Agent
Build an agent
Configuration
System Prompt
Enter system prompt...
User Prompt
Enter context or user message...
Memories
Connect memory block output...
Available in Advanced mode.
Model*
Type or select a model...
Temperature
0.5
Shown when model is one of 'claude-opus-4-6', 'claude-sonnet-4-6', 'claude-opus-4-5', 'claude-sonnet-4-5', 'claude-haiku-4-5', 'azure-anthropic/claude-opus-4-6', 'azure-anthropic/claude-opus-4-5', 'azure-anthropic/claude-sonnet-4-5', 'azure-anthropic/claude-haiku-4-5', 'bedrock/anthropic.claude-opus-4-5-20251101-v1:0', 'bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0', 'bedrock/anthropic.claude-haiku-4-5-20251001-v1:0', 'bedrock/amazon.nova-2-lite-v1:0', 'bedrock/amazon.nova-pro-v1:0', 'bedrock/amazon.nova-lite-v1:0', 'bedrock/amazon.nova-micro-v1:0', 'bedrock/meta.llama4-maverick-17b-instruct-v1:0', 'bedrock/meta.llama4-scout-17b-instruct-v1:0', 'bedrock/meta.llama3-3-70b-instruct-v1:0', 'bedrock/meta.llama3-1-70b-instruct-v1:0', 'bedrock/meta.llama3-1-8b-instruct-v1:0', 'bedrock/mistral.mistral-large-3-675b-instruct', 'bedrock/mistral.pixtral-large-2502-v1:0', 'bedrock/mistral.magistral-small-2509', 'bedrock/mistral.ministral-3-14b-instruct', 'bedrock/mistral.ministral-3-8b-instruct', 'bedrock/mistral.ministral-3-3b-instruct', 'bedrock/mistral.mixtral-8x7b-instruct-v0:1'.
Temperature
1
Shown when model is one of 'fireworks/glm-5.2', 'fireworks/kimi-k3', 'gpt-4.1', 'gpt-4.1-mini', 'azure/gpt-5-chat', 'azure/gpt-4.1', 'azure/gpt-4.1-mini', 'azure/gpt-4.1-nano', 'gemini-3.6-flash', 'gemini-3.5-flash-lite', 'gemini-3.5-flash', 'gemini-3.1-pro-preview', 'gemini-3.1-flash-lite', 'gemini-3-flash-preview', 'gemini-2.5-pro', 'gemini-2.5-flash', 'gemini-2.5-flash-lite', 'vertex/gemini-3.5-flash', 'vertex/gemini-3.1-pro-preview', 'vertex/gemini-3.1-flash-lite', 'vertex/gemini-3-flash-preview', 'vertex/gemini-2.5-pro', 'vertex/gemini-2.5-flash', 'vertex/gemini-2.5-flash-lite', 'deepseek-v4-flash', 'deepseek-chat', 'grok-4.6', 'grok-4.5', 'grok-4.3', 'grok-4.20-0309-reasoning', 'grok-4.20-0309-non-reasoning', 'grok-4.20-multi-agent-0309', 'cerebras/gpt-oss-120b', 'cerebras/zai-glm-4.7', 'cerebras/gemma-4-31b', 'groq/openai/gpt-oss-120b', 'groq/openai/gpt-oss-20b', 'groq/openai/gpt-oss-safeguard-20b', 'groq/qwen/qwen3.6-27b', 'groq/llama-3.1-8b-instant', 'groq/llama-3.3-70b-versatile'.
Reasoning Effort
medium
Shown when model is one of 'gpt-5.6-sol', 'gpt-5.6-terra', 'gpt-5.6-luna', 'gpt-5.5-pro', 'gpt-5.5', 'gpt-5.4-pro', 'gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-nano', 'gpt-5.2-pro', 'gpt-5.2', 'gpt-5.1', 'gpt-5-pro', 'gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano', 'azure/o3', 'azure/o4-mini', 'deepseek-v4-pro', 'deepseek-v4-flash', 'deepseek-reasoner', 'grok-4.6', 'grok-4.5', 'grok-4.3', 'grok-4.20-multi-agent-0309', 'groq/openai/gpt-oss-120b', 'groq/openai/gpt-oss-20b', 'groq/openai/gpt-oss-safeguard-20b'.
Verbosity
medium
Shown when model is one of 'gpt-5.6-sol', 'gpt-5.6-terra', 'gpt-5.6-luna', 'gpt-5.5', 'gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-nano', 'gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano'.
API Key
••••••••
Shown when applicable to the selected model at runtime.
Azure OpenAI Endpoint
••••••••
Shown when model is one of 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano', 'azure/gpt-5-chat', 'azure/o3', 'azure/o4-mini', 'azure/gpt-4.1', 'azure/gpt-4.1-mini', 'azure/gpt-4.1-nano', 'azure/model-router'.
Azure API Version
2024-07-01-preview
Shown when model is one of 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano', 'azure/gpt-5-chat', 'azure/o3', 'azure/o4-mini', 'azure/gpt-4.1', 'azure/gpt-4.1-mini', 'azure/gpt-4.1-nano', 'azure/model-router'.
Tools
Tools
Skills
Skills
Response Format
json
Enter JSON schema...
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
systemPrompt | string | No | Initial system instructions |
userPrompt | string | No | User message or context |
memories | json | No | Agent memory data |
model | string | Yes | AI model to use |
apiKey | string | No | Provider API key. Shown when applicable to the selected model at runtime. |
azureEndpoint | string | No | Azure OpenAI endpoint URL. Shown when model is one of 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano', 'azure/gpt-5-chat', 'azure/o3', 'azure/o4-mini', 'azure/gpt-4.1', 'azure/gpt-4.1-mini', 'azure/gpt-4.1-nano', 'azure/model-router'. |
azureApiVersion | string | No | Azure API version. Shown when model is one of 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano', 'azure/gpt-5-chat', 'azure/o3', 'azure/o4-mini', 'azure/gpt-4.1', 'azure/gpt-4.1-mini', 'azure/gpt-4.1-nano', 'azure/model-router'. |
responseFormat | json | No | JSON response format schema |
temperature | number | No | Response randomness level |
reasoningEffort | string | No | Reasoning effort level for GPT-5 models. Shown when model is one of 'gpt-5.6-sol', 'gpt-5.6-terra', 'gpt-5.6-luna', 'gpt-5.5-pro', 'gpt-5.5', 'gpt-5.4-pro', 'gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-nano', 'gpt-5.2-pro', 'gpt-5.2', 'gpt-5.1', 'gpt-5-pro', 'gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano', 'azure/o3', 'azure/o4-mini', 'deepseek-v4-pro', 'deepseek-v4-flash', 'deepseek-reasoner', 'grok-4.6', 'grok-4.5', 'grok-4.3', 'grok-4.20-multi-agent-0309', 'groq/openai/gpt-oss-120b', 'groq/openai/gpt-oss-20b', 'groq/openai/gpt-oss-safeguard-20b'. |
verbosity | string | No | Verbosity level for GPT-5 models. Shown when model is one of 'gpt-5.6-sol', 'gpt-5.6-terra', 'gpt-5.6-luna', 'gpt-5.5', 'gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-nano', 'gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'azure/gpt-5.4', 'azure/gpt-5.4-mini', 'azure/gpt-5.4-nano', 'azure/gpt-5.2', 'azure/gpt-5.1', 'azure/gpt-5.1-codex', 'azure/gpt-5', 'azure/gpt-5-mini', 'azure/gpt-5-nano'. |
tools | json | No | Available tools configuration |
skills | json | No | Selected skills configuration |
Output
| Parameter | Type | Description |
|---|---|---|
content | string | Generated response content |
model | string | Model used for generation |
tokens | any | Token usage statistics |
toolCalls | any | Tool calls made |
toolResults | any | Tool results returned by the provider |
Usage Instructions
Send system and user prompts to the selected model, optionally with integration tools, custom tools, skills, and conversation history. Available models come from the deployment catalog and configured provider connections. To retain conversation history across runs, save user and assistant messages with Memory Add, then pass the message array from Get Memory into this block’s Memories field. Workflow variables alone do not persist conversation history. With a Response Format, valid JSON response fields become top-level outputs alongside response metadata; malformed JSON falls back to standard content with a warning. Without a Response Format, the block returns the standard outputs listed below.
Notes
- Category:
blocks - Type:
agent