id: 5_web_research_agent
namespace: zoomcamp

description: |
  This flow demonstrates an advanced AI agent that uses tools autonomously.
  The agent:
  - Decides when to use the web search tool
  - Gathers information from multiple sources
  - Synthesizes findings into a structured report
  - Saves the output as a markdown file
  Key concept: You specify the GOAL, the agent decides HOW to achieve it.  

inputs:
  - id: research_topic
    type: STRING
    displayName: Research Topic
    defaults: |
      Research the latest trends in data orchestration and workflow automation.
      Include information about:
      - Popular tools and platforms
      - Emerging patterns (e.g., AI-driven orchestration)
      - Key challenges in the space
      - Recent innovations      

tasks:
  - id: research_agent
    type: io.kestra.plugin.ai.agent.AIAgent
    description: Autonomous research agent with web search capabilities
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
      modelName: gemini-2.5-flash
    prompt: "{{ inputs.research_topic }}"
    systemMessage: |
      You are a thorough research assistant. Follow this process:
      1. Use the TavilyWebSearch content retriever to gather up-to-date information on the topic. Search multiple times if needed to get comprehensive coverage.
      2. Evaluate the search results and determine if you have enough information. If not, search again with refined queries.
      3. Synthesize your findings into a well-structured Markdown report with:
         - Executive Summary (2-3 sentences)
         - Key Findings (3-5 bullet points)
         - Detailed Analysis (2-3 paragraphs)
         - Sources (list URLs of key references)
      4. Save the final report as 'research_report.md' in the /tmp directory
         using the filesystem tool.
      Important rules:
      - Always use the TavilyWebSearch content retriever to get current information
      - Do not make up or hallucinate information
      - Include specific examples and data points when available
      - Always save the final report to research_report.md using the filesystem tool.      
    contentRetrievers:
      - type: io.kestra.plugin.ai.retriever.TavilyWebSearch
        apiKey: "{{ secret('TAVILY_API_KEY') }}"
        maxResults: 10
    tools:
      - type: io.kestra.plugin.ai.tool.DockerMcpClient
        image: mcp/filesystem
        command: ["/tmp"]
        binds: ["{{workingDir}}:/tmp"]
    outputFiles:
      - research_report.md

  - id: log_report
    type: io.kestra.plugin.core.log.Log
    message: |
      ✅ Research completed!
      📄 Report saved to: {{ outputs.research_agent.outputFiles['research_report.md'] }}
      🔍 Agent made autonomous decisions about:
      - Which searches to perform
      - How many searches were needed
      - How to structure the report
      - When the task was complete
      📊 Token usage: {{ outputs.research_agent.tokenUsage.totalTokenCount }} tokens
      💡 This demonstrates the power of AI agents: you specified the GOAL,
         the agent figured out the HOW!