Agents 101: How AI Agents Actually Work
Understand every part of an agent and know what to change when the output falls short.About
Every time an agent gives you weak work, there is a reason inside the system. The useful skill is knowing where to look.
A practical way to understand an agent is a model operating inside a harness. The harness gives the model instructions, context, files, tools, skills, memory, permissions, time, and ways to check its work. Together, these parts determine what the agent can do and the quality of what it produces.
In this live session, I will take an agent apart piece by piece using products you already know, including ChatGPT, Claude Code, Cowork, and Notion AI. You will see how the parts work together and learn a repeatable way to improve the output.
This session is for people who already use AI and want to understand why agents behave the way they do.
You will leave with:
- A clear mental model of what the model and harness control.
- An understanding of how prompts, context, tools, skills, memory, and evaluation shape the work.
- A diagnostic framework for knowing what to change when an agent gets stuck, misses context, or produces weak output.
Join me live Friday. By the end, you will be able to look inside any agent and know where to improve it.