How to build an automated coding assistant with Gemini 3.5 Flash API: a complete 30-minute tutorial

Tutorial Objectives

In 30 minutes, use Gemini 3.5 Flash API to build an automated coding assistant to achieve a three-in-one workflow of code generation, review and refactoring. This article is a complete step-by-step tutorial.

What will you build?

• Coding Assistant Core: Code generation and review system based on Gemini 3.5 Flash
• Automated pipeline: end-to-end workflow from requirement description to code output
• Quality Monitoring: Automatic code review and refactoring suggestions

Preparation list

• Google AI Studio or Gemini API account (free quota available) -Basic Python and terminal operation knowledge
• An API key (get it in 5 minutes)

Overall architecture

The teaching process is broken down into 4 modules and can be advanced in order. When it's all done, you'll have an AI coding assistant that you can actually use.

Step 1: Get Gemini 3.5 Flash API Key

Gemini 3.5 Flash was just announced today via Google I/O 2026 and is available directly through Google AI Studio. Visit Google AI Studio and log in with your Google account:

1. Click "Get API Key" in the upper right corner
2. Create or select a project in the Google Cloud Console
3. Enable Gemini API and generate API key
4. Copy the key and save it to a safe location

#
export GEMINI_API_KEY="_API_"

****Gemini 3.5 Flash $1.50/ token $9.00/ token， 2.5 Flash 3 ，。，。

2 Python SDK

Gemini google-genai Python SDK，

# Gemini Python SDK
pip install google-genai

#
python3 -c "import google.genai; print('SDK ready')"

API

from google import genai

client = genai.Client(api_key="_API_")
response = client.models.generate_content(
    model="gemini-3.5-flash",
 contents=" Python "
)
print(response.text[:200])

， API 。

3

SDK ，。、

from google import genai
import os

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

def coding_assistant(task_type, input_text):
 """generate / review / refactor"""
    prompts = {
 "generate": f"，

{input_text}",
 "review": f"，、

{input_text} __T OK13__ {input_text}

    }

    response = client.models.generate_content(
        model="gemini-3.5-flash",
        contents=prompts.get(task_type, input_text),
        config={
 "temperature": 0.3, #
            "max_output_tokens": 4096
        }
    )
    return response.text

# Web
result = coding_assistant("generate", " Python Flask REST API， CRUD ")
print(result[:500])

****Gemini 3.5 Flash ——Google 「 agentic coding 」。 Anthropic Claude。

4

——，

import json
from google import genai

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

class CodingPipeline:
    def __init__(self):
        self.history = []

    def generate_code(self, requirement):
        step1 = client.models.generate_content(
            model="gemini-3.5-flash",
 contents=f"，

{requirement}"
        )
        design = step1.text
        self.history.append({"step": "design", "output": design[:200]})

        step2 = client.models.generate_content(
            model="gemini-3.5-flash",
 contents=f"，

{design}"
        )
        code = step2.text
        self.history.append({"step": "code", "output": code[:200]})

        step3 = client.models.generate_content(
            model="gemini-3.5-flash",
 contents=f"

{code}"
        )
        review = step3.text
        self.history.append({"step": "review", "output": review[:200]})

        return {"design": design, "code": code, "review": review}

#
pipeline = CodingPipeline()
result = pipeline.generate_code(" Todo ，、、")
print(json.dumps(result, indent=2))

n8n

n8n， AI GitHub Issue、Slack 。 n8n Cloud ，。

AI Claude Code + n8n AI ，He Built an AI Automation Stack with Claude + n8n — $4K to $12K/mo in 6 Months。 A real case of a data analyst using Claude Code + n8n to build an automated report SaaS with a monthly income of $3,800。

（FAQ）

Q1API 429 Too Many Requests？

Gemini API ， time.sleep() ，。

Q2？

max_output_tokens ，Gemini 3.5 Flash ， 4096 。

Q3Gemini 3.5 Flash Claude Code ？

Gemini 3.5 Flash （）（$9/M vs Claude $15/M）。， OpenRouter ，。

SEO+GEOFAQ GEO ，

（）

， tools hover-cardGemini、Gemini API、Google AI Studio、Python、n8n、Claude Code、OpenRouter、Google Cloud

Reference video/material

• Google Blog: Gemini 3.5
• Google AI Dev: Gemini 3.5 Flash API
• HN : Gemini 3.5 Flash (588 points)

Internal link guidance

• Successful case: He used Claude + n8n to build an AI automation system, He Built an AI Automation Stack with Claude + n8n — $4K to $12K/mo in 6 Months
• Recommended tool: Unified management of multi-model API calls through OpenRouter