AX-300 · Lesson 3 of 12 · Module 1: What Makes an Agent · 3:08
Plans and memory
An agent keeps two kinds of notes. Its plan is a written checklist for this run, made before it acts, ticked off and changed when a check fails, so long runs stay on track and a person can see what it intends. Working memory is everything it can see during the run and ends with it; long-term memory is short, dated notes saved for later runs and read at the start of each. Every saved note comes back in every run, so the agent suggests notes and a person approves them: no personal details or secrets, and no outside claim the business’s own pages don’t support. Worked example: the agent featured the same tea three weeks running until dated notes were added, and a review’s false “free shipping” claim was kept out of memory.

What you will learn
- Ask the agent for a plan before it acts
- Tell working memory from long-term memory
- Decide what the agent may remember
The one thing to remember
Write the plan; choose what it remembers.
Common mistake: Letting the agent remember anything it likes
Every saved note comes back in every run, so one wrong or private note does harm again and again, long after anyone remembers where it came from.
The fix: Keep memory notes short, dated and reviewed, with no personal details.
Key terms
- Plan
- The agent’s written checklist of steps for this run.
- Working memory
- What the agent can see in this run; it ends with the run.
- Long-term memory
- Notes saved for later runs, read at the start of each.
Part of AI Agent Builder (AX-300)
For people who run AI workflows: build an agent with the right tools, tests and guardrails, and approvals where it counts.
12 lessons, practice quizzes, a final exam and the Sophyx Certified AI Agent Builder – Professional certificate. Regular price USD 49.99. Your first certification is free. Free with any paid Sophyx plan.
Start the course free