AI ๅŽŸ็”Ÿๅผ€ๆ”พๆ•™ๆ

ๅค–่ง‚

Awesome LLM Appsๆธ…ๅ•ไธŽ้€ŸๆŸฅยท่‹ฑๆ–‡ๅŽŸๆ–‡ โ†—ๅŽŸไปถ โ†“ไป“ๅบ“ โ†—

๐Ÿ”ฌ AI Research Planner & Executor Agent with Google's Interactions API โ€‹

A streamlined multi-phase research agent built with Google's Interactions API that demonstrates stateful conversations, model mixing, background execution, and automatic infographic generation.

๐ŸŒŸ Features โ€‹

  • ๐Ÿ“‹ Phase 1 - Research Planning: Uses Gemini 3 Flash to create structured, actionable research plans
  • ๐Ÿ” Phase 2 - Task Selection & Deep Research: Select specific tasks and leverage Deep Research Agent with built-in web search
  • ๐Ÿ“Š Phase 3 - Synthesis + TL;DR: Uses Gemini 3 Pro for executive reports + Gemini 3 Pro Image for automatic infographic generation
  • ๐ŸŽจ Auto-Generated Infographics: Creates whiteboard-style TL;DR summary at the top of every report
  • ๐Ÿ”„ Stateful Conversations: Demonstrates previous_interaction_id for maintaining context across phases
  • โšก Background Execution: Async research execution with progress tracking
  • ๐Ÿ“ฅ Export Reports: Download comprehensive research reports as markdown files

๐ŸŽฏ How It Works โ€‹

User Goal
    โ†“
[Phase 1] Gemini 3 Flash โ†’ Research Plan
    โ†“
[Phase 2] Select Tasks โ†’ Deep Research Agent โ†’ Research Results
    โ†“
[Phase 3] Gemini 3 Pro โ†’ Executive Report
         + Gemini 3 Pro Image โ†’ TL;DR Infographic

Phase 1: Planning โ€‹

  1. Enter your research goal
  2. Gemini 3 Flash creates a numbered research plan with 5-8 specific tasks
  3. Plan is stored as an Interaction for stateful continuation

Phase 2: Select & Research โ€‹

  1. Review the research plan with checkboxes for each task
  2. Select/deselect tasks to focus your research
  3. Deep Research Agent executes comprehensive web research using previous_interaction_id

Phase 3: Synthesis + Infographic โ€‹

  1. Gemini 3 Pro synthesizes findings into an executive report
  2. Gemini 3 Pro Image automatically generates a whiteboard TL;DR infographic
  3. Report displays with infographic at the top, followed by full text
  4. Download as markdown

๐Ÿ› ๏ธ Tech Stack โ€‹

ComponentTechnology
Planning Modelgemini-3-flash-preview
Research Agentdeep-research-pro-preview-12-2025
Synthesis Modelgemini-3-pro-preview
Infographic Modelgemini-3-pro-image-preview
UI FrameworkStreamlit
Python SDKgoogle-genai

How to get Started? โ€‹

  1. Clone the GitHub repository
bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd advanced_ai_agents/single_agent_apps/research_agent_gemini_interaction_api
  1. Install the required dependencies:
bash
pip install -r requirements.txt
  1. Get your Google API Key
  1. Run the Streamlit App
bash
streamlit run research_planner_executor_agent.py

  1. Open your browser at http://localhost:8501

  2. Enter your Google API key in the sidebar and start researching!

๐Ÿ“ Example Research Goals โ€‹

  • "Research the B2B HR SaaS market in Germany - key players, regulations, pricing models"
  • "Analyze market opportunities for AI-powered customer support tools"
  • "Investigate the competitive landscape for sustainable packaging in e-commerce"
  • "Research regulatory requirements for fintech products targeting Gen Z"

โš ๏ธ Notes โ€‹

  • Beta API: The Interactions API is in Beta - features may change
  • Deep Research: May take 2-5 minutes for comprehensive research
  • Agent vs Model: Deep Research uses agent parameter, not model
  • Image Generation: Infographic generation uses the standard generate_content API

๐Ÿ”— Resources โ€‹

๐Ÿ“„ License โ€‹

Part of the Awesome LLM Apps collection.