Component Types =============== Components are the building blocks of an Agentic Flow. They are organised into categories in the sidebar. Each component exposes input and output handles that determine how data flows between them. .. image:: ../images/agentic-component-panel.png :alt: Agentic Flow component configuration panel :align: center :width: 100% | Saved ----- The **Saved** category lists components you have previously saved from the canvas for reuse across flows. Right-click any component on the canvas and select **Save** to add it here. Input / Output -------------- .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Input ` - The entry point for the flow. Receives the user's message or trigger payload and passes it downstream. * - :ref:`Output ` - The exit point of the flow. Returns the final result to the caller or connected channel. The Playground is only available when the flow contains at least one Input and one Output component. Prompts ------- .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Prompt ` - Constructs a prompt string from a template. Supports variable interpolation using ``{variable}`` syntax. The output is a formatted prompt message passed to an Agent component. Data ---- .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`API Request ` - Makes an HTTP request to an external URL and passes the response downstream. * - :ref:`File ` - Loads a file (uploaded or from a URL) and makes its content available to the flow. * - :ref:`MySQL ` - Executes a query against a MySQL database and returns the results. * - :ref:`PostgreSQL ` - Executes a query against a PostgreSQL database and returns the results. * - :ref:`Redshift ` - Executes a query against an Amazon Redshift data warehouse. * - :ref:`S3 Operations ` - Reads from or writes to an Amazon S3 bucket. * - :ref:`SQL Query ` - Executes a SQL query against a configured database connection. * - :ref:`URL ` - Fetches content from a URL and returns the raw response. * - :ref:`Webhook ` - Receives an inbound HTTP request and uses the payload as input to the flow. Processing ---------- .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Combine Data ` - Merges outputs from multiple upstream components into a single data object. * - :ref:`Data → DataFrame ` - Converts raw data into a tabular DataFrame structure for further processing. * - :ref:`Data Operations ` - Applies transformations to structured data (filter, map, merge, rename, remove keys, etc.). * - :ref:`DataFrame Operations ` - Applies operations on a DataFrame (sort, filter, sample, select columns). * - :ref:`Document Parser ` - Extracts text and structure from documents (PDF, DOCX, etc.) using configurable parsing strategies. * - :ref:`Ingest Approved Response ` - Captures the approved response from a Human In The Loop step and injects it back into the flow. * - :ref:`Lambda Filter ` *(Beta)* - Filters a list of items using a custom expression. * - :ref:`LLM Router ` - Routes the flow to one of several downstream paths based on the output of an LLM classification. * - :ref:`Message to Data ` *(Beta)* - Converts a conversation message object into a structured data record. * - :ref:`Parser ` - Parses structured text (JSON, XML, CSV) into a usable data object. * - :ref:`Regex Extractor ` - Extracts values from text using a regular expression pattern. * - :ref:`Split Text ` - Splits text or a DataFrame into chunks using configurable size and overlap settings. * - :ref:`Streaming Data to Message ` - Converts a streaming data response into a standard message format. Knowledge Base -------------- .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Knowledge Retrieval ` - Retrieves relevant chunks from a knowledge base using semantic search. Connects to knowledge bases configured in the Foundry. * - :ref:`OpenSearch ` - Queries an Amazon OpenSearch index directly with configurable search type, scoring threshold, and hybrid search support. Agents ------ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Agent ` - A general-purpose autonomous agent that uses an LLM with tools and knowledge bases to reason and act over multiple steps. * - :ref:`Intent Classification Agent ` *(Beta)* - Classifies the user's intent and returns a structured output with the classified category. * - :ref:`Human In The Loop ` *(Beta)* - Pauses the flow and sends an approval request to configured delivery targets. Resumes once approved or rejected. * - :ref:`Channel Agent ` *(Legacy)* - An agent wired to a communication channel. Handles inbound messages and routes outbound replies to configured delivery targets. Superseded by the **Channel Output** node — use Channel Output for all new channel integrations. See :doc:`/13_channels/index`. * - :ref:`Flow Agent ` - Calls another Agentic Flow as a sub-flow and returns its output into the current flow. * - :ref:`Voice Agent Call ` - Triggers a Voice Agent call and returns the call response. * - :ref:`Break Agent ` - Immediately terminates the current flow execution with an optional break reason and instruction. Logic ----- .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`If-Else ` - Branches the flow based on a boolean condition evaluated against an input value. * - :ref:`Condition ` *(Legacy)* - Evaluates a conditional expression and routes to one of multiple output paths based on the result. * - :ref:`Code Execution ` - Executes a Python snippet and returns the result. Use for custom logic that cannot be expressed with other components. * - :ref:`Guardrail ` - Applies a configured guardrail policy to data passing through this point. Blocks or flags content that violates the policy. * - :ref:`Loop ` - Iterates over a list of items and executes a downstream path for each item. * - :ref:`Run Flow ` *(Beta)* - Executes another flow by ID and returns its output. * - :ref:`Confidence Score Component ` - Evaluates a confidence score and branches on whether it exceeds a configured threshold. Others ------ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Notes ` - A non-executable annotation node. Add comments or labels to sections of the canvas. * - :ref:`Current Date ` - Outputs the current date and time, which can be injected into prompts or conditions. * - :ref:`Message History ` - Retrieves the conversation message history for use in prompts or as context for an agent. * - :ref:`Structured Output ` - Parses agent output into a structured schema (JSON object) according to a defined format. Integrations ------------ The Integrations category combines built-in tools, MCP tool components, and any custom tools configured in the workspace. The category is always visible; the components inside depend on what has been set up by a workspace administrator. .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - **Calculator** - Evaluates a mathematical expression and returns the result. * - **Python REPL** - Executes Python code in a sandboxed environment and returns the output. * - :ref:`MCP Client ` - Connects to an MCP (Model Context Protocol) server configured in the workspace and exposes its tools to an Agent component. * - :ref:`Public MCP Client ` - Connects to any publicly accessible MCP server by URL. * - **Custom Tools** - In-house and custom tools added by a workspace administrator. Each appears as a draggable component once configured. Bundles ------- Bundles are grouped sets of components from a specific vendor or framework. They appear as collapsible sections at the bottom of the sidebar. Agentic Patterns ~~~~~~~~~~~~~~~~ Advanced multi-agent orchestration components for structured collaboration and task decomposition. .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Agent Capability ` - Defines a capability that can be assigned to an agent within a multi-agent pattern. * - :ref:`Collaboration Orchestrator ` - Orchestrates multiple agents working in parallel or sequence to complete a shared goal. * - :ref:`Hierarchical Decomposer ` - Decomposes a goal into a hierarchical task tree and assigns sub-tasks to agents. * - :ref:`Task Decomposer ` - Breaks down a high-level task into smaller sub-tasks for downstream agents. * - :ref:`Task Orchestrator ` - Coordinates execution of a task graph produced by a decomposer. * - :ref:`Task Visualization ` - Renders a task graph for inspection and monitoring within the flow. Memories ~~~~~~~~ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`PostgreSQL Chat Memory ` - Stores and retrieves conversation history from a PostgreSQL database for persistent memory across sessions. Amazon / AWS ~~~~~~~~~~~~ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Amazon Bedrock Embeddings ` - Generates text embeddings using Amazon Bedrock embedding models. * - **Amazon Bedrock Model** - Calls an Amazon Bedrock language model and returns the response. * - :ref:`Amazon Intelligent Document Parser ` - Extracts structured data from documents using Amazon Bedrock Data Automation. * - :ref:`AWS AgentCore Code Interpreter ` - Executes code using the AWS AgentCore managed code interpreter service. * - :ref:`AWS AgentCore Memory ` - Stores and retrieves long-term memory using the AWS AgentCore Memory service. * - :ref:`AWS Nova Image Generation ` - Generates images using Amazon Nova via Amazon Bedrock. * - :ref:`AWS Stability Image Generation ` - Generates images using Stability AI models via Amazon Bedrock. * - :ref:`S3 Bucket Uploader ` - Uploads files to a specified Amazon S3 bucket. LangChain ~~~~~~~~~ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`CharacterTextSplitter ` - Splits text into chunks using a character-based splitter. * - :ref:`CSV Agent ` - A LangChain agent that can read and query CSV files using natural language. * - :ref:`SQL Agent ` - A LangChain agent that can query a SQL database using natural language. * - :ref:`SQLDatabase ` - Connects to a SQL database and exposes it as a data source for LangChain agents. * - :ref:`Tool Calling Agent ` - A LangChain agent that uses tool-calling capable language models to reason and act. * - :ref:`XML Agent ` *(Beta)* - A LangChain agent that processes XML-structured inputs and tool responses. MCP ~~~ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`MCP Client ` - Connects to an MCP (Model Context Protocol) server configured in the workspace and exposes its tools to an Agent component. * - :ref:`Public MCP Client ` - Connects to any publicly accessible MCP server by URL. Red Hat ~~~~~~~ .. list-table:: :widths: 20 80 :header-rows: 1 * - Component - Description * - :ref:`Red-Hat OpenAI Chat ` - Calls a Red Hat–hosted OpenAI-compatible chat endpoint and returns the response.