For the past few years, AI has mostly waited for a prompt. You asked, it answered, and you did the rest. That's changing fast. AI agents can now plan a task, use connected tools and apps, take action, check their own work, and keep going until the job is done, and the software businesses already use is building them in. Open standards like the Model Context Protocol (MCP) let agents connect directly to email, files, and business systems, and Gartner forecasts that by 2028, 15% of daily accounting decisions will be made autonomously by AI agents. This session explains what agentic AI is, how it works, and what it means for the way accounting and business teams get work done. This session is about understanding agents well enough to put them to work responsibly. You'll see how an agent differs from the chat assistants and automations you already know, watch agents plan and carry out multi-step work, and learn which tasks are good candidates for agents and which aren't. Just as important, you'll learn how to keep people in charge: what agents should be allowed to access, where a human must approve, and how to start with a small, low-risk pilot. You'll leave knowing where agents fit in your organization and how to take the first step safely.
Who Should Attend
Accounting and finance professionals, firm leaders, and operations managers who've moved past basic AI prompts and want to implement autonomous workflows.
Topics Covered
- From assistant to agent: what changed and why it matters
- How agents work: planning, tools, connectors, and MCP
- Where agents fit: agent-ready work in accounting and business
- Staying in charge: oversight, risk, and running a first pilot
Learning Objectives
- Distinguish between AI assistants, rule-based automations, and AI agents
- Describe how an AI agent plans tasks and uses tools and connectors, including MCP, to act across systems
- Identify accounting and business processes suited to agentic AI
- Evaluate the risks of autonomous AI actions, including data access, errors, and accountability
- Select oversight controls and a pilot approach for introducing AI agents into a team
Level
Basic
Instructional Method
Group: Internet-based
NASBA Field of Study
Information Technology (2 hours)
Program Prerequisites
None
Advance Preparation
None
Instructor
Stephen M. Yoss
Stephen M. Yoss, Jr., CPA, MS, is a certified public accountant, the senior technology strategist and partner of
Devmatics, a continuing education instructor for financial professionals, and a licensed pyrotechnician. While his interests and skills are varied, they all share a common thread—his love for and skill in finding technology-based solutions.
Whether it’s teaching in the classroom, consulting clients in a boardroom, or shooting a fireworks display, Steve brings passion, hard work, value—and above all else—technological expertise to each of his clients. With an open, honest approach, he creates a unique strategy for each client specifically designed to benefit their needs and streamline their operations in order to create efficiency and maximize their financial potential. For more information about Steve, please
click here to visit his personal website.