# Advent of Agents — Google Cloud (LLM & Agent Markdown Index)

> Production-ready AI Agent tutorials, 5-minute daily katas, ADK patterns, A2A mesh, A2UI, and Cloud Run deployments.
> **Tip for AI Agents & Crawlers**: Request any route with `Accept: text/markdown` or `curl` User-Agent, or append `.md` to any URL (e.g. `/2026/10/01.md`).
> **WebMCP Discovery**: `/.well-known/mcp.json` and `navigator.modelContext`.

## Season 3 — October 2026 (Autumn / Halloween Edition) (`/2026/10/`)


## Season 2 — March 2026 (Spring Cherry Blossom Edition) (`/2026/03/`)

- **Day 01: [Season 2 Kick Off](https://adventofagents.com/2026/03/01?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day01)** ([.md](https://adventofagents.com/2026/03/01.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day01)) — 31 days. Zero to Production-Ready AI Agents on Google Cloud.
- **Day 02: [Build ADK Agents with Gemini 3.1 Pro](https://adventofagents.com/2026/03/02?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day02)** ([.md](https://adventofagents.com/2026/03/02.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day02)) — Choose your language. One command. Total language flexibility. Bootstrap high-performance agents in seconds.
- **Day 03: [Build AI Agents with Gemini 3.1 Flash-Lite](https://adventofagents.com/2026/03/03?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day03)** ([.md](https://adventofagents.com/2026/03/03.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day03)) — Announcing Gemini 3.1 Flash-Lite: our most cost-efficient model for building high-quality AI agents at scale.
- **Day 04: [MCP Servers: Add external tools to your agents in just a few lines](https://adventofagents.com/2026/03/04?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day04)** ([.md](https://adventofagents.com/2026/03/04.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day04)) — Wire up multiple MCP servers simultaneously to trace bugs from Linear to GitHub PRs.
- **Day 05: [Long Term Recall: Memory Plugins](https://adventofagents.com/2026/03/05?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day05)** ([.md](https://adventofagents.com/2026/03/05.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day05)) — Implement persistent semantic memory for AI agents using the GoodmemPlugin.
- **Day 06: [ADK Skills](https://adventofagents.com/2026/03/06?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day06)** ([.md](https://adventofagents.com/2026/03/06.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day06)) — Eliminate wasted tokens with progressive disclosure. Use ADK Skills to load complex instructions only when needed.
- **Day 07: [ADK Agent Skill Design Patterns](https://adventofagents.com/2026/03/07?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day07)** ([.md](https://adventofagents.com/2026/03/07.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day07)) — Five design patterns for structuring SKILL.md content in ADK — Tool Wrapper, Generator, Reviewer, Inversion, and Pipeline.
- **Day 08: [Multi-Agent Patterns: Sequential Agents](https://adventofagents.com/2026/03/08?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day08)** ([.md](https://adventofagents.com/2026/03/08.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day08)) — Build predictable sequential workflows where the output of one agent goes straight to the next.
- **Day 09: [Multi-Agent Patterns: Coordinator/Dispatcher Agents](https://adventofagents.com/2026/03/09?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day09)** ([.md](https://adventofagents.com/2026/03/09.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day09)) — Build high-fidelity educational video agents that maintain character and scene consistency using the Google ADK, Gemini 3.1 Pro, Nano Banana and Veo 3.1.
- **Day 10: [Multi-Agent Patterns: Parallel Fanout and State Interpolation](https://adventofagents.com/2026/03/10?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day10)** ([.md](https://adventofagents.com/2026/03/10.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day10)) — Drastically reduce latency by running independent, grounded LLM tasks concurrently and automatically synthesizing their outputs.
- **Day 11: [Multi-Agent Patterns: Hierarchical Decomposition](https://adventofagents.com/2026/03/11?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day11)** ([.md](https://adventofagents.com/2026/03/11.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day11)) — Use a top-level Manager agent that utilizes an AgentTool to dynamically generate a plan before executing it.
- **Day 12: [Multi-Agent Patterns: Generator-Critic Agent Loop](https://adventofagents.com/2026/03/12?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day12)** ([.md](https://adventofagents.com/2026/03/12.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day12)) — Automatically refine LLM outputs using ADK's LoopAgent to orchestrate a conversation between a creative Writer and a strict Critic.
- **Day 13: [Multi-Agent Patterns: Iterative Refinement](https://adventofagents.com/2026/03/13?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day13)** ([.md](https://adventofagents.com/2026/03/13.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day13)) — Compose Skills, MCP, and Code Execution into a meta-agent that builds, tests, and refines other ADK agents through iterative loops.
- **Day 14: [Multi-Agent Patterns: Human in the Loop](https://adventofagents.com/2026/03/14?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day14)** ([.md](https://adventofagents.com/2026/03/14.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day14)) — Inject an approval breakpoint to pause agent execution and wait for manual user confirmation before executing sensitive financial APIs.
- **Day 15: [Grounding with ADK: Agentic RAG with Vector Search 2.0](https://adventofagents.com/2026/03/15?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day15)** ([.md](https://adventofagents.com/2026/03/15.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day15)) — Build an Agentic RAG system in 3 minutes with Vector Search 2.0 and ADK.
- **Day 16: [ADK Dev Skills: Accelerated Multiagent Triage](https://adventofagents.com/2026/03/16?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day16)** ([.md](https://adventofagents.com/2026/03/16.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day16)) — Accelerate multiagent system development from scaffolding to deployment using ADK Dev Skills.
- **Day 17: [Workspace & Gemini Enterprise: no-code agents](https://adventofagents.com/2026/03/17?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day17)** ([.md](https://adventofagents.com/2026/03/17.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day17)) — Connect and use Google Workspace connectors in personal Gemini Enterprise agents.
- **Day 18: [Workspace & Gemini Enterprise: ADK agents](https://adventofagents.com/2026/03/18?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day18)** ([.md](https://adventofagents.com/2026/03/18.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day18)) — Build ADK agents that use the Vertex AI Search MCP server and Google Workspace APIs, deploy them to Vertex AI, and register them with Gemini Enterprise.
- **Day 19: [Live Shopping Agent: Build with ADK and Gemini Embedding 2](https://adventofagents.com/2026/03/19?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day19)** ([.md](https://adventofagents.com/2026/03/19.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day19)) — Build a live multimodal shopping app with ADK and Gemini Embedding 2.
- **Day 20: [ADK Agent Harness: Build a Generate-Validate-Refine Pipeline](https://adventofagents.com/2026/03/20?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day20)** ([.md](https://adventofagents.com/2026/03/20.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day20)) — Build a README improvement harness that fetches a GitHub repo via MCP, generates against a quality checklist, and refines in a loop until a critic approves.
- **Day 21: [Developer's Guide to AI Agent Protocols](https://adventofagents.com/2026/03/21?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day21)** ([.md](https://adventofagents.com/2026/03/21.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day21)) — Six protocols, disambiguated. See how MCP, A2A, UCP, AP2, A2UI, and AG-UI work together to build a production-ready supply chain agent with ADK.
- **Day 22: [ADK Evaluation: Trajectory Tests and Rubric-Based Scoring](https://adventofagents.com/2026/03/22?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day22)** ([.md](https://adventofagents.com/2026/03/22.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day22)) — Define deterministic trajectory tests and rubric-based evaluations that run on every code push, catching agent regressions before they reach production.
- **Day 23: [Model Armor: AI Security Firewall for Agents](https://adventofagents.com/2026/03/23?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day23)** ([.md](https://adventofagents.com/2026/03/23.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day23)) — Protect AI agents from prompt injection, jailbreaks, and data leakage using Google Cloud Model Armor as a defense-in-depth security layer.
- **Day 24: [Batch Processing: Scale to 10k with ADK](https://adventofagents.com/2026/03/24?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day24)** ([.md](https://adventofagents.com/2026/03/24.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day24)) — Shift from interactive processing to an Agent as Orchestrator pattern using the ADK and Gemini Batch API for efficient, large-scale asynchronous workloads.
- **Day 25: [Agent Deployment: How to Deploy AI Agents](https://adventofagents.com/2026/03/25?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day25)** ([.md](https://adventofagents.com/2026/03/25.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day25)) — Deploy your AI agents to Vertex AI Agent Engine or Google Cloud Run securely and easily.
- **Day 26: [Authentication: End-User Identity Propagation](https://adventofagents.com/2026/03/26?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day26)** ([.md](https://adventofagents.com/2026/03/26.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day26)) — Securely delegate permissions by prompting end-users for OAuth consent during agent execution.
- **Day 27: [Scion: an open testbed for agent orchestration](https://adventofagents.com/2026/03/27?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day27)** ([.md](https://adventofagents.com/2026/03/27.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day27)) — Explore multi-agent patterns with an agnostic supra-harness system that isolates agents in git worktrees and containers, allowing easy orchestration and communication
- **Day 28: [A2A Protocol: Decoupling Reasoning from Execution](https://adventofagents.com/2026/03/28?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day28)** ([.md](https://adventofagents.com/2026/03/28.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day28)) — Decouple your reasoning engine from execution using the universal A2A 1.0 protocol to bridge a Python LangGraph orchestrator and a Go ADK service.
- **Day 29: [ApiRegistry: Dynamically Fetching BigQuery Tools](https://adventofagents.com/2026/03/29?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day29)** ([.md](https://adventofagents.com/2026/03/29.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day29)) — Learn how to use the ApiRegistry object to dynamically fetch an admin-approved, fully configured BigQuery tool directly from the Cloud API Registry at runtime.
- **Day 30: [Observability: Debug with Hierarchical Tracing](https://adventofagents.com/2026/03/30?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day30)** ([.md](https://adventofagents.com/2026/03/30.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day30)) — Eliminate silent failures in AI agents by implementing Hierarchical Trace Observability with OpenTelemetry and Arize Phoenix.
- **Day 31: [A2UI & A2A: Building the Dog Weather App](https://adventofagents.com/2026/03/31?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day31)** ([.md](https://adventofagents.com/2026/03/31.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s2_2026&utm_content=day31)) — Transform static agent responses into rich interactive micro-apps natively rendered in Gemini Enterprise using A2UI.

## Season 1 — December 2025 (Winter Holiday Edition) (`/2025/12/`)

- **Day 01: [Launch Initiative](https://adventofagents.com/2025/12/01?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day01)** ([.md](https://adventofagents.com/2025/12/01.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day01)) — 25 days. Zero to Production-Ready AI Agents on Google Cloud.
- **Day 02: [Hello World with YAML](https://adventofagents.com/2025/12/02?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day02)** ([.md](https://adventofagents.com/2025/12/02.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day02)) — Build your first AI agent with Gemini 3 in under 5 minutes without writing a single line of code.
- **Day 03: [Gemini 3 + ADK](https://adventofagents.com/2025/12/03?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day03)** ([.md](https://adventofagents.com/2025/12/03.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day03)) — Build a powerful AI Agent using Gemini 3 and ADK with native support for Google Search grounding, computer use, and real-time streaming.
- **Day 04: [Source-Based Deployment](https://adventofagents.com/2025/12/04?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day04)** ([.md](https://adventofagents.com/2025/12/04.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day04)) — Deploy your agents directly from source code with Agent Engine - no more serialization headaches.
- **Day 05: [Production Observability](https://adventofagents.com/2025/12/05?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day05)** ([.md](https://adventofagents.com/2025/12/05.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day05)) — Agent Starter Pack includes production-grade observability with zero config. Cloud Trace, Log Analytics, and BigQuery integration out of the box.
- **Day 06: [🧑‍💻 ADK ready in Antigravity, Gemini CLI, Cursor, Firebase Studio and more](https://adventofagents.com/2025/12/06?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day06)** ([.md](https://adventofagents.com/2025/12/06.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day06)) — Building agents shouldn't require an hour of environment configuration. If you use the Agent Starter Pack you already have IDE magnet context baked in for the Agent Development Kit (ADK).
- **Day 07: [LLMs Can Execute Code: Autonomous Problem Solving](https://adventofagents.com/2025/12/07?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day07)** ([.md](https://adventofagents.com/2025/12/07.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day07)) — Explore how LLMs can not only write but also execute, debug, and refine code autonomously, transforming them into powerful problem solvers.
- **Day 08: [Effective Context Management with ADK Layers](https://adventofagents.com/2025/12/08?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day08)** ([.md](https://adventofagents.com/2025/12/08.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day08)) — ADK Context design thesis: context as a compiled view
- **Day 09: [⏪ Undo buttons for your Agents](https://adventofagents.com/2025/12/09?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day09)** ([.md](https://adventofagents.com/2025/12/09.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day09)) — Building an "Edit Message" or "Regenerate" feature shouldn't require complex database migrations. In the ADK, time travel is built-in.
- **Day 10: [Big Context ≠ Better Memory](https://adventofagents.com/2025/12/10?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day10)** ([.md](https://adventofagents.com/2025/12/10.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day10)) — Long-running agent sessions face two enemies: latency and "lost in the middle" syndrome. The ADK solves this with Context Caching and Context Compaction.
- **Day 11: [Google Managed MCP](https://adventofagents.com/2025/12/11?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day11)** ([.md](https://adventofagents.com/2025/12/11.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day11)) — Connect Agents to Google Services with Managed MCP.
- **Day 12: [Multimodal Agents with Gemini Live API](https://adventofagents.com/2025/12/12?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day12)** ([.md](https://adventofagents.com/2025/12/12.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day12)) — Explore ADK Bi-Directional Streaming: A visual guide to real-time multimodal AI agent development with WebSockets and Gemini Live.
- **Day 13: [Interactions API](https://adventofagents.com/2025/12/13?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day13)** ([.md](https://adventofagents.com/2025/12/13.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day13)) — Interactions API marks a fundamental shift from stateless text generation to stateful, autonomous workflows.
- **Day 14: [Connecting Agents with A2A](https://adventofagents.com/2025/12/14?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day14)** ([.md](https://adventofagents.com/2025/12/14.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day14)) — Connect agents across teams, frameworks, and languages with the Agent2Agent (A2A) Protocol. ADK makes implementing A2A simple.
- **Day 15: [Introducing A2UI](https://adventofagents.com/2025/12/15?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day15)** ([.md](https://adventofagents.com/2025/12/15.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day15)) — Discover A2UI (Agent-to-User Interface), an open project that enables agents to stream dynamic, generative UIs as JSONL payloads, decoupling UI definition from rendering and breaking the ceiling of traditional chat interfaces.
- **Day 16: [LangGraph + A2A](https://adventofagents.com/2025/12/16?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day16)** ([.md](https://adventofagents.com/2025/12/16.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day16)) — Build LangGraph agents with full A2A capabilities using Agent Starter Pack. Your agent becomes instantly discoverable by other agents.
- **Day 17: [Gemini 3 Flash is here!](https://adventofagents.com/2025/12/17?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day17)** ([.md](https://adventofagents.com/2025/12/17.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day17)) — Google's fastest model just got smarter with configurable thinking levels and granular controls.
- **Day 18: [Cloud API Registry + ADK](https://adventofagents.com/2025/12/18?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day18)** ([.md](https://adventofagents.com/2025/12/18.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day18)) — The biggest friction in enterprise agent development isn't the model—it's the tools. Vertex AI Agent Builder now integrates with Cloud API Registry, providing a centralized tool repository.
- **Day 19: [Register to Gemini Enterprise](https://adventofagents.com/2025/12/19?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day19)** ([.md](https://adventofagents.com/2025/12/19.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day19)) — Register your agent to Gemini Enterprise! 🌐 and make it discoverable to everyone in your organization, right alongside Google's built-in agents.
- **Day 20: [A2A Extensions: The Flexible Sidecar for Custom Data](https://adventofagents.com/2025/12/20?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day20)** ([.md](https://adventofagents.com/2025/12/20.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day20)) — The Agent-to-Agent (A2A) protocol relies on a strict format, but real-world complexity often requires unique data. A2A Extensions provide a "Sidecar" pattern for custom data without breaking backward compatibility.
- **Day 21: [Kaggle Capstone Winners Highlight](https://adventofagents.com/2025/12/21?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day21)** ([.md](https://adventofagents.com/2025/12/21.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day21)) — 🏆 The Hall of Fame: Meet the Winners
- **Day 22: [Security & Guardrails](https://adventofagents.com/2025/12/22?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day22)** ([.md](https://adventofagents.com/2025/12/22.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day22)) — Prompt Engineering is not a Security Strategy. Asking an LLM nicely to "please ignore PII" is not governance; it's wishful thinking.
- **Day 23: [Durable, Resilient Agents with Google ADK + Restate](https://adventofagents.com/2025/12/23?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day23)** ([.md](https://adventofagents.com/2025/12/23.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day23)) — Most agents are fragile. Durable Execution with Google ADK and Restate ensures your agent never loses context, survives crashes, and can pause execution for days.
- **Day 24: [A2A-ify Anything](https://adventofagents.com/2025/12/24?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day24)** ([.md](https://adventofagents.com/2025/12/24.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day24)) — Take any ADK or LangGraph sample and launch it with A2A on top. Layer A2A capabilities onto existing agents with a single flag.
- **Day 25: [🎉 Grand Finale: Mission Accomplished!](https://adventofagents.com/2025/12/25?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day25)** ([.md](https://adventofagents.com/2025/12/25.md?utm_source=adventofagents&utm_medium=markdown&utm_campaign=adventofagents_s1_2025&utm_content=day25)) — Congratulations! You've successfully completed the 25-day Advent of Agents journey.