Skip to main content

​
What is the Agent Builder?

The Agent Builder is a visual workflow editor that allows you to create sophisticated AI agent automations by chaining together multiple steps. Each step can be configured with specific instructions, tools, and context to build complex, multi-stage processes that handle everything from data gathering to decision-making to action execution.
Think of the Agent Builder as a flowchart for AI agents—you define the steps, provide context and tools, and let Narada orchestrate the execution.

​
Getting Started

1

Create a new agent workflow

Navigate to the Agent Builder and click Create Agent to start building your workflow.
2

Add agent steps

Add Agent steps to your workflow. Each step represents a specific task or action that your agent will perform.
3

Configure each step

Define the prompt, add context through attachments, provide tools via MCP servers, and specify output variables for each step.
4

Connect steps together

Link steps to create a logical flow. Use variables from previous steps to pass data forward.
5

Run your agent

Execute your agent workflow and watch as it completes each step in sequence.

​
Understanding Agent Steps

Agent Builder showing an agent step configuration
Agent steps are the building blocks of your workflow. Each step can be configured with:

​
Prompt

The natural language instruction that tells the agent what to accomplish in this step. Be specific and clear about the expected outcome.
Reference variables from previous steps using $variableName or $arrObj[$i] syntax to create dynamic, context-aware workflows.

​
Agent Type

Select the specialized agent for your task:

Operator

Browser automation agent for web-based tasks, form filling, navigation, and data extraction

Other Agent Types

Additional specialized agents for email management, CRM operations, and more

​
Attachments

Upload files to provide additional context to the agent. You can select multiple files that the agent will use to inform its actions.
Attachments are useful for providing reference documents, data files, or examples that the agent should consider during execution.

​
MCP Servers

Configure Model Context Protocol servers to provide additional tools and capabilities to the agent. Paste the URL of your MCP server to give the agent access to all tools within that server during this step’s execution.

Learn more about MCP

Create custom tools for your agents using the MCP Builder

​
Other Tools

Create custom Python tools directly within the agent step. These tools are defined with Python code and will be available to the agent during execution.
  • Other Tools: Quick, one-off functions specific to this agent workflow
  • MCP Servers: Reusable tool collections you want to share across multiple workflows

​
Output Variables

Define structured outputs that the agent should extract during this step. Output variables allow you to capture specific data that can be referenced in subsequent steps.
Add at least one output variable if you want the agent to generate structured output. Without output variables, the agent generates free-form responses only.
Example use case:
  • Step 1 outputs: $jobListings (array of job postings)
  • Step 2 references: "Analyze each job in $jobListings and extract requirements"

​
Additional Options

Enable this option to start the step with a clean slate, removing context from previous steps. Useful when you want to prevent context bleed between unrelated tasks.
This is checked by default in the UI to ensure each step starts fresh.

​
Building Complex Workflows

​
Variable References

Pass data between steps using variable syntax:
  • Simple Variables
  • Array Elements
  • Object Properties
Reference output from a previous step:
My data is $outputVariable

​
Example Workflow

Here’s a complete example of a multi-step agent workflow:
1

Step 1: Search for jobs

Prompt: "Search for software engineering jobs in Berkeley and extract the top 5 listings"
Output Variables: $jobListings
The agent searches job boards and extracts structured data.
2

Step 2: Analyze requirements

Prompt: "For each job in $jobListings, analyze the requirements and identify required skills"
Output Variables: $skillsAnalysis
The agent processes each job listing and extracts skills.
3

Step 3: Generate summary

Prompt: "Create a summary report of $skillsAnalysis showing the most common skills required"
Output Variables: $finalReport
The agent synthesizes the data into a final report.

​
Best Practices

Clear Prompts

Write specific, actionable prompts that clearly state the expected outcome for each step

Structured Outputs

Use output variables to extract structured data that subsequent steps can reliably reference

Modular Steps

Break complex tasks into smaller, focused steps for better reliability and debugging

Context Management

Use “Clear chat history” strategically to prevent context overload in long workflows

​
Common Use Cases

Build workflows that search multiple sources, collect data, analyze findings, and generate comprehensive reports.Example steps:
  1. Search academic databases for papers
  2. Extract key findings from each paper
  3. Synthesize findings into a summary report
Create workflows that gather information from various sources and fill out complex forms across multiple pages.Example steps:
  1. Extract data from uploaded documents
  2. Navigate to form website
  3. Fill out multi-page form with extracted data
  4. Verify submission and capture confirmation
Build pipelines that fetch data, transform it, validate it, and output it in a specific format.Example steps:
  1. Fetch data from API using MCP tool
  2. Transform and clean data
  3. Validate against business rules
  4. Export to desired format
Create workflows that analyze information, make decisions based on criteria, and take appropriate actions.Example steps:
  1. Gather relevant data
  2. Analyze against decision criteria
  3. Branch based on analysis (using If conditions)
  4. Execute appropriate action

​
Tips for Success

Test incrementally: Build your workflow step by step, testing each stage before adding the next. This makes debugging much easier.
Use descriptive variable names: Name your output variables clearly (e.g., $customerData, $searchResults) so they’re easy to reference later.
Leverage MCP servers: For common operations (API calls, data transformations), create reusable tools in MCP servers instead of rebuilding them in each workflow.

​
Next Steps

MCP Builder

Create custom tools to extend your agent’s capabilities

Python SDK

Integrate agent workflows into your applications programmatically

Plugins

Enable integrations with external services and platforms
⌘I