- AI Development & Automation tags:
- Gemini
- AI
- Agent
- API keywords:
- agent development
- thinking level
- API implementation guide
Gemini 3 Agent Development Guide: Implementing thinking_level and Autonomous Execution¶
In November 2025, Google launched an "agent-first" design. The key feature is controlling reasoning depth with the thinking_level parameter.
Target Audience
- Intermediate developers interested in agent development with API
Key Points¶
- thinking_level parameter usage criteria
- thoughtSignature handling implementation
- OSS framework integration procedures
thinking_level Parameter Basics¶
The thinking_level parameter controls reasoning depth with two settings: low and high.
| Setting | Use Case | Characteristics |
|---|---|---|
| low | Simple instruction following | Minimal latency, cost reduction |
| high (default) | Deep planning | Maximizes reasoning depth |
thinking_level Implementation Example¶
import google.generativeai as genai
model = genai.GenerativeModel("gemini-3-pro")
response = model.generate_content(
"Solve this complex math problem step by step",
generation_config={"thinking_level": "high"}
)
By specifying thinking_level: "high", the model internally executes multi-layer reasoning for step-by-step problem solving.
thoughtSignature Handling¶
Capturing thoughtSignature is mandatory for Function Calling.
response = model.generate_content(
"Get weather and suggest plan",
tools=[weather_tool]
)
next_response = model.generate_content(
"Revise previous suggestion",
thought_signature=response.thought_signature
)
OSS Framework Integration¶
LangChain, LlamaIndex, and Pydantic AI are supported from day one.
LangChain Integration¶
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.agents import initialize_agent
llm = ChatGoogleGenerativeAI(model="gemini-3-pro")
agent = initialize_agent([search_tool], llm)
result = agent.run("Find Tokyo's population")
Issues and Solutions¶
| Symptom | Solution |
|---|---|
| Shallow reasoning | Explicitly set "high" |
| Calling disconnects | Pass thoughtSignature |
| Cost increase | Use low for simple tasks |
Summary¶
Understanding thinking_level and thoughtSignature handling enables efficient agent development. Leverage frameworks like LangChain to build autonomous execution systems.