What is MCP?
The Model Context Protocol (MCP) is an open standard for connecting AI applications to tools and data through servers that expose capabilities in a consistent way.
Sources: Model Context Protocol
What is an AI agent?
An AI agent uses a language model to plan steps and call tools to reach a goal, as opposed to a single prompt and reply. Agents need guardrails, logging and review.
Sources: Model Context Protocol
How can agents help with Adobe Experience Platform?
They can draft schema or query suggestions, summarise monitoring output and prepare documentation by calling approved APIs, with a person reviewing changes before production.
Sources: Adobe Experience Platform APIs Model Context Protocol
What are the risks of connecting AI to customer data?
Risks include leaking personal data, prompt injection from untrusted content, over-broad permissions and unreviewed changes. Apply least privilege, read-only defaults, logging and human approval.
How do I keep API keys out of the frontend?
Call models from a server or workflow tool, keep keys in environment variables or a secret manager, and never commit them to Git or ship them to the browser.
Sources: Adobe Experience Platform APIs
What is human-in-the-loop?
A design where an agent proposes and a person approves before an irreversible action, such as publishing, sending or deleting.
Sources: Model Context Protocol
How do I evaluate an AI workflow?
Define success cases and failure cases, test with realistic samples, record outputs, and measure accuracy, cost and latency before expanding scope.
Sources: Model Context Protocol
What does the Academy teach about Agentic AI?
The AI Engineering Bootcamp covers LLM fundamentals, tool use, MCP and workflows with MarTech scenarios. See the programme page for the syllabus and fee on request.
Source: Infinite360 Tech Academy programme information.
Ask a question or join a demo
Need help applying this? Ask us via the form WhatsApp +91 82968 93895 LinkedIn: Pavan Babu Gandla
Answers are AI-assisted summaries of Adobe's public documentation and the instructors' practice, written for learning. Product behaviour changes, so confirm details in the linked official page before relying on them.
Last updated: