Description
Agent Composer provides theAgenticResearchStep pattern for building agentic workflows that can dynamically select and execute tools. This separates research (tool use) from response generation for better control and observability.
AgenticResearchStep Pattern
The recommended pattern for research-focused agents:version: 0.1
inputs:
query: str
outputs:
response: str
nodes:
create_message_history:
type: CreateMessageHistoryStep
input_mapping:
query: __inputs__#query
research:
type: AgenticResearchStep
ui_stream_types:
retrievals: true
config:
tools_config:
- name: search_docs
description: |
Search the datastore containing user-uploaded documents.
step_config:
type: SearchUnstructuredDataStep
config:
top_k: 50
lexical_alpha: 0.1
semantic_alpha: 0.9
reranker: "ctxl-rerank-v2-instruct-multilingual-FP8"
rerank_top_k: 12
reranker_score_filter_threshold: 0.2
agent_config:
agent_loop:
num_turns: 10
parallel_tool_calls: false
model_name_or_path: "vertex_ai/claude-sonnet-4-5@20250929"
identity_guidelines_prompt: |
You are a retrieval-augmented assistant created by Contextual AI.
research_guidelines_prompt: |
You have access to the following tool:
- `search_docs` — Search the document datastore.
input_mapping:
message_history: create_message_history#message_history
generate:
type: GenerateFromResearchStep
ui_stream_types:
generation: true
config:
model_name_or_path: "vertex_ai/claude-sonnet-4-5@20250929"
identity_guidelines_prompt: |
You are a retrieval-augmented assistant created by Contextual AI.
response_guidelines_prompt: |
Write a concise, well-structured answer in Markdown.
input_mapping:
message_history: create_message_history#message_history
research: research#research
__outputs__:
type: output
input_mapping:
response: generate#response
Agent Loop Configuration
| Parameter | Description |
|---|---|
num_turns | Maximum number of tool-use iterations |
parallel_tool_calls | Whether the agent can call multiple tools simultaneously |
model_name_or_path | The LLM to use for reasoning and planning |
identity_guidelines_prompt | Defines who the agent is and its purpose |
research_guidelines_prompt | Instructions for tool use strategy |
Agent Loop Prompts
| Prompt | Used By | Description |
|---|---|---|
identity_guidelines_prompt | Both steps | Defines who the agent is |
research_guidelines_prompt | AgenticResearchStep | Instructions for tool selection |
response_guidelines_prompt | GenerateFromResearchStep | Output format instructions |
Example Prompts
identity_guidelines_prompt: |
You are an expert research assistant specializing in technical documentation.
You work for Acme Corp and help employees find information in internal docs.
research_guidelines_prompt: |
Use the search_docs tool to find relevant information.
- For factual questions, search once with precise terms
- For complex topics, search multiple times with different queries
- Stop searching when you have sufficient information
response_guidelines_prompt: |
Format your response as follows:
1. Start with a direct answer
2. Provide supporting details with citations
3. Use markdown formatting for readability
4. Include a "Sources" section at the end