We use cookies to enhance your experience and measure how the site performs. Choose "Essential Only" to disable analytics. Read our Privacy Policy.

    Odeus Docs

    Agent

    Use AI to analyze data, make decisions, generate content, and extract structured information.

    Agent

    Use AI to analyze data, make decisions, generate content, and extract structured information.

    Agent Node

    Overview

    The Agent node is where AI comes into your workflow. It can analyze text, make intelligent decisions, extract structured data, generate content, answer questions, and much more - all using natural language instructions.

    Best for: Content analysis, categorization, data extraction, decision-making, summarization, and any task requiring intelligence.

    When to Use Agent Node

    Perfect for:

    • Analyzing and categorizing content
    • Extracting structured data from unstructured text
    • Making decisions based on criteria
    • Generating summaries or reports
    • Sentiment analysis
    • Answering questions about data
    • Content generation
    • Translation and language tasks

    Not ideal for:

    • Simple data reshaping between nodes (use the Transform node)
    • Deterministic branching (use the Condition node)
    • Sending data to an external endpoint (use the Webhook node)

    Configuration

    Select or Create Agent

    Use Existing Agent

    • Choose from your workspace agents
    • Inherits agent's configuration and knowledge
    • Consistent behavior across chat and workflows

    Create New Agent

    • Define agent specifically for this workflow
    • Configure independently
    • Optimized for automation

    Agent Instructions

    Provide clear instructions for what the agent should do:

    Good Instructions:

    Analyze the customer feedback and determine:
1. Sentiment (positive, neutral, negative)
2. Main topic category (product, service, pricing, support)
3. Urgency level (low, medium, high)
4. Key issues mentioned

Feedback: {{trigger.output.feedback_text}}

    Poor Instructions:

    Analyze this feedback: {{trigger.output.feedback_text}}

    Input Variables

    Pass data from previous nodes to the agent:

    Customer: {{trigger.output.customer_name}}
Order ID: {{trigger.output.order_id}}
Issue: {{trigger.output.description}}

Please analyze this support ticket and categorize it.

    Structured Output (Recommended)

    Define the exact structure you want from the agent:

    Why Use Structured Output:

    • Guaranteed format (always valid JSON)
    • No parsing errors
    • Reliable for downstream nodes
    • Easier to debug

    Example:

    {
  "sentiment": "positive",
  "category": "product_feedback",
  "priority": "medium",
  "summary": "Customer loves the new feature",
  "action_needed": false
}

    Configure:

    1. Enable "Structured Output"
    2. Define output fields:
      • Field name
      • Type (string, number, boolean, array)
      • Description

    Max Steps

    The maximum number of tool call steps the agent can take during execution. This prevents runaway agents from consuming excessive resources.

    Default: 25 steps Minimum: 1

    When to adjust:

    • Lower (5-10): Simple tasks with predictable tool usage
    • Default (25): Most use cases
    • Higher (50-100): Complex research or multi-step analysis tasks

    Tools & Capabilities

    Give the agent extra capabilities so it can do more than reason over the prompt:

    Web Search

    • The agent can search the web for fact-checking and current information

    Knowledge Hub

    • Attach Knowledge Hub content so the agent can retrieve from your documents
    • The agent automatically searches relevant content, with inline citations to the source file, page, and location

    Integration Actions (MCP connectors)

    • Add specific actions from your connected MCP connectors (for example, Slack, Notion, Linear, Jira, GitHub, HubSpot, Google Workspace, Microsoft 365)
    • Each action can optionally require confirmation before it runs (human-in-the-loop)
    • Specify which connection to use if you have multiple

    When a Node Fails

    If the agent node fails, the workflow stops and the run is marked as failed. Open the run in the Runs tab to inspect the node's input and output, then adjust the configuration and run again. For sensitive actions, add a Human-in-the-Loop approval node before them.

    Connection Overrides

    When using integration actions, you can override which connection the agent uses for specific tools. This is useful when:

    • You have multiple connections to the same integration (e.g., different Slack workspaces)
    • You want the workflow to use a specific service account

    Attachments

    Attach files directly to the agent node that will be available for processing. These can be:

    • Files uploaded to the workflow
    • Files from previous node outputs
    • Static reference documents

    Example Use Cases

    Content Categorization

    Agent Configuration:
- Instructions: "Categorize this article by topic and suggest tags"
- Input: {{trigger.output.article_text}}
- Model: Claude Haiku
- Structured Output:
  {
    "category": "string",
    "tags": ["string"],
    "confidence": "number"
  }

    Lead Qualification

    Agent Configuration:
- Instructions: "Score this lead based on company size, role, and use case"
- Input:
  Company: {{trigger.output.company}}
  Role: {{trigger.output.role}}
  Use case: {{trigger.output.use_case}}
- Model: Claude Sonnet
- Structured Output:
  {
    "score": "number (0-100)",
    "qualification": "hot|warm|cold",
    "reasoning": "string"
  }

    Document Summarization

    Agent Configuration:
- Instructions: "Summarize this document in 3-5 bullet points"
- Input: {{trigger.output.document_text}}
- Model: Claude Sonnet
- Structured Output:
  {
    "summary_points": ["string"],
    "key_topics": ["string"],
    "word_count": "number"
  }

    Sentiment Analysis

    Agent Configuration:
- Instructions: "Analyze sentiment and emotional tone"
- Input: {{trigger.output.customer_message}}
- Model: Claude Haiku
- Structured Output:
  {
    "sentiment": "positive|neutral|negative",
    "emotion": "string",
    "confidence": "number"
  }

    Accessing Agent Output

    Without Structured Output:

    {{agent_node_name.output.messages}}

    With Structured Output:

    {{agent_node_name.output.structured.sentiment}}
{{agent_node_name.output.structured.category}}
{{agent_node_name.output.structured.summary}}
{{agent_node_name.output.structured.tags[0]}}

    Prompt Engineering Tips

    Be Explicit

    ❌ "Analyze this text"
✅ "Analyze this customer feedback and categorize as bug, feature request, or question"

    Provide Context

    You are analyzing customer support tickets for a SaaS company.
Categorize by urgency based on:
- Urgent: System down, data loss, security issue
- High: Blocking user's work
- Medium: Inconvenience but has workaround
- Low: Feature request or question

    Use Examples

    Categorize these issues:
Example 1: "Can't log in, getting 500 error" → Urgent
Example 2: "How do I export data?" → Low

Now categorize: {{trigger.output.issue}}

    Constrain Output

    Respond with ONLY one of these categories: bug, feature, question
Do not explain your reasoning.

    Best Practices

    For workflows, structured output is almost always better. It prevents parsing errors and makes data easier to use in subsequent nodes.



Clear, detailed instructions lead to better results. Include examples if the task is complex.



Agents work best with focused inputs. If processing long documents, consider extracting relevant sections first.



Agent performance can vary. Test with actual data examples to ensure consistent results.



Add a Condition node after the agent to branch on unexpected outputs, and an
Approval node before any sensitive action.

    Next Steps

    • Transform Node — Reshape data before or after agent processing

    • Condition Node — Route based on agent decisions

    • Cost Management — Optimize agent costs

    • Agents — Learn about using agents in workflows