Agent Node

What is an Agent Node?

The Agent Node is the core building block of Splox workflows. It’s an autonomous AI system that combines an LLM with tools, conversation memory, and iteration logic to complete tasks. Unlike a simple LLM call, an Agent Node can:

Reason and plan using large language models
Execute actions through autonomous tool calling
Iterate in a loop — calling tools, processing results, and deciding next steps
Maintain conversation context across multiple turns with built-in memory
Stream responses in real-time via SSE
Collaborate with other agents using configurable execution modes
Handle voice/realtime interactions with supported providers

Autonomous Execution

The agent decides which tools to use and when to stop based on the task

Tool Integration

Connect tools via tool edges for the agent to use autonomously

Built-in Memory

Conversation context is managed automatically — no separate memory node needed

Configurable Limits

Set max iterations and timeouts to control behavior

Real-time Streaming

Token-by-token output streaming with session-based chat support

Multi-Agent

Connect agents together with sync, async, fire-forget, or handoff modes

How It Works

The Agent node runs an autonomous loop that alternates between LLM reasoning and tool execution:

Receive Input

The Agent receives input from its parent node (Start payload, previous node output, or variable mappings). If context memory is configured, the input is appended as a user message.

LLM Completion

The configured LLM processes the full conversation context — system prompt, memory history, and current input — and produces either a text response or tool call requests.

Tool Execution

If the LLM requests tool calls, the Agent executes them via connected Tool nodes (through tool edges). Results are appended to the conversation context as tool result messages.

Iteration

The Agent loops back to the LLM with tool results. The loop continues until:

The LLM responds without tool calls (task complete)
The max iterations limit is reached

Output

The Agent’s final response is emitted as its output, flowing to downstream nodes via parallel edges.

Configuration

LLM Settings

Provider & Model

Select the LLM provider and model for text generation.

Field	Description	Default
Text LLM Provider	Provider slug (`anthropic`, `openai`, `gemini`, `openrouter`, etc.)	`anthropic`
Text LLM Model	Model identifier (e.g., `claude-sonnet-4-5-20250929`)	`claude-sonnet-4-5-20250929`
Credential	Optional custom API key credential	Account default

You can also configure a Voice LLM for realtime audio interactions (supported by OpenAI and Gemini).

System Prompt

The system prompt instructs the agent on its role, behavior, and constraints. It supports Jinja2 templates for dynamic content.

You are a helpful research assistant. 
The user's name is {{ start.user_name }}.
Today's date is {{ start.date }}.

Use variable mappings to reference data from other nodes in your system prompt.

Advanced LLM Config

Additional configuration passed to the LLM:

Field	Description	Default
Thinking Tokens	Enable extended thinking with token budget	`4096`
Modalities	Output types (`text`, `image`)	`["text", "image"]`
Cache Control	Prompt caching duration	`5m`
Max Completion Tokens	Maximum output token length	`48000`
Enable 1M Context	Allow extended context window	`true`

Tool Calling

Tool Choice

Controls how the LLM selects tools:

Value	Behavior
`auto`	LLM decides whether to use tools (default)
`required`	LLM must call at least one tool per turn
`none`	Tool calling is disabled
`<tool_name>`	Force a specific tool to be called

On Tool Error

What happens when a tool call fails:

Value	Behavior
`continue`	Report the error to the LLM and let it decide what to do (default)
`fail`	Stop the agent entirely and mark it as failed

Tool Approval

Enable human-in-the-loop approval for sensitive tool calls. When enabled, the agent pauses and waits for user approval before executing specific tools.Default timeout: 5 minutes.

Skills

Attach reusable skill sets to the agent. Skills provide additional tools and capabilities that can be shared across multiple agents.

Iteration Control

Field	Description	Default	Range
Max Iterations	Maximum number of LLM → Tool → LLM cycles	`50`	1–50
Timeout	Maximum execution time in minutes	525,600 (1 year)	—
Max Retries	Retries on transient failures	`3`	0–10

Setting max iterations too high can lead to excessive credit usage. Start with a lower value and increase as needed.

Context Memory

The Agent has built-in conversation memory that persists across executions. This replaces the need for separate memory nodes.

Memory ID

The Context Memory ID links conversations across executions. Typically set to {{ start.chat_id }} so the same chat session maintains continuity.Different memory IDs create separate conversation threads.

User Message Content

Template for the user message appended each turn. Default: {{ start.text }}This determines what the agent sees as the “user’s message” each time the workflow runs.

Limits & Trimming

Control memory size to prevent context overflow:

Field	Options	Default
Limit Type	`tokens` or `messages`	`tokens`
Max Tokens	Token limit for conversation history	`70,000`
Min Messages to Keep	Minimum messages preserved during trimming	`70`
Trim Strategy	`drop_oldest` or `drop_middle`	`drop_oldest`
Empty Tool Results	Replace tool result content with empty strings to save tokens	`false`

Summarization

When enabled, old messages are summarized before being dropped, preserving key context.

Field	Description	Default
Enable Summarization	Automatically summarize before trimming	`true`
Summarize Prompt	Custom prompt for the summarization LLM call	Default summary prompt

Custom Messages

Inject predefined messages into the conversation context. Useful for few-shot examples or persistent instructions.Enable Use Predefined Messages and add messages with specific roles (user, assistant, system).

Streaming

Field	Description	Default
Enable Streaming	Stream tokens in real-time via SSE	`true`
Chat Streaming Mode	`session` for persistent chat connections	`session`

Voice & Realtime

Voice agents are supported with OpenAI and Gemini providers.

Field	Description	Default
Realtime Enabled	Enable voice/audio interactions	`false`
Voice LLM Provider	Provider for voice model	`gemini`
Voice LLM Model	Voice-capable model	`gemini-2.5-flash-native-audio-preview-12-2025`

Agent-to-Agent Communication

When connecting Agent nodes together, the edge between them can be configured with an execution mode that controls how the child agent runs relative to the parent:

Mode	Parent Behavior	Child Result	Best For
`sync`	Blocks until child completes	Returned directly	Sequential delegation
`async_inject`	Continues immediately	Auto-injected when ready	Background processing
`async_bidir`	Continues immediately	Child has `reply_to_parent` tool	Ongoing collaboration
`fire_forget`	Continues immediately	Not received	Logging, notifications
`handoff`	Exits completely	Child takes over	Agent routing, escalation

Configuration

When connecting agents, you can customize how they appear to each other:

Field	Description
Child Tool Name	How the child agent appears as a tool to the parent
Child Tool Description	Description of what the child agent does
Reply Tool Name	For `async_bidir`: name of the reply-to-parent tool
Reply Tool Description	For `async_bidir`: description of the reply tool

Handles

Handle	Position	Type	Description
Input	Left	Execution	Receives data from parent nodes
PARALLEL	Right	Execution	Sends output to next nodes on success
ERROR	Right	Error	Routes to fallback nodes on failure
TOOLS	Right	Tool	Connects to Tool nodes for autonomous tool calling

Output

The Agent node produces an AgentResponse with:

Field	Description
text	The agent’s final text response
tool_calls	List of tool calls made during execution
reasoning	The agent’s reasoning/thinking output (if thinking tokens enabled)
iterations	Number of LLM → Tool cycles performed
input_tokens	Total input tokens consumed
output_tokens	Total output tokens generated

Access these in downstream nodes via variable mappings: {{ agent_node_name.text }}, {{ agent_node_name.iterations }}, etc.

What’s Next?

Tool Node

Learn about tools that agents can use

Variable Mappings

Reference data between nodes with Pongo2 templates

Tool Edges

How to connect agents to tools

Node Lifecycle

Understand execution states and transitions

Getting Started

Core Concepts

Nodes

Edges

What is an Agent Node?

Autonomous Execution

Tool Integration

Built-in Memory

Configurable Limits

Real-time Streaming

Multi-Agent

How It Works

Configuration

LLM Settings

Tool Calling

Iteration Control

Context Memory

Streaming

Voice & Realtime

Agent-to-Agent Communication

Configuration

Handles

Output

What’s Next?

Tool Node

Variable Mappings

Tool Edges

Node Lifecycle

Getting Started

Core Concepts

Nodes

Edges

​What is an Agent Node?

Autonomous Execution

Tool Integration

Built-in Memory

Configurable Limits

Real-time Streaming

Multi-Agent

​How It Works

​Configuration

​LLM Settings

​Tool Calling

​Iteration Control

​Context Memory

​Streaming

​Voice & Realtime

​Agent-to-Agent Communication

​Configuration

​Handles

​Output

​What’s Next?

Tool Node

Variable Mappings

Tool Edges

Node Lifecycle

What is an Agent Node?

How It Works

Configuration

LLM Settings

Tool Calling

Iteration Control

Context Memory

Streaming

Voice & Realtime

Agent-to-Agent Communication

Configuration

Handles

Output

What’s Next?