Docs Navigation

Blocks

Reasoning Agent

Step-by-step reasoning agent

Create an agent that uses structured reasoning techniques like Chain-of-Thought, ReAct, or Tree of Thoughts to solve complex problems step by step.

Back to Catalog

Agentsreasoning_agent

Block Preview

Reasoning Agent

Step-by-step reasoning agent

Usage

Add the block to your workflow and connect it to the upstream step.
Configure any required credentials or tokens in the inputs.
Fill in required inputs and optional parameters for the run.
Run a test execution, inspect outputs, and iterate before deploying.
Deploy the reasoning_agent block with monitoring enabled in production.

Inputs (UI)

Problem

long-input

Placeholder: Enter the problem or question for the agent to solve...

Layout: full

Reasoning Framework

dropdown

Layout: half

Options: Chain of Thought, ReAct, Tree of Thoughts, Socratic Method

Model

dropdown

Layout: half

Options: Dynamic options

Temperature

slider

Layout: half

Condition: model = ["gpt-4o","gpt-4o-mini","gpt-4-turbo","gpt-4","gpt-3.5-turbo","o3-mini","gpt-5-mini","gpt-5","o1-mini","o1-preview","gemini-2.5-pro-preview-05-06","gemini-2.5-flash-preview-05-20","gemini-2.0-flash","gemini-2.0-flash-lite","deepseek-chat","deepseek-reasoner","llama-4-scout-17b-16e-instruct","llama-4-maverick-17b-128e-instruct","llama-3.3-70b-versatile","qwen-qwq-32b","deepseek-r1-distill-llama-70b"]

Temperature

slider

Layout: half

Condition: model = ["claude-opus-4-5-20251022","claude-sonnet-4-20250514","claude-opus-4-20250514","claude-haiku-4-5-20251001","claude-3-7-sonnet-20250219","grok-3-latest","grok-3-fast-latest"]

API Key

short-input

Placeholder: Enter your API key

Layout: full

Condition: model = ["qwen2.5:0.5b","qwen2.5:1.5b","qwen2.5:3b","llama3.2:1b","llama3.2:3b","phi3.5:3.8b"]

Max Steps

short-input

Placeholder: 10

Layout: half

Verify Steps

switch

Layout: half

Tools

tool-input

Layout: full

Condition: reasoningFramework = "react"

Domain Knowledge

long-input

Placeholder: Enter any domain-specific knowledge or context...

Layout: full

Output Format

dropdown

Layout: half

Options: Full Reasoning, Answer Only, Summary with Key Steps

Knowledge Sources

knowledge-source-input

Layout: full

Max Search Results

slider

Layout: half

Condition: knowledgeSources = ""

Similarity Threshold

slider

Layout: half

Condition: knowledgeSources = ""

Enable Memory

switch

Layout: half

Memory Limit

slider

Layout: half

Condition: memoryEnabled = true

Importance Threshold

slider

Layout: half

Condition: memoryEnabled = true

Memory Tags

short-input

Placeholder: customer-support, billing, technical

Layout: half

Condition: memoryEnabled = true

Inputs (API)

problem

string

Required

reasoningFramework

string

Required

model

string

Required

apiKey

string

Required

maxSteps

number

Optional

verifySteps

boolean

Optional

tools

json

Optional

domainKnowledge

string

Optional

outputFormat

string

Optional

temperature

number

Optional

knowledgeSources

string

Optional

searchMaxResults

number

Optional

similarityThreshold

number

Optional

memoryEnabled

boolean

Optional

memoryLimit

number

Optional

memoryImportance

number

Optional

memoryTags

string

Optional

Outputs

Primary response type:

{
  "answer": "string",
  "reasoning": "json",
  "model": "string",
  "tokens": "json"
}

Tool Access

openai_chatanthropic_chatgoogle_chatxai_chatdeepseek_chat