Lesson 1763 of 2116
Agentic AI: Choose Short-Term vs Long-Term Memory Without Building Both
Most agents do not need a vector database — pick the simplest memory that solves the actual recall problem in front of you.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1The premise
- 2working memory
- 3scratchpad
- 4summarization
Concept cluster
Terms to connect while reading
Section 1
The premise
Teams reach for vector stores too early; scratchpads, summaries, and structured task state solve most agent memory needs with less complexity and clearer behavior.
What AI does well here
- Distinguish working memory, task memory, and durable memory
- Recommend the cheapest store that meets the recall need
- Show when summarization beats retrieval
- Outline a migration path if you outgrow it
What AI cannot do
- Operate your retrieval index
- Decide your privacy retention policy
- Tell you whether your traffic justifies a vector DB
Key terms in this lesson
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “Agentic AI: Choose Short-Term vs Long-Term Memory Without Building Both”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 23 min
Memory Context Fences: Recall Without Injection
Build a memory layer that recalls useful facts while preventing old memories from becoming new user commands. Build the small version Draw or write a fenced prompt layout that includes system rules, user input, retrieved memory, and tool results in separate sections.
Creators · 11 min
Agent Context Window Management: Long-Running Agents
Agents that run for hours hit context limits. Managing context across long-running agents requires explicit design.
Creators · 40 min
Setting Context-Window Budget Policies for Long-Running Agents
How to keep an agent's context window from filling with noise mid-run.