Agent Component — Complete configuration guide

Learn how to quickly create your first Agent and then explore the full set of configuration options step by step.

Create your own AI Agent with the Agent Component. This component abstracts the APIs of major LLM providers so you can easily perform tasks such as text classification, information extraction, summarization, content evaluation, and more — all inside your Digibee pipelines.

This guide walks you through:

• Setting up a working Agent in minutes

• Understanding each configuration option

• Exploring advanced features like tools, retrieval, guardrails, and mock responses

Quickstart: Build your first working agent in 5 steps

Prerequisites

Before starting, you need:

• An account with the chosen LLM provider and an API key (token).

• The API key registered in Digibee as an Account of type “Secret Key”.

This test will consume tokens from your provider.

To add your API key:

Open Accounts, select Create, choose Secret Key, paste the provider token, and save. The token must be generated from the provider console (for example, the OpenAI dashboard). Keep it secure.

Steps

1. Add the Agent Component to your pipeline from the Step Library or via the Smart Connector.

2. In Model, choose a model from any supported provider (for example, OpenAI — GPT-4.1 Mini).

3. Click the gear icon (⚙) and select the Secret Key account you configured in the Accounts page.

4. In the Messages section, insert:

   • System: You are an assistant.

   • User: Explain what an API is in one paragraph.

5. Click Play to test the Agent.

6. The response should look similar to this:

{
    "body": {
        "text": "An API, or Application Programming Interface, is a set of rules and protocols that allows different software applications to communicate and interact with each other. It defines the methods and data formats that programs can use to request and exchange information, enabling developers to integrate and extend the functionality of existing systems without needing to understand their internal workings. Essentially, APIs act as bridges that facilitate seamless interaction between different software components, making it easier to build complex applications by leveraging external services and data."
        },
    "tokenUsage": 
    {
        "inputTokenCount": 16,
        "outputTokenCount": 93,
        "totalTokenCount": 109
    }
}

Your Agent is now successfully running.

The next sections explain each configuration in detail.

Detailed configuration

Some settings are required for the component to run properly. After completing the basic configuration, you can explore more advanced features.

Required configuration

With the two steps below, your Agent is ready for simple and direct tasks.

1

Select the model (required)

Choose the LLM provider and model your Agent will use. Supported providers:

• Anthropic Claude

• DeepSeek

• Google Gemini

• OpenAI

• Azure OpenAI

• Custom Model

• Azure OpenAI (Private)

• Amazon Bedrock (Private)

Or select Custom Model to personalize the model.

After selecting the provider, click the gear icon (⚙) to open the Model Configuration page. Complete the fields below.

Account Configuration

These settings define how Digibee authenticates with the selected LLM provider. If no account is selected, the connector will not operate. Some providers also require a custom Endpoint, depending on how they expose their models.

Private providers — such as Azure OpenAI (Private) and Amazon Bedrock (Private) — always require a custom endpoint. When you select one of these providers, make sure you provide the correct endpoint for your environment.

For Amazon Bedrock, additional configuration is required:

• Select the AWS-V4 account type, the authentication method supported by Bedrock.

• Because Digibee does not offer predefined models for Bedrock, you must enable Custom Model and enter the ARN (Amazon Resource Name) of the model you want to use from your AWS account.

Parameter	Description	Data type	Supports DB	Default
Account	The account used to authenticate with the LLM provider. It must be previously registered in Accounts. Supported types: Secret Key or AWS-V4 (for Bedrock).	Account	❌	N/A
Endpoint	Custom endpoint for the selected provider. Required for private providers (such as Azure OpenAI or Amazon Bedrock).	String	✅	N/A
Allow Insecure Connections	Allows the client to accept insecure SSL connections. Recommended only for testing or internal environments.	Boolean	❌	false

If you select a private model, you must also configure the Custom Model Name. If you choose to fully customize the model, you must set both the Custom Model Name and a compatible provider.

Model Parameters

These values determine the model’s personality and behavior. You can adjust them as needed or keep the default settings.

Parameter	Description	Data type	Supports DB	Default
Temperature	Controls creativity. Lower values = more focused; higher values = more diverse.	Float	✅	0.7
Max Output Tokens	Limits the number of tokens in the output.	Integer	✅	1024
Top K	Limits how many word options the model considers at each step. Lower = safer; higher = more diverse.	Integer	✅	64
Top P	Controls variability using probability thresholds. Lower = more focused answers.	Integer	✅	1
Frequency Penalty	Reduces repetition of identical words.	Integer	✅	N/A
Presence Penalty	Encourages the model to bring in new ideas instead of staying in the same topic.	Float	✅	N/A

Advanced Settings

Use these options to fine-tune the model’s performance and resilience. You can modify them if necessary or keep the default configuration.

Parameter	Description	Data type	Supports DB	Default
Timeout	Maximum allowed time (in ms) for the operation to complete.	Integer	✅	30000
Max retries	Number of retry attempts after a failure.	Integer	✅	3
Custom Parameters	Additional custom parameters to include in the model API request.	Key-value pair	❌	N/A

Response Format

Define how the model should structure the output. When supported by the provider, setting a JSON Schema is recommended to ensure more precise and consistent responses.

Parameter	Description	Data type	Supports DB	Default
Use JSON Schema	Enables providing a JSON Schema to enforce response structure.	Boolean	❌	false
JSON Schema definition	The Schema defining the expected structure.	JSON	❌	N/A
Use JSON Mode	Enables sending a JSON example to guide the response.	Boolean	❌	false
JSON definition	The JSON example the model should follow.	JSON	❌	N/A

2

Configure the messages (required)

Messages define how the model behaves and how it interprets your prompt.

• System message: Describes rules, tone, and general behavior.

  • Example: “You are a senior data analyst…”

• User message: The actual prompt. You can inject pipeline data using Double Braces.

  • Example: “Summarize the content below…”

After adding your messages, you’re ready to test the Agent.

Every execution consumes tokens from your provider. To reduce token usage when testing the full pipeline, consider adding a mock response.

Optional configuration

Optional settings let you extend and customize the behavior of the Agent. These are not required, but they are useful when you need integrations, external context retrieval, validation, or controlled testing.

1

Add tools (optional)

Tools expand what the Agent can do. Use them when the Agent needs to:

• Call APIs

• Access internal systems

• Trigger other pipelines

• Fetch external web content

If you're only generating text or doing classification, you can skip tools.

Here’s how to configure the supported tool types.

MCP Server

A Model Context Protocol (MCP) server handles communication between the AI model and source systems, enabling the LLM to securely access external tools and data.

Parameter	Description	Data type	Supports DB	Default
Name	Identifier for this MCP server.	String	✅	N/A
Server URL	Endpoint that receives the request.	String	✅	N/A
Account	The account to authenticate with. Must be configured in Accounts. Supported type: Secret Key.	Account	❌	N/A
Custom Account	A secondary account, referenced via Double Braces, for example {{ account.custom.value }}.	String	❌	N/A
Headers	HTTP headers to include in requests.	Key-value pairs	❌	N/A
Query Parameters	Query parameters to include in the request.	Key-value pairs	❌	N/A

Content Retrieval

Enable Retrieval-Augmented Generation (RAG) so the model can use external context stored in a vector database.

Embedding Model

An embedding model converts text into vectors that capture its meaning. Choose a provider and model that match your architecture. Supported options:

Local (all-MiniLM-L6-v2)

Parameter	Description	Data type	Supports DB	Default
Max Results	Maximum number of vectors returned from the similarity search.	Integer	❌	N/A
Min Score	Minimum similarity score (0.0 to 1.0) for a result to be considered relevant. Higher is more restrictive.	String	✅	0.7

OpenAI

Parameter	Description	Data type	Supports DB	Default
Embedding Account	The OpenAI account for embeddings. Supported types: Basic, Secret Key.	Select	❌	N/A
Embedding Model Name	Name of the embedding model, for example text-embedding-3-large.	String	✅	N/A
Vector Dimension	Number of dimensions in the embeddings. Must match your vector store’s config.	Integer	❌	N/A
Max Results	Maximum number of similar vectors to return.	Integer	❌	N/A
Min Score	Minimum similarity score for a result to be considered. More restrictive when higher.	String	✅	0.7

Hugging Face

Parameter	Description	Data type	Supports DB	Default
Embedding Account	Hugging Face account credentials. Supported: Basic, Google Key.	Select	❌	N/A
Embedding Model Name	Name of the embedding model (for example, sentence-transformers/all-mpnet-base-v2)	String	✅	N/A
Vector Dimension	Number of dimensions in the embedding vector. Must align with your store.	Integer	❌	N/A
Wait for Model	Whether the system should wait for the model to load (true) or return an error if it’s not ready (false).	Boolean	❌	true
Max Results	Maximum number of vectors returned.	Integer	❌	N/A
Min Score	Minimum similarity score for relevance.	String	✅	0.7

Vector Store

A vector store is a database optimized to store and retrieve embeddings. You can connect to:

PostgreSQL (PGVector)

Parameter	Description	Data type	Supports DB	Default
Host	Hostname or IP address of your PostgreSQL server.	String	✅	localhost
Port	Port number for the Postgres connection.	Number	❌	5432
Database Name	Name of the database containing the vector table.	String	✅	N/A
Vector Store Account	The Postgres account with credentials.	Select	❌	N/A
Table Name	Name of the table where embeddings are stored.	String	✅	embeddings

Neo4j

Parameter	Description	Data type	Supports DB	Default
Database Name	Name of the Neo4j database used for vector storage.	String	✅	N/A
Vector Store Account	Credentials for connecting to Neo4j.	Select	❌	N/A
Index Name	Index that holds the embedding vectors.	String	✅	N/A
URI	URI used to connect to the Neo4j instance.	String	✅	N/A
Node Label	Label for nodes storing embeddings.	String	✅	Document
Embedding Property	Node property that holds the embedding vector.	String	✅	embedding
Text Property	Node property that stores the original text or document.	String	✅	text

2

Add files (optional)

To include external documents (PDFs, images, among others) as context:

1. Upload them using a storage connector (for example, S3, Azure Blob, Digibee Storage)

2. Click the plus (+) button.

3. Enter the filename (for example, bankslip_1.pdf) or reference it with Double Braces.

The content will be injected into the prompt as additional context for the model.

3

Setup guardrails (optional)

Use guardrails when your inputs may contain sensitive data (like PII), or when you must strictly control what is sent to the LLM.

1. Click the gear icon (⚙) next to Guardrails to open the Guardrail Settings.

2. Check the validations you want, or choose Select All to enable all options.

Parameter	Description
Mask on detection	Masks detected PII before sending to the LLM. If disabled, the execution fails with an error.
CNPJ detection	Detects CNPJ (Cadastro Nacional da Pessoa Jurídica) patterns in the User Message, such as 00.000.000/0000-00. It doesn’t validate the numerical logic.
Credit Card detection	Detects credit card number patterns in the User Message, ranging from 13 to 19 digits. It doesn’t perform checksum (Luhn) validation.
IP detection	Detects IPv4 and IPv6 address patterns in the User Message. It doesn’t validate network or range correctness.
Datetime detection	Detects datetime patterns in the User Message, such as 2025-11-05, 05/11/2025, or Nov 5, 2025. It doesn’t validate date logic.
IBAN code detection	Detects IBAN (International Bank Account Number) patterns in the User Message, such as GB82WEST12345698765432. It doesn’t perform checksum validation.
CPF detection	Detects CPF (Cadastro de Pessoa Física) patterns in the User Message, such as 000.000.000-00. It doesn’t validate the numerical logic.
Email detection	Detects email addresses in the User Message, such as [email protected]. It doesn’t validate domain or address existence.
Crypto Wallet Address detection	Detects crypto wallet address patterns in the User Message, such as Bitcoin addresses starting with 1 and containing 26–35 base58 characters. It doesn’t validate the checksum or blockchain type.
Phone number detection	Detects phone number patterns in the User Message, such as (11) 99999-9999 or [phone]. It doesn’t validate carrier or region.
URL detection	Detects URL patterns in the User Message, such as http://example.com or https://www.example.org/path. It doesn’t verify link validity.

On the same page, you can also:

• Enable JSON Schema validation for responses. The output is validated against the schema you provide. If it’s invalid, the Agent sends a reprompt requesting the correct format. If the model still returns an invalid response, the execution ends with an error.

• Define custom regex patterns to validate the input. Provide both the Pattern Name and the Regex Pattern.

Testing your Agent

Use the Test Panel to validate your configuration before running the full pipeline.

1. Enter an Input (optional).

2. Click Play.

3. Review the request and response received.

Once everything looks good, click Save and Return.

Each successful test will consume tokens, and the number of tokens used is shown in the output. If you want to test the entire pipeline with a specific Agent Component response, you can mock this response during the pipeline run to avoid AI usage costs.

Configure general settings

These parameters influence how the component behaves within your pipeline, not how the LLM operates.

They can be accessed on the Settings tab.

Configure step

• Step Name: The name displayed in your pipeline.

• Alias: An alias you can use to reference this connector’s output later via Double Braces. Learn more.

Configure mock response

Create a mock response to test your pipeline without sending real requests to an LLM.

This is helpful when you want:

• Deterministic testing

• To avoid usage costs

Mocks substitute live model calls during pipeline execution.

Steps to create a mock:

1. Click Create mock response.

2. Provide a Name.

3. Enter the JSON of the mock response in the JSON Response field.

4. Activate Set as active to use this mock for tests.

5. Click Create mock response to save.

Setup error handling

Enable Fail On Error if you want the pipeline to stop on failure. Otherwise, the connector continues and returns { "success": false } inside the output.

Document the Agent Component’s usage

Use the Documentation tab to record:

• Use cases

• Business rules

• Required inputs

• Output examples

You can format all of this in Markdown.

FAQ

How can I test and experiment with my prompts?

Use the testing panel located on the right side of the connector’s configuration form. For detailed guidance, see the Testing your Agent topic.

Can I use data from the previous connectors?

Yes. You can use Double Braces expressions to reference data from previous connectors and include it in your prompt.

How is sensitive data handled?

The connector doesn’t redact or filter payload data. We recommend following the same data handling practices used with other connectors.

Can I chain multiple LLM calls in one pipeline?

Yes. You can use the output of one LLM call as input for another. For example, first classify a support ticket, then generate a response based on the classification.

What if the connector produces inaccurate or made-up results?

For critical tasks, reduce the risk of hallucinations by following these best practices:

• Configure parameters such as Temperature, Top K, Top P, Frequency Penalty, and Presence Penalty.

• Break processes into smaller steps, for example, generate first and verify afterward. This approach provides better control and allows you to validate results before using them.

• Create more effective prompts by applying prompt engineering techniques.

What happens if the provider takes too long to respond?

If the provider takes too long to respond, the request will time out and an error message will be shown in the Execution Panel.