惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

GbyAI
GbyAI
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
IT之家
IT之家
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
N
News | PayPal Newsroom
Cloudbric
Cloudbric
Webroot Blog
Webroot Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
Simon Willison's Weblog
Simon Willison's Weblog
Spread Privacy
Spread Privacy
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
V
Vulnerabilities – Threatpost
Attack and Defense Labs
Attack and Defense Labs
C
Cyber Attacks, Cyber Crime and Cyber Security
Cisco Talos Blog
Cisco Talos Blog
C
Cybersecurity and Infrastructure Security Agency CISA
H
Hackread – Cybersecurity News, Data Breaches, AI and More
P
Proofpoint News Feed
阮一峰的网络日志
阮一峰的网络日志
S
Secure Thoughts
T
Tor Project blog
Latest news
Latest news
aimingoo的专栏
aimingoo的专栏
V2EX - 技术
V2EX - 技术
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
S
Securelist
T
Tenable Blog
N
Netflix TechBlog - Medium
Google Online Security Blog
Google Online Security Blog
博客园 - Franky
T
Troy Hunt's Blog
量子位
大猫的无限游戏
大猫的无限游戏
T
Threat Research - Cisco Blogs
T
The Exploit Database - CXSecurity.com
MongoDB | Blog
MongoDB | Blog
H
Heimdal Security Blog
D
Docker
W
WeLiveSecurity
Stack Overflow Blog
Stack Overflow Blog
G
Google Developers Blog
博客园 - 叶小钗
腾讯CDC
The Hacker News
The Hacker News
WordPress大学
WordPress大学
人人都是产品经理
人人都是产品经理
Project Zero
Project Zero
Martin Fowler
Martin Fowler

Developer tools

We're rolling out AlphaEvolve widely to solve Google Cloud customers' hardest problems. Expanding Managed Agents in Gemini API: background tasks, remote MCP and more The latest AI news we announced in June 2026 Ask an AI expert: What exactly is the full stack? Interactions API: our primary interface for Gemini models and agents DiffusionGemma: 4x faster text generation See what 3 builders are making with Gemma 4 Bringing the latest Gemini models to Apple developers Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency Kaggle is making AI benchmark creation effortless Introducing Gemma 4 12B: a unified, encoder-free multimodal model How we used Gemini to build Google I/O 2026 Take our I/O 2026 quiz, vibe coded in Google AI Studio. Here's what developers can do with the latest Google Play updates. Building the agentic future: Developer highlights from I/O 2026 I/O 2026 Introducing Managed Agents in the Gemini API Bring any idea to life: Google AI Studio at I/O 2026 Gemini API File Search is now multimodal: build efficient, verifiable RAG Accelerating Gemma 4: faster inference with multi-token prediction drafters The latest AI news we announced in April 2026 Reduce friction and latency for long-running jobs with Webhooks in Gemini API Join the new AI Agents Vibe Coding Course from Google and Kaggle Deep Research Max: a step change for autonomous research agents Start vibe coding in AI Studio with your Google AI subscription. Prepay for the Gemini API to get more control over your spend Introducing Learn Mode: your personal coding tutor in Google Colab Gemma 4: Byte for byte, the most capable open models New ways to balance cost and reliability in the Gemini API The latest AI news we announced in March 2026 Build with Veo 3.1 Lite, our most cost-effective video generation model
Improve coding agents’ performance with Gemini API Docs MCP and Agent Skills.
Trey Nguyen · 2026-04-01 · via Developer tools

Agents can generate outdated Gemini API code because their training data has a cutoff date. We built two complementary tools to fix this.

The Gemini API Docs MCP (https://gemini-api-docs-mcp.dev) connects your coding agent to the current Gemini API documentation, SDKs and model information via the Model Context Protocol. This ensures that your coding agent has access to the most up-to-date APIs and code and builds with the most optimal configuration settings.

The Gemini API Developer Skills adds best-practice instructions, resources-links and patterns to guide the agent toward current SDK patterns.

While each tool independently improves your workflow, using them together unlocks their full potential. Our evals show that combining MCP and Skills leads to a 96.3% pass rate on our eval set, with 63% fewer tokens per correct answer compared to vanilla prompting. Set up both at ai.google.dev/gemini-api/docs/coding-agents.