Big picture for Day 2

Day 1 was about what agents are. Day 2 is about how they touch the real world — databases, websites, other software, and even other agents — without writing a separate custom connector every time.

The core lesson: standards beat one-off hacks. When everyone uses the same “plug shape,” tools swap easily, like USB devices.

Concepts you need today

API (Application Programming Interface)

A defined way for one program to ask another program for data or actions. Example: “send this JSON, get weather back.” Agents use APIs to read calendars, query databases, or post messages.

Tool (for an agent)

Any capability you give the agent: run code, search docs, create a ticket, fetch a file. Often exposed as functions the LLM can choose to call.

CLI (Command-Line Interface)

You type commands in a terminal window. No mouse-heavy UI — good for scripts, servers, and repeating tasks. agy in this course is Antigravity’s CLI.

GUI = steering wheel and dashboard. CLI = speaking short precise orders to the machine.

Interoperability

Different products working together because they follow the same rules. Your agent app should not need a totally new integration for every model and every service.

Protocol

An agreed public rulebook for how systems talk. Day 2 introduces several agent-related protocols (MCP, A2A, etc.).

MCP (Model Context Protocol)

A standard way for an AI client to discover and use tools from an MCP server. One MCP server can serve many clients; one client can plug in many MCP servers.

USB-C for AI tools — same connector, many devices.

A2A (Agent-to-Agent)

Agents advertising what they can do and asking other specialized agents to help with subtasks — like delegating within a team.

A2UI (Agent-to-UI)

Agents outputting UI pieces (forms, buttons, layouts) in a safe, structured way instead of random HTML that might be unsafe.

The N×M problem

If you have 5 AI apps and 10 tools and wire each pair manually, you maintain 50 integrations. Protocols reduce that mess to “each app speaks MCP” + “each tool offers MCP.”

Tool categories (not just Google)

Category What it does In this course Same idea elsewhere
AI coding CLI Run an coding agent from the terminal; scriptable and fast for power users. Antigravity CLI (agy) Claude Code, Gemini CLI, GitHub Copilot CLI, Aider
Tool protocol / plug standard Standard socket between AI apps and tool servers. MCP OpenAPI tools, LangChain tools, custom function calling (non-standard)
MCP server Exposes a service (docs, DB, tickets) in MCP format. Google Developer Knowledge MCP Filesystem MCP, GitHub MCP, Postgres MCP, company-internal MCP servers
Multi-agent coordination Agents delegate work to other agents. A2A (concept) CrewAI crews, AutoGen groups, OpenAI Swarm patterns
Generative UI UI adapted to the user or task. A2UI (concept) Custom React from LLM, Vercel v0 UI output (with your own safety rules)

Podcast

Whitepaper Companion Podcast: Agent Tools & Interoperability youtube.com/watch?v=GjjKXqxFTOY

What you will get from it: Why open protocols matter for vibe coders, and how they let you assemble a “virtual team” of tools without drowning in custom glue code.

Whitepaper

Agent Tools & Interoperability kaggle.com/whitepaper-agent-tools-and-interoperability

Main ideas: MCP for tools, A2A for agent teams, A2UI for interfaces, and commerce protocols (UCP/AP2) for shopping and payments with human approval on money moves.

Codelabs

Codelab 1: Get started with Antigravity CLI codelabs.developers.google.com/antigravity-cli-hands-on

Concept practiced: Terminal-based agent use — permissions, models, interactive vs one-shot prompts (agy -p "...").

Transferable skill: Every AI CLI has trust folders, model pickers, and permission modes; learn to read those settings anywhere.

Codelab 2: Google Developer Knowledge MCP in Antigravity codelabs.developers.google.com/developer-knowledge-mcp-antigravity

Concept practiced: Wiring an MCP server into a client via config file — API key, server URL, refresh, test with prompts.

Transferable skill: Same steps for any MCP host (Cursor, Claude Desktop, VS Code MCP extensions): add server entry → authenticate → verify tools appear.

Livestream

Day 2 Livestream (~53 min) youtube.com/watch?v=PGI_S59EoRA

Experts explain MCP in production, database security for MCP, and personalized UI futures. Includes codelab demos and a pop quiz.

Bonus course links

Supported Google MCP products docs.cloud.google.com/mcp/supported-products Google MCP GitHub repo github.com/google/mcp

Check yourself