Is the AI Agents Academy completely free?

Yes, 100% free. No sign-up, no credit card. All 13 modules, 58 lessons, 9 terminal labs, and 115 quiz questions are accessible immediately. Your progress saves locally in your browser.

How is Infinity AI Agents Academy different from vendor-locked agent courses?

Unlike single-framework platforms (such as LangChain Academy or CrewAI University) that tie you to a single proprietary ecosystem, Infinity Tech Stack's AI Agents Academy is a 100% free, vendor-neutral engineering curriculum. It teaches the complete production stack across ReAct loops, LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, A2A protocol, and Model Context Protocol (MCP) integration with in-browser terminal labs and zero sign-up required.

What topics does the AI Agents Academy cover?

The course covers agent fundamentals, ReAct loops, Plan-and-Solve, tool use & function calling, MCP integration, Agentic RAG, multi-agent systems (CrewAI, LangGraph), A2A protocol, Google ADK, agent memory, safety & guardrails, red teaming, CI/CD for agents, and production observability.

What is the A2A protocol?

A2A (Agent-to-Agent) is Google's open protocol for enabling interoperability between AI agents. It allows agents from different vendors and frameworks to discover each other, exchange capabilities via Agent Cards, and delegate tasks securely.

Google ADK (Agent Development Kit) is an open-source framework for building, orchestrating, and deploying AI agents. It supports Python, Go, Java, and TypeScript, and integrates with MCP for tools and A2A for agent-to-agent communication.

Do I need any prerequisites?

Basic programming knowledge is helpful but not required. The course starts from absolute fundamentals (what is an agent?) and progressively advances to expert-level topics like multi-agent orchestration and production safety.

Does the AI Agents Academy include hands-on labs?

Yes. Hands-on terminal labs are built into the lessons - build the minimal agent loop, scaffold a CrewAI crew, and launch LangGraph dev using real, vendor-verified commands, with objectives, hints, solutions, and XP rewards. No sign-up or setup needed.

What does the 'MCP Apps' extension enable?

Interactive UI elements like charts, forms, and video players rendered inline within conversations — MCP Apps let a server return interactive widgets, not just text or JSON, so tool results can be rendered as rich, clickable UI inside the conversation.

How do MCP extensions like Tasks, Skills over MCP, and MCP Apps get adopted without breaking older clients?

They are opt-in and explicitly negotiated between client and server during initialization — Extensions are always optional and negotiated during the initialization handshake - a client or server that doesn't support one simply doesn't use it, so the core protocol stays backward compatible.

MCP Spec 2026-07-28: Tasks, Apps & Skills Tutorial | Tool Use & Function Calling

[ ABORT TO HUD ]

SEQ. 1

SEQ. 2

SEQ. 3

SEQ. 4

SEQ. 5

SEQ. 6

MCP Spec 2026-07-28: Tasks, Apps & Skills

🔧 Tool Use & Function Calling⏱ 10 min⭐ 90 BASE XP⌨ HANDS-ON LAB

MCP's Newest Extensions

MCP is a living standard, and its specification is dated by revision. The current revision - 2026-07-28 - is published at modelcontextprotocol.io/specification/2026-07-28. Beyond the core protocol (Tools, Resources, Prompts), MCP now defines optional extensions: modular capabilities that both client and server must explicitly negotiate per-request via _meta and server/discover before they take effect (Spec 2026-07-28 stateless core).

Three Notable Extensions

Extension	What It Adds	Why It Matters
Tasks	Asynchronous execution of long-running operations, with polling, mid-flight input, and durable handles	A tool call that takes minutes (e.g. a deep research job) no longer has to block the connection - the client polls a durable task handle instead.
Skills over MCP	Rich, structured instructions for agent workflows, discovered and consumed through MCP	Lets a server publish reusable "how-to" playbooks, not just single tools, that an agent can discover and follow.
MCP Apps	Interactive UI elements (charts, forms, video players) rendered inline within conversations	Tool results stop being plain text/JSON - a server can return an actual interactive widget the user can click.

Because extensions are opt-in and negotiated at connection time, a client that doesn't understand Tasks or MCP Apps simply ignores them - older clients and servers keep working exactly as before.

💡 Key Insight: Extensions are how MCP evolves without breaking changes. Instead of bumping the whole protocol for every new idea, experimental capabilities ship as opt-in extensions first - Tasks, Skills over MCP, and MCP Apps are the first three to reach the specification.

⌨ HANDS-ON LABNegotiate MCP 2026-07-28 Extension Capabilities

⭐ +150 XP

Query an MCP server supporting the 2026-07-28 specification revision to negotiate and inspect experimental Tasks and Skills extensions.

1Send a stateless MCP discovery request declaring support for the Tasks extension.

lab-sandbox — simulated environment

INFINITY LAB SANDBOX v2.6 — simulated shell
Type the command for the current objective. Helpers: "hint", "solution", "clear".
$

OBJECTIVE 1 / 1 — type "hint" if stuck

SYNAPSE VERIFICATION

QUERY 1 // 3

What is the purpose of the MCP 'Tasks' extension?

Faster JSON parsing

Asynchronous execution of long-running operations with polling and durable handles

Encrypting tool arguments

Replacing Resources