Blocks
Research Agent
Comprehensive research and analysis agent
Create a research agent that can conduct thorough investigations, analyze data, synthesize findings, and provide evidence-based insights with proper citations and methodology.
Block Preview
Research Agent
Comprehensive research and analysis 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 research_agent block with monitoring enabled in production.
Inputs (UI)
System Prompt
long-inputPlaceholder: You are a thorough research analyst...
Layout: full
Research Query
long-inputPlaceholder: Enter the research question or topic to investigate...
Layout: full
Research Scope
dropdownLayout: half
Options: Broad Overview, Focused Analysis, Deep Dive, Comparative Study
Timeframe
dropdownLayout: half
Options: Current (Last 6 months), Recent (Last 2 years), Historical (5+ years), All Time
Model
dropdownLayout: half
Options: Dynamic options
Temperature
sliderLayout: half
API Key
short-inputPlaceholder: 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"]
Data Sources
long-inputPlaceholder: Enter available data sources, databases, documents to analyze...
Layout: full
Research Criteria
codePlaceholder: { "credibilityThreshold": 0.8, "sourceTypes": ["academic", "industry", "government", "news"], "excludeKeywords": ["opinion", "speculation"], "requiredKeywords": ["data", "study", "research"], "maxSources": 20 }
Layout: full
Output Format
dropdownLayout: half
Options: Executive Summary, Detailed Report, Key Findings, Research Brief
Include Citations
switchLayout: half
Tools
tool-inputLayout: full
Response Format
codePlaceholder: { "type": "object", "properties": { "findings": { "type": "array", "items": { "type": "object", "properties": { "topic": {"type": "string"}, "summary": {"type": "string"}, "sources": {"type": "array", "items": {"type": "string"}}, "confidence": {"type": "number"} } } }, "methodology": {"type": "string"}, "limitations": {"type": "array", "items": {"type": "string"}}, "recommendations": {"type": "array", "items": {"type": "string"}}, "citations": {"type": "array", "items": {"type": "string"}} } }
Layout: full
Knowledge Sources
knowledge-source-inputLayout: full
Max Search Results
sliderLayout: half
Condition: knowledgeSources = ""
Similarity Threshold
sliderLayout: half
Condition: knowledgeSources = ""
Enable Memory
switchLayout: half
Memory Limit
sliderLayout: half
Condition: memoryEnabled = true
Importance Threshold
sliderLayout: half
Condition: memoryEnabled = true
Memory Tags
short-inputPlaceholder: customer-support, billing, technical
Layout: half
Condition: memoryEnabled = true
Inputs (API)
systemPrompt
stringOptional
researchQuery
stringRequired
researchScope
stringOptional
timeframe
stringOptional
model
stringRequired
apiKey
stringRequired
temperature
numberOptional
dataSources
stringOptional
researchCriteria
jsonOptional
outputFormat
stringOptional
includeCitations
booleanOptional
tools
jsonOptional
responseFormat
jsonOptional
knowledgeSources
stringOptional
searchMaxResults
numberOptional
similarityThreshold
numberOptional
memoryEnabled
booleanOptional
memoryLimit
numberOptional
memoryImportance
numberOptional
memoryTags
stringOptional
Outputs
Primary response type:
{
"content": "string",
"model": "string",
"findings": "json",
"methodology": "string",
"limitations": "json",
"recommendations": "json",
"citations": "json",
"tokens": "json"
}Conditional output based on: responseFormat
When empty: {"content":"string","model":"string","findings":"json","methodology":"string","limitations":"json","recommendations":"json","citations":"json","tokens":"json"} | When filled: "json"