Agentic RAG

How StateBase Powers Agentic RAG

StateBase serves as the Store and Trace layer for this loop.

The Loop

Reasoning: Agent thinks “I need to check the pricing page.”

Tool Call: Agent calls search_tool("pricing").

State Update: StateBase records the tool call and the raw result.

Reflection: Agent analyzes result. “This is outdated 2024 pricing.”

Refinement: Agent calls search_tool("pricing 2025").

Implementation

# 1. Decision Step
state = sb.sessions.get_state(session_id)
action = agent.decide(state)

if action == "search":
    # 2. Tool Execution
    result = search_tool.run(query)
    
    # 3. State Preservation
    sb.sessions.add_turn(
        input={"type": "tool_result", "content": result},
        output={"type": "thought", "content": "Analyzing pricing data..."}
    )

By storing the intermediate thought process (Reasoning traces) in StateBase, your agent can “learn” from failed retrieval attempts in future sessions.

Getting Started

Core Concepts

Live Demos

API Reference

Agent Patterns

Integrations

SDKs

Production Playbook

Security & Compliance

Templates & Examples

How StateBase Powers Agentic RAG

The Loop

Implementation

​How StateBase Powers Agentic RAG

​The Loop

​Implementation

How StateBase Powers Agentic RAG

The Loop

Implementation