: Provides advanced natural language understanding and generation abilities, enabling the agent to comprehend the prompt and generate structured content.

3. Tool-Calling Agent

Node: Tool Calling Agent
Function: Orchestrates the creation of the pitch deck by:
- Accepting user input and context
- Utilizing connected tools (Google Search, URL Content Retriever, Google Slides Creator)
- Following a system message that instructs it to build a professional pitch deck in Google Slides, using Google as an information source
- Limiting iterations to 20 to ensure quick responses

4. Connected Tools

The agent can call the following tools dynamically as needed:

Tool Name	Purpose
Google Search	Searches Google for information related to the subject.
URL Content Retriever	Fetches and processes the content of found URLs.
Google Slides Creator	Automatically generates a new presentation and slides.

a. Google Search

Node: GoogleSearch
Function: Performs a Google search (country: US, language: EN, location: NYC) and returns the top 3 results relevant to the query.
Why Useful: Ensures the most current and relevant information is available for the pitch deck.

b. URL Content Retriever

Node: URLContent
Function: Downloads and processes content from URLs found via Google Search, extracting key sections (headers, paragraphs, metadata).
Why Useful: Allows the agent to quote, summarize, or analyze source material for inclusion in the presentation.

c. Google Slides Creator

Node: CreateGooglePresentation
Function: Programmatically creates a new Google Slides presentation, including title, subtitle, and subsequent slides as instructed by the agent.
Why Useful: Automates the otherwise manual and time-consuming process of slide creation.

5. Output Display

Node: ChatOutput
Function: Presents the generated message or final output (e.g., confirmation or link to the created Google Slides presentation) to the user in the chat interface.

Data Flow Diagram

User Input → Tool Calling Agent
LLM OpenAI → Tool Calling Agent (provides natural language capabilities)
Google Search Tool → Tool Calling Agent (as an agent tool)
URL Content Tool → Tool Calling Agent (as an agent tool)
Google Slides Tool → Tool Calling Agent (as an agent tool)
Tool Calling Agent → Chat Output (final response to user)

Benefits and Use Cases

Scalability: Enables one person (or bot) to generate many presentations quickly.
Automation: Reduces manual research and slide-building time from hours to minutes.
Consistency: Ensures all presentations follow a professional, repeatable structure.
Up-to-date Content: Incorporates real-time information from the web.
Versatility: Can be adapted for use in sales, fundraising, education, consulting, and more.

Why This Is Useful

This workflow is ideal for anyone who frequently needs to create tailored, data-rich presentations—such as entrepreneurs, marketers, analysts, or educators. By automating research and slide creation, it frees up time for higher-level thinking and strategy, while ensuring that every deck is informed by the latest available information.

Let us build your own AI Team

We help companies like yours to develop smart chatbots, MCP Servers, AI tools or other types of AI automation to replace human in repetitive tasks in your organization.

Schedule a demo Try it now